模型定价

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.26423v1 Announce Type: new Abstract: This paper proposes a framework for constructing a classifier as a safeguard layer, and for developing a complementary diagnostic that identifies which of the classifier's confident decisions can be trusted. This framework, the Latent Diagnostic Taxonomy, consists of (i) constructing a dimensionality-optimized classifier, in which the embedding dimensionality is empirically selected via cross-validated performance rather than fixed a priori, (ii) locating a relatively small set of latent support vectors (~ 29% of total training examples) representing influential prompts for identifying tokens that alter the classifier's predicted labels, and (iii) utilizing such tokens and their associated attack magnitudes for constructing a diagnostic taxonomy. This diagnostic taxonomy provides an end-to-end guideline for flagging prompts that require different treatments: rely Safely on the classifier's decision; flag Heuristic Bias and Heuristic Override cases; route Insufficient Context cases for further human/safety review. Applying the framework to a classifier trained on a public prompt injection dataset, we find that a substantial fraction of its confident decisions (~ 77%) are not robust to removing a single token, and that this brittleness separates into two distinct failure patterns: a confidence calibration failure and a genuinely exploitable shortcut. For each zone of the taxonomy, we also recommend strategies for remediating diagnosed prompts. We illustrate the framework as a series of steps, demonstrating how each step operates.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.26132v1 Announce Type: new Abstract: Labeled property graphs combine relational structure with heterogeneous textual and categorical properties attached to both nodes and relationships. Conventional graph neural networks typically represent these properties as static feature vectors, limiting their ability to determine which semantic evidence should influence message propagation for a particular prediction target. We propose SLM-Conditioned Hierarchical Relation Routing, an architecture that integrates a small language model directly into graph message selection. A topology GNN provides a stable structural representation and prediction anchor. For each target node, incident messages combine the neighbor's structural state, node-property encoding, relationship-property encoding, and relationship type. A parameter-efficient SLM processes structured graph soft tokens and produces a target-conditioned routing query. This query first selects relevant messages within each relationship type and subsequently routes information across relation-level summaries. The resulting representation provides a bounded residual update to the topology anchor, preserving structural evidence while allowing contextual semantic information to modify the prediction. The architecture supports interpretable analysis at both the neighbor and relationship-type levels and provides a general mechanism for integrating language-derived semantics into property-rich graph learning.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.26145v1 Announce Type: new Abstract: Our research focuses on evaluating literature reviews generated in short and long context settings of large language models (LLMs) to investigate the impact of context window on the quality of AI-generated literature reviews and the role of AI in supporting literature review writing. Twenty AI-generated literature reviews based on research sources from Semantic Scholar and Arxiv were evaluated by two researchers across 15 dimensions. Our findings reveal that AI-generated literature reviews require human oversight to meet academic publishing standards. As context windows increase, LLMs can incorporate broader information and maintain coherence across longer inputs, but they also exacerbate issues such as content repetition, omission of critical work, and a tendency towards descriptiveness over synthesis. Our work shows that AI-generated reviews can provide foundational overviews, but their output must be critically evaluated and refined by domain experts. Future research should consider integrating other LLMs and fine-tuned models in different domains with hybrid approaches that combine human expertise with AI capabilities to address the limitations identified in this study.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.24959v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models encode visual observations as flat 2D patch tokens that carry no intrinsic geometric structure, and augmenting them with dense monocular depth injects per-pixel scalar values that encode neither surface orientation nor geometric confidence. This leaves the policy with limited structured spatial reasoning for action prediction. We propose GaussVLA, a Mamba-based VLA that incorporates two custom modules: Gaussian Spatial Tokenizer (GST) to lift frozen semantic and depth features into compact 3D Gaussian tokens, pools geometrically salient regions with learned queries, and \emph{Depth-Aware Chain-of-Thought (DA-CoT)} that performs structured, non-autoregressive geometric reasoning under language and flow-time conditioning. Across both simulation and real-world evaluations, GaussVLA demonstrates strong spatial-manipulation performance while remaining parameter-efficient. On LIBERO, it achieves 93.5% average success and 100.0% success on the Spatial suite with only 200M parameters, improving over SpatialVLA by 19.7% relative average success while remaining significantly more parameter-efficient.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.25168v1 Announce Type: new Abstract: In multi-view anomaly detection, more cross-view information can actually hurt. When multiple inspection views are naively fused in a reconstruction-based pipeline, normal cues from intact views propagate to the decoder, which faithfully reconstructs anomalous regions, collapsing the reconstruction gap the detector depends on. We call this failure mode \emph{cross-view information leakage} and show that effective multi-view fusion must explicitly restrict the information reaching the decoder. Building on this insight, we present GLAD(Global-Local Attention Driven framework), the first framework combining vision foundation model features with local and global cross-view fusion for multi-view anomaly detection. The Multi-view Merging Attention (MMA) module performs local cross-view fusion at linear complexity with learnable view importance weighting and token-wise gating, letting each view selectively incorporate fine-grained evidence from other views at $\mathcal{O}(N)$ cost. The Object-Guided Attention (OGA) module captures global context by aggregating class tokens from all views into a single object-level representation and broadcasting it back to patch tokens via temperature-scaled sigmoid gating, replacing the original patch representations rather than adding a residual to preserve the reconstruction gap. Experiments on Real-IAD and MANTA-Tiny show that GLAD outperforms state-of-the-art methods across sample-, image-, and pixel-level metrics, confirming that principled information restriction is key to multi-view anomaly reasoning.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.24966v1 Announce Type: new Abstract: Vision-language models such as LLaVA-1.5-7B often hallucinate objects absent from the image when generating captions. We ask whether an interpretability diagnosis of this failure can guide a targeted fix, and we measure what that fix actually changes. We rank attention heads by how much their image attention drops around hallucinated object words, then screen the shortlist by ablating candidate heads and measuring the change in hallucination-token log probability, yielding a 32-head set. We restrict two interventions to these heads: a head-sliced LoRA adapter and an inference-time grounding controller. On 400 held-out COCO images, the combined method lowers CHAIRs (the fraction of captions with a hallucinated object) from 0.370 to 0.230 and CHAIRi (the fraction of hallucinated object mentions) from 0.156 to 0.096 (p < 0.001, paired sign-flip tests). Two controls sharpen attribution. A random-head LoRA control, matched layer-for-layer and trained identically, performs no better than the matched baseline on a separate 200-image control split, supporting the role of head selection rather than LoRA capacity. Under fixed decoding budgets, the CHAIR reduction persists and grows with budget (23% at 64 tokens to 58% at 128), arguing against a pure max-token or truncation artifact, although the method remains shorter and more conservative. The resulting behavior reduces unsupported object mentions while also lowering object recall (0.78 to 0.70). We present a diagnosis-to-intervention pipeline for object hallucination, and, more importantly, a controlled account of what acting on the diagnostic signal actually does: it localizes intervention sites with real, non-random leverage, reported as a behavioral profile rather than a single score.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.24952v1 Announce Type: new Abstract: Systematic dialectal performance gaps in language models (LMs) are well documented, but the source of these disparities within the modern language modeling pipeline remains unclear. Our study traces this "dialect tax" across the natural language processing pipeline. Using parallel English dialect corpora that hold meaning fixed while varying surface form, we first confirm that LMs recognize matched Standard American English (SAE) and dialectal texts as semantically equivalent. However, we discover further representational gaps corresponding to downstream performance gaps. Across model families and generations, modern LMs still encode dialectal texts unequally during tokenization, pre-training, post-training, and inference. Strikingly, bypassing traditional subword segmentation via a character-level counterfactual tokenizer removes neither input and output asymmetries nor dialectal accuracy gaps. During pre-training, dialect pairs induce more divergent gradient updates than pairs of entirely unrelated SAE documents, indicating that models find semantically equivalent dialectal content harder to learn from than unrelated SAE documents. During post-training, reward models show contextual, unstable dialect preferences, assigning higher values to isolated AAVE-exclusive tokens than to SAE-exclusive tokens, while full reasoning contexts receive task- and model-dependent dialect penalties. Overall, our findings suggest that the dialect tax is encoded and accumulated not by any one step in isolation, but at every step of the language modeling process.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：<p><strong><a href="https://qwen.ai/blog?id=qwen3.8-flash-next">Qwen3.8-Flash-Next</a></strong></p> Another open weights model from Qwen. This one is "a multimodal MoE model that also serves as an early preview of the architecture used in Qwen4".</p> <p>It's pretty big: 125B tokens, but only 6B active which means it gets a pretty big performance boost.</p> <p>I've been trying it out on a DGX Spark using <a href="https://huggingface.co/unsloth/Qwen3.8-Flash-Next-GGUF">these Unsloth quantized models</a>. I'm still exploring the model - so far I've tried the 72.5GB UD-IQ1_S one (producing <a href="https://tools.simonwillison.net/markdown-svg-renderer#url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Ff9c69ebdab90d8a45b8de4742cc7b840">these pelicans</a>) and the 78.9GB UD-Q2_K_XL (producing <a href="https://tools.simonwillison.net/markdown-svg-renderer#url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F6ba7cbfc1a9336986703b41f7fccd73a">these</a>).</p> <p>My favorite so far was this xhigh reasoning effort one from UD-Q2_K_XL:</p> <p><img alt="Flat vector illustration: a white pelican with an orange beak and orange legs rides a red bicycle along a sandy path, a wicker basket on the handlebars holding a blue fish, with green rolling hills, a small tree and bushes, white clouds and a bright yellow sun in a blue sky behind it" src="https://static.simonwillison.net/static/2026-08-27/IMG_7667.png" /> <p><small></small>Via <a href="https://news.ycombinator.com/item?id=49448210">Hacker News</a></small></p> <p>Tags: <a href="https://simonwillison.net/tags/ai">ai</a>, <a href="https://simonwillison.net/tags/generative-ai">generative-ai</a>, <a href="https://simonwillison.net/tags/llms">llms</a>, <a href="https://simonwillison.net/tags/qwen">qwen</a>, <a href="https://simonwillison.net/tags/pelican-riding-a-bicycle">pelican-riding-a-bicycle</a>, <a href="https://simonwillison.net/tags/ai-in-china">ai-in-china</a>, <a href="https://simonwillison.net/tags/nvidia-spark">nvidia-spark</a></p>

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Z.ai has released GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series — a 320B-total / 18B-active MoE with a 1,048,576-token context window, MIT-licensed weights on Hugging Face, and API pricing at $0.15/M input and $0.50/M output. It scores 84.3 on Terminal-Bench 2.1 and 63.4 on DeepSWE v1.1, using hybrid KDA linear plus NoPE sparse MLA attention to cut attention compute ~3× and KV cache 4.4× versus GLM-5.3. The post Z.ai Releases GLM-5.3-Flash: A 320B-A18B Natively Multimodal MoE With a 1M-Token Context appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：We look at Qwen3.8-Flash-Next, Alibaba's open-weight multimodal Mixture-of-Experts model and an early preview of the Qwen4 architecture. We break down where the 180B parameters actually sit: a 125B backbone, a 51B N-gram embedding table, and a 4B multi-token prediction module, with only 6B active per token. We walk through the four architectural changes — the Gated DeltaNet and Qwen Sparse Attention hybrid, Gated Residual, N-gram Embedding, and the Muon optimizer. We also cover the benchmark results, the reported 1/9 training cost against Qwen3.7-Plus, and what self-hosting a 172.78 GiB FP8 checkpoint really demands. The post Alibaba’s Qwen Team Releases Qwen3.8-Flash-Next: A 125B Multimodal MoE With 6B Active Parameters Previewing the Qwen4 Architecture appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.23626v1 Announce Type: new Abstract: Foundation models for astronomy are trained on survey pixels together with the catalogue products derived from those pixels. Those catalogues are incomplete at a measurable rate, and a model trained on both inherits that incompleteness as a systematic. We audit AION-1, a 39-modality transformer trained on more than 200 million objects, using causal interventions on its inputs. Holding the image tokens byte-identical and editing only the survey segmentation map changes every quantity the model reports -- flux, size, ellipticity, redshift -- by 110-4400 times a matched placebo. The mechanism is detection gating, presence at the field centre (r = 0.47), not the light the mask encloses (r = 0.30); across 322 real blends the model ignores how the pipeline partitioned the light (R = -0.006). Nor is the preference specific to that channel: contradicted catalogue photometry leaves the model nine times worse than supplying no metadata at all. The Legacy Survey pipeline leaves 3.68% of targets with no segment covering their position. Propagating that rate, with a miss represented by the fields the pipeline actually returns, shifts tomographic mean redshifts by a median 0.71 times the LSST DESC requirement over 40 assignments and exceeds it in 12; observed positional errors take the worst bin to 8.3 times. Drawing the misses by their measured magnitude dependence rather than uniformly does not change it. Spectroscopy removes the effect, withholding the detection channel removes it at no measurable cost, and the effect grows with model scale. Two further limits lie in the tokeniser: its image codec resolves 28 effective states on source patches against 934 for the spectrum codec, and the redshift readout is quantisation-limited. Sparse dictionaries are unreliable causal handles: across 15, recovery spans 26-75% and moves up to 18 points on the seed alone.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.21415v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases from their training data, resulting in biased behavior when processing portraits from different social groups. Existing debiasing approaches typically compare token probabilities between the original and biased generations during decoding, but they are fundamentally limited by their reliance on a single, stereotyped viewpoint and fail to account for the diversity of social perspectives. Inspired by the social science principle that diversity fosters fairness, we propose Counterfactual Ensemble Decoding (CED), a novel framework that constructs multi-group counterfactual perspectives within the visual representation space and integrates them during decoding to promote equitable model behavior. CED first performs counterfactual steering in the visual space by identifying semantic directions associated with each social group and generating counterfactual representations along these directions, thereby offering diverse perspectives that disrupt stereotypical narratives. During decoding, CED locates the decoder layer exhibiting the greatest divergence among these perspectives and ensembles their token distributions using uncertainty-aware weights, prioritizing high-confidence tokens from different groups to yield a more balanced probability distribution that guides fairer generation. Extensive experiments on three social bias evaluation benchmarks demonstrate that \tool achieves substantial improvements over leading baselines, reducing bias by up to 47.97% across scenarios involving occupations, descriptors, and persona traits. Moreover, CED also preserves the core capabilities of the original model with minimal degradation.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.21375v1 Announce Type: new Abstract: Heterogeneous agentic retrieval-augmented generation (RAG) systems increasingly orchestrate external APIs, internal databases, vector stores, and graph stores. Exposing all tool descriptions to an LLM agent, or selecting tools only by vector similarity, causes two costly failures: over-fetching, which increases payload size, token use, and latency, and under-fetching, which omits fields needed to answer the query. We present SchemaRouter, a lightweight routing layer that represents tools, endpoints, parameters, response fields, domain concepts, units, provenance, and license policies as a schema graph. Given a query, SchemaRouter emits an executable tool plan specifying which tools to call and which fields to retrieve. A small LLM extracts intent, concepts, and source constraints, while field selection is deterministic over the graph through intent-group projection and concept-field matching with an alias layer. On a materials-science benchmark of 110 queries, SchemaRouter achieves answer accuracy of 0.71, matching fetch-everything within overlapping confidence intervals and exceeding prompt-all's 0.66, though their intervals overlap. It uses 227 retrieved-context tokens versus 2,066 for fetch-everything and achieves 2.7x lower end-to-end latency than prompt-all. It also obtains the best tool-exact rate of 0.93 and parameter validity of 1.0. SchemaRouter grounds provenance and license information in 62 percent of answers, compared with approximately 0 percent for all baselines. We also find that minimizing selected-field count is counterproductive: it reduces answer accuracy to 0.56 with negligible token savings, while recall-preserving projection restores top accuracy. SchemaRouter improves efficiency, schema-size-independent scaling, and verifiable provenance/license-grounded answering at competitive accuracy.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.21362v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) incur high prefill latency because key-value (KV) tensors must be recomputed for each request. Existing prefix-caching systems reduce this cost but require prompts to share a leading contiguous prefix, limiting effectiveness when shared content appears at arbitrary positions. We present KVBoost, a chunk-level KV cache reuse system for HuggingFace-compatible decoder models that enables reuse regardless of content position. KVBoost introduces a dual-hash keying scheme that separates positional identity (prefix hash) from content identity (content hash), supporting both exact and approximate cache matches. To address attention boundary errors from independently cached chunks, KVBoost employs two repair strategies: SelectiveRecompute, which re-encodes boundary regions, and CacheBlendRecompute, which identifies and recomputes high-deviation tokens after a probe pass. The system further incorporates asymmetric KV quantization (int8/int4), adaptive chunk boundary splitting, and importance-weighted eviction under a fixed memory budget. Evaluated on Qwen/Qwen2.5-3B over 1,000 bug-localization samples, KVBoost achieves a 4.49x reduction in time-to-first-token (142.4 ms vs.\ 639.1 ms) and outperforms prefix caching by 16%, with no loss in accuracy (99.2% vs.\ 99.1%). KVBoost provides a practical, memory-bounded inference acceleration layer compatible with RoPE-based models without architectural modification.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Generalist AI has released GEN-1.5, a robot foundation model that learns a new physical task from a single demonstration. Drop 3–12 seconds of sensorimotor data into its 30-second context window, and the robot performs the task. No gradient updates, no fine-tuning, no task-specific programming. Across 10 diverse manipulation tasks, this one-shot in-context prompting averaged 59% […] The post Generalist AI Releases GEN-1.5: A Robot Foundation Model That Learns New Tasks From One 3–12 Second Demo appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Moonshot AI’s Kimi K3 is a 2.8-trillion-parameter open-weight model built with a Mixture-of-Experts architecture. It activates only a small fraction of its parameters per token, helping reduce inference costs while delivering strong coding and agentic performance. K3 combines near-frontier capabilities, open weights, and lower API pricing, making it an interesting alternative to proprietary models. In […] The post How to Use Kimi K3: Moonshot AI’s 2.8T Open-Weight Model appeared first on Analytics Vidhya.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.20348v1 Announce Type: new Abstract: Electronic health records now routinely exceed 100,000 tokens per patient. Yet large language models exhibit the lost-in-the-middle (LitM) effect: information near the center of a long context is retrieved less reliably than information near the edges. In clinical use this is not benign: the single most consequential fact in a note can sit at its center. We term this the clinical lost-in-the-middle (CLitM) problem, give its first systematic characterization using MedAlign, and compare context-selection strategies as remedies. Across 2,196 instruction-response pairs and six language models, we observe a 21.9 percentage-point gap between peak accuracy (59.5%, 95% CI [46.3, 71.0], 20-30% decile) and trough accuracy (37.6% [23.2, 52.5] at 70-80%); 67.8% of reference answers fall between the 10th and 90th percentiles of the EHR timeline, inside the CLitM trough. We introduce Query-Conditioned Clinical Suppression (QCCS), a lightweight query-conditioned selection gate, and evaluate it against BM25, BM25 with section-header filtering, dense retrieval, and cross-encoder reranking (N=83 held-out instructions). With Qwen2.5-7B-Instruct (16k context), QCCS outperforms all five comparators under LLM-as-judge scoring: for middle-position instructions QCCS reaches 16.7% versus BM25 3.3%, cross-encoder 0.0%, dense 0.0%, and full context 6.7%; overall QCCS reaches 25.3% versus at most 3.6% for retrieval-only comparators. This advantage is not explained by retrieval recall: at k=20, BM25 retrieves the gold evidence sentence in 98.8% of instructions (QCCS 34.9%), yet retrieval arms stay at most 2.6% accurate even when they retrieve it, whereas QCCS reaches 25.0% even when it does not. In this proof-of-concept evaluation, query-aligned context selection predicts EHR instruction-following accuracy better than gold-sentence retrieval recall.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.20427v1 Announce Type: new Abstract: Dense causal attention remains expensive at long context even when implemented with highly optimized exact kernels. We study BF1, a deterministic block-aligned dyadic sparse-attention route that combines a small exact local neighborhood, a global first block, and logarithmically spaced historical blocks. The route is related to prior log-sparse and dilated attention patterns; our contribution is a correctness-gated pretrained-model retrofit, a matched topology-control study, and a systems characterization that connects per-layer sparsity to whole-model latency. For fixed block width, every converted layer uses O(n log n) selected token interactions and has O(log n) graph communication depth. On an NVIDIA RTX PRO 6000 Blackwell GPU, an optimized BF16 implementation crosses dense attention between 2K and 4K tokens and reaches a 10.91x per-layer prefill speedup at 32K. Retrofitting eight of 28 Qwen3-0.6B attention layers lowers warm whole-model time to first token by 7.7%, 11.3%, and 15.3% at 8K, 16K, and 32K, respectively, while the remaining dense layers keep the complete model asymptotically quadratic. Under a matched 1,000-step, 16.384M-token adaptation protocol, BF1 ranks first across three training seeds: mean report perplexity is 1.68639 versus 1.69154 for a matched static-random nonlocal graph, 1.69258 for dense continued training, and 1.81505 for equal-budget local sliding. At seed 1234, the packed-report paired interval places Dense-CT 0.3169-0.4055% above BF1 and static-random graph 17 0.2441-0.3642% above BF1. These results establish BF1 as a reproducible sparse operator and selective retrofit primitive with real long-context systems value. This paper evaluates numerical correctness, selected-interaction scaling, kernel performance, partial-model inference, and matched next-token language modeling.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.20397v1 Announce Type: new Abstract: Agentic large language models (LLMs) on the Model Context Protocol (MCP) re-encode verbose tool schemas every turn, so prefill - quadratic in sequence length - dominates time-to-first-token (TTFT) as the tool registry grows. Nexus's primary lever is to decouple routing from the schema-prefill cost: an INT8 semantic lookaside buffer (SLB) with a calibrated cross-encoder margin gate selects tools by retrieval, and arguments are generated over a compressed textual signature (median 19 tokens) rather than over spliced key/value (KV) cache. This path is depth-independent: routing accuracy stays near 89% as the registry scales to 250 tools - where a concatenate-all-schemas baseline overflows the context window entirely - and it reaches a first-argument token 1.66x sooner than a full-schema re-prefill at a ~80% main-context token saving. As a secondary, bounded lever we transplant a compiled schema KV block directly into the live context. This is fundamentally limited by rotary position embedding (RoPE) phase drift: an anchored splice is output-exact, but off-anchor placement corrupts attention, so beyond a threshold P=256 Nexus repairs the seam with a depth-adaptive suffix redecode that escalates to a full re-prefill. The resulting never-regress property is a guarantee on output fidelity (top-1 agreement, D_KL approx. 0) - not on latency, which can dip to 0.98x before converging to parity - alongside a 1.1-1.7x TTFT speedup at moderate depth that narrows to parity at deep context. Two negative results bound the design: the off-anchor RoPE fidelity boundary, and the failure of a reference-free drift gate to predict drift (Spearman rho = 0.193). All measurements are from one model tuple (Qwen2.5-14B-Instruct Q4_K_M) on Apple-silicon unified memory; the qualitative boundaries generalize, while the quantitative envelope is tuple-specific.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.20384v1 Announce Type: new Abstract: Multimodal affect and behaviour classifiers that fuse heterogeneous text, audio, and visual streams must simultaneously achieve competitive accuracy and produce human-understandable explanations of the cues driving their decisions -- a dual objective that current high-capacity models, notably Transformers, only partially address. While Transformers attain strong predictive performance, their distributed representations and deep nonlinearity make it difficult to assign meaningful importance weights to individual multimodal features, limiting their use in trust-sensitive applications such as clinical affect monitoring and educational assessment. We address this gap by developing a framework based on tree-based ensembles that balances accuracy and interpretability. The framework encodes each modality into tokens, extracts and clusters concepts to reduce dimensionality, routes the fused modalities through tree-based ensemble classifiers, and interprets trends using a novel modified feature importance metric. The modified importance reduces the influence of the negative class in binary classification tasks, thereby improving indicator or marker detection. The proposed tree-based ensembles -- Linear Discriminant Tree (LDT), Linear Discriminant Forest (LDF), and Linear Discriminant AdaBoost (LDAB) -- achieve F1-mod gains of 4.3\% over the Multimodal Transformer and accuracy gains of 3.0\% over the primary interpretable multimodal baseline, Interpretable Multimodal Routing (IMR). The proposed multimodal feature importance extracts salient inter-modal concepts with substantially higher human-annotator agreement scores than default feature importance (62.2\% vs.\ 43.2\% on IEMOCAP; 46.7\% vs.\ 32.1\% on CMU-MOSI).

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.20342v1 Announce Type: new Abstract: Large language model (LLM) coding agents start each session with an empty context window, discarding accumulated knowledge from prior work. We present PrimeAgentOrchestrator (PAO), a system that spawns new instances of Claude Code -- Anthropic's terminal-based coding agent -- pre-loaded with relevant memories compiled from the user's existing personal databases. At spawn time, PAO queries two independently-operated memory backends in parallel (a PostgreSQL entity-observation database and a Cloudflare Worker semantic search index), fuses results using backend-specific retrieval strategies, and delivers the compiled briefing via filesystem injection that exploits the host agent's configuration auto-read behavior. PAO manages the full agent lifecycle including trust pre-seeding, readiness polling with error detection, and adaptive terminal text injection. We report on four months of regular deployment (December 2025 through March 2026) as an experience report, documenting three generations of context delivery mechanisms, the failure modes that motivated each redesign, and the engineering tradeoffs of bridging heterogeneous memory systems rather than building a unified one.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.20341v1 Announce Type: new Abstract: Frontier coding agents backed by large language models with context windows from hundreds of thousands to millions of tokens are restructuring the Software Development Life Cycle (SDLC). Rich context handling and multi-step reasoning now allow substantial Functional Requirement Documents (FRDs) and repository context to be ingested in a single workflow, making specification quality the execution fuel for autonomous delivery. This report formalises Spec-Driven Agentic Development (SDAD) as a synthesis of disciplined up-front formalisation and high-velocity implementation: intent capture, machine-readable specification, agentic synthesis, and independent multi-agent verification under human sign-off. We revisit the historical pendulum between Waterfall and Agile, introduce AI-code as a fourth production paradigm, and compare Human-Agile (circa 2020) with Agentic-SDAD (circa 2026) across artefacts, cadence, accountability, and security posture. Beyond process description, we extend the model to team role metamorphosis (engineer, QA, platform, and product functions), quantitative governance (Ambiguity Tax, Spec Fidelity, SER, and TCI_agentic with repair multiplier phi), and pragmatic adoption via hybrid estimation and a staged migration blueprint. Industrial and research evidence on AI-augmented testing and verification is integrated to motivate separation between synthesis and release authority. Overall, the paper argues that agentic speed does not eliminate engineering discipline; it relocates discipline upstream into specification precision, explicit gates, and auditable provenance.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：We burned 11.7bn tokens to find the best cyber AI model GLM5.3 and DeepSeek are now frontier-tier models Debarshi Philippe Dourassov Published on: Aug 21, 2026 We burned 11.7 billion tokens to benchmark the cyber capabi…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Modern LLMs rely on quantization, pruning, distillation, and faster attention kernels, but production performance often depends most on KV cache management. As context windows grow, the cache consumes significant GPU memory, limiting concurrency, throughput, and latency. Two breakthroughs transformed this challenge: PagedAttention improves memory allocation, while RadixAttention enables efficient prefix reuse. Together, these techniques make […] The post PagedAttention vs. RadixAttention: Optimizing LLM KV Cache Management appeared first on Analytics Vidhya.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Free preview available. Sign in and subscribe to unlock the full book. Vizuara AI Labs · advanced Pretraining a Mini Kimi K3 One H200, five billion tokens, $252.35 — the complete worklog of a Kimi K3 replica trained fro…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.19285v1 Announce Type: new Abstract: Recent Visual-Language Models (VLMs) have enhanced the capabilities of pre-trained LLMs by adding vision tokens alongside text, with approaches like LLaVA showing impressive results. However, the computational burden of processing up to 576 or 729 visual tokens makes edge deployment challenging. While various token pruning techniques require retraining, some are training-free and thus can easily adapt to architecture changes. We introduce ClustRS, a two-part, training-free algorithm for robust token pruning. Its first component is an attention-weighted, clustering algorithm that selects representative tokens from each semantic cluster. The second component, Residual Shrinkage, is a one-pass denoising step on the selected tokens. These training-free lightweight steps make LLaVA ready for real-world data, improving robustness to a wide range of image-noise types and intensities. Experimental results on the ScienceQA-IMG and MM-VET benchmarks show our method outperforms attention- and diversity-based methods by up to 20\% under extreme noise and token conditions (reducing tokens by 97\%, down to 16 tokens) on LLaVA 1.5 7b and achieves exceptional results on LLaVA-OneVision, where we match baseline performance with fewer than one-third of their tokens under mild noise conditions. Our study demonstrates a simple yet powerful alternative to both score-only and diversity-only pruning rules, paving the way for compute-efficient and noise-resilient VLM deployment.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.19202v1 Announce Type: new Abstract: Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed with a default assumption or spend tokens on a clarifying question, retrieval call, tool call, or prompt trial. We formulate this tradeoff as active inference for context acquisition. An inner inference step updates beliefs over a latent task state, and an outer decision selects the next context action, task action, or stop action to minimize expected free energy under cost. In deterministic settings, the epistemic term reduces to expected information gain, optionally normalized by token cost. We instantiate the framework in Optimal Question Asking (OQA), with exact posteriors and a dynamic programming oracle, and benchmark frontier language models on binary and multiway categorical tasks from 25 to 300 candidates. We also study clarification before generation and automated prompt optimization under token budgets. The formulation is model-agnostic and views active inference as a design principle for the context-acquisition layer of AI agents.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.18215v1 Announce Type: new Abstract: Existing 3D relighting methods operate through either explicit material decomposition, diffusion-based view-space generation, or a combination of both, requiring full recomputation for each new lighting condition. We observe that recent latent scene representations, which encode multi-view images into a set of compact tokens with no fixed physical semantics, open up a novel design space for relighting. We present LumiTokens, a framework that formulates 3D relighting as a direct transformation on latent scene tokens, without explicit 3D representations, rendering equations, or physics-based decomposition. Our model introduces a Scene Token Editor that processes scene tokens jointly with light-ray tokens through self-attention, producing updated tokens that can be decoded into multi-view-consistent relit images. To support diverse lighting types through a unified interface, all lighting signals, including environment maps, point lights, and area lights, are parameterized as Plucker ray tokens, enabling native 3D user interaction with a representation that carries no explicit spatial structure. Crucially, this design supports progressive relighting: because the editor's output remains in the same latent space as its input, a user can incrementally build up illumination one light source at a time, with each edit composing in token space. Experiments demonstrate that LumiTokens achieves comparable or superior relighting quality to other methods and supports progressive, composable lighting edits. Project page: https://neu-vi.github.io/LumiTokens/

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.18183v1 Announce Type: new Abstract: Visual on-policy distillation (OPD) improves the training of compact visual autoregressive models by learning from trajectories generated by the current student. However, these online rollouts are still produced token by token with autoregressive decoding, which adds substantial cost to every on-policy training step. Speculative Jacobi Decoding (SJD) provides an alternative because it can process multiple tokens in parallel without an auxiliary draft model, but the original method is designed for single-sequence inference. We introduce HB-SJD, a batched SJD rollout backend for visual OPD. HB-SJD allows each image to advance independently according to its own decoding progress, while images at different sequence positions are still verified in batched model forwards. As images finish, HB-SJD switches between Full and Compact execution to reduce the cost of later rollout rounds. HB-SJD only replaces the student rollout backend and leaves the teacher, distillation objective, and optimization procedure unchanged. Experiments with LlamaGen show that HB-SJD substantially reduces rollout and end-to-end training time while preserving the generation quality of the distilled student.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：GLM 5.3 - API Pricing & Providers | OpenRouter Z.ai: GLM 5.3 z-ai/glm-5.3 Compare GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.16978v1 Announce Type: new Abstract: Turning a frontier vision-language model into a robot policy usually means fine-tuning it to emit an action representation it never saw in pretraining, which throws away much of the reasoning that made the model worth reaching for. We go the other way and keep the VLM frozen. It writes the policy as a short Python control function, with no demonstrations and no fine-tuning. Writing that code once is open-loop, though. Existing closed-loop methods react at the wrong level: they retry a fixed policy or pick a different subtask, but never rewrite the code that failed. VLCP closes the loop where the failure actually lives, on the control code, within a single episode. Every $K$ steps the VLM re-observes the scene from multi-view RGB, proprioceptive state, and a state delta, then rewrites the control function from what it just saw, so a failure is caught before it compounds. We evaluate on a 57-task MuJoCo/RoboVerse sweep. This training-free policy reaches $35.1\%$ pooled success, against $3.5\%$ for the identical system queried once per episode. That tenfold gap holds with non-overlapping confidence intervals in every scene family. The gain traces to a $27.3\%$ within-episode recovery rate on failed grasps: a miss an open-loop controller would carry to the end of the episode gets re-observed and fixed at the next replan. And the loop stays cheap. A median $84\%$ of input tokens hit cache, an episode needs only about $10$ compact queries, and control blocks written during any replan persist to a cross-episode skill library reused in later prompts.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.17095v1 Announce Type: new Abstract: Vision-language-action (VLA) driving models couple a reasoning stage with a diffusion-based trajectory decoder, but do not give a direct way to redirect attention toward safety-critical actors at inference time without retraining. We studied a bounded additive pre-softmax attention bias on the visual tokens of detector localized traffic actors on Alpamayo-R1's Qwen3-VL backbone. It is applied as a fail open forward pre-hook with no weight changes. On 50 lane-change scenarios from the Physical AI World Model Synthetic dataset. The trajectory decoder shows a monotonic dose response in the bias magnitude, separate from a paired zero bias control at every tested magnitude. It reaches $\approx 17$\,cm mean displacement with lateral shifts up to $\sim 140$\ cm at the clamp. A layer ablation places the action-relevant signal in late layers, where the effect increases with the number of hooked layers (2.0cm for the first 8 layers; 67.6cm for all 36). A per call injection audit explains why the Chain-of-Causation text never changes. The mask based bias never reaches the reasoning pathway in this serving stack, so the invariance is verified exposure, not robustness. Steered trajectories tend to shift toward the attended actor, suggesting the bias governs where the model looks rather than encoding a target behavior.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Google has open-sourced SAM (Sovereign Agent Mesh) under Apache-2.0 — and it has nothing to do with Segment Anything. SAM is a zero-config, zero-trust P2P overlay that lets autonomous agents discover and call each other's MCP tools across cloud, on-prem, laptop and edge environments, without exposing a single internal endpoint to the public internet. Identity flows from OIDC into Biscuit capability tokens, so nodes authorize every request offline under a strict default-deny model. The post Meet SAM (Sovereign Agent Mesh): A Zero-Config, Zero-Trust P2P Network for AI Agents appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.14614v1 Announce Type: new Abstract: As AI datacenters retire functional GPUs, vast quantities of still capable accelerators enter secondary markets. This paper investigates whether these retired GPUs can find a productive afterlife to form a DumpsterCluster that can serve modern LLM inference, and under what conditions such repurposing is economically viable and environmentally sustainable. We physically built a 128-GPU DumpsterCluster from scratch using only second-hand components and ran it for one year. At current market prices (\$22K for the DumpsterCluster vs. \$600K for an 8-GPU B200 system), the economic advantages are substantial. Through pipeline-parallel optimizations, our V100 based DumpsterCluster achieves competitive LLaMA-70B throughput, validating production viability. However, our deployment reveals critical context dependencies. Older GPUs consume significantly more energy per token, making total cost of ownership favorable only in regions with inexpensive electricity. Under grid-average carbon intensity, second-hand systems can produce approximately 4x higher total carbon emissions per token for 8B models, and over 40x for 70B models, compared to current-generation hardware. These findings show that GPU afterlife is not universally sustainable - hardware repurposing must be strategically coupled with low carbon energy sources. When deployed in regions with favourable energy economics and clean electricity, second-hand GPUs offer a viable pathway for expanding AI capacity while advancing affordability, energy security, and environmental responsibility.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.13580v1 Announce Type: new Abstract: Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong performance across the Arabic and culturally grounded benchmarks evaluated in this report. The family includes, to our knowledge, the largest open Arabic-centric LLM trained from scratch at 70B parameters, and a competitive 8B-parameter variant among the evaluated open models. A custom Arabic-centric vocabulary enables efficient training and inference. In addition, an optimized architecture and training recipe yield highly compute-efficient training. With a substantially smaller token budget than comparable models, Jais 2 achieves strong Arabic performance on the benchmarks considered in this report and competitive English results. The models obtain leading results among the evaluated open models on OALL2 and AraGen. They also perform strongly on several culturally grounded Arabic benchmarks, including poetry, religion, cuisine, and dream interpretation, as well as in general tasks such as translation and summarization. We release the models in HuggingFace under a commercially permissive license. Jais 2 70B is also released as a chat app on the Web, iOS, and Android; it runs on Cerebras hardware, delivering up to 2,000 tokens per second, and enabling high-throughput Arabic-centric chat serving in our deployment setting. By uniting scale, linguistic diversity, cultural fidelity, openness, and speed, Jais 2 provides an open-weight foundation intended to support further research and development in Arabic-centric LLMs.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.13578v1 Announce Type: new Abstract: Transformer architectures rely on dense self-attention to model long-range dependencies, but this mechanism exhibits quadratic complexity with respect to sequence length. We introduce BCMT (Blockwise Causal Memory Transformer), an architecture for long-context language modeling that decouples local token interactions from global context propagation. Dense causal self-attention is applied independently within local blocks, while each block produces an adaptive summary aggregated through an exponential causal memory. This memory is subsequently injected back into the token representations, enabling efficient propagation of long-range contextual information without relying on explicit global attention. Unlike standard Transformers and recurrent memory architectures, BCMT maintains neither dense interactions between distant tokens nor learned memory states. Its memory mechanism is fully parallelizable and remains compatible with standard implementations of dense self-attention. Experiments on language modeling with context lengths of up to 1024 tokens show that BCMT achieves validation performance comparable to that of Dense Transformers while significantly improving training throughput and reducing memory consumption. An ablation study further confirms that these improvements arise from the proposed memory mechanism. These results demonstrate that an exponential causal memory constructed from block summaries provides an effective alternative to dense global attention mechanisms for long-context language modeling.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.13571v1 Announce Type: new Abstract: When a language model fails to answer a query on the first attempt, an agentic system retries, consuming additional tokens each time. This retry overhead creates a gap between what a model's per-token price implies and what a full workflow actually costs. We call this gap \emph{token inflation} and define it as the ratio of true workflow cost to single-call cost. Systems like FrugalGPT route based on the latter, which can underestimate real cost by more than $2\times$ on difficult tasks. We address this with InflationAgent, a four-stage router that (1) measures token inflation systematically across model tiers and task types, finding inflation as high as $4.25\times$ for a 7B model on multi-hop question answering; (2) introduces CoT Branching Entropy (CBE), a pre-execution difficulty signal computed entirely from local inference, which predicts high inflation with AUROC 0.887; and (3) selects models by maximizing a Semantic Exchange Rate (SER) that divides expected accuracy by predicted true cost, with a fresh-escalation policy that discards failed chains before routing to a stronger model. On GSM8K under a fixed budget, InflationAgent achieves 94.7\% accuracy versus 91.0\% for FrugalGPT while using 31\% fewer tokens, and we show that forwarding a failed reasoning chain to GPT-4o reduces its accuracy by up to 34.8 percentage points, validating the fresh-escalation design.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.13568v1 Announce Type: new Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot tell a definition from a call from a comment. Semantic retrieval via the Language Server Protocol (LSP) is precise and typed, but needs a running, indexed server and pays a per-symbol round-trip. The claim that semantic retrieval is more token-efficient is, we find, asserted almost everywhere and measured almost nowhere: no public source isolates the LSP-vs-lexical token delta for an agent at equal task-success. This paper formalizes the question with one metric (tokens-to-success), specifies a five-arm ablation isolating semantic retrieval from confounds, maps three pre-stated failure modes onto measurable variables, and reports a preliminary study (Python and TypeScript repos; Claude Opus 4.8, Sonnet 4.6, Haiku 4.5). The answer is conditional and usually negative. On symbol-named localization the LSP costs tokens (+6% to +118%) and the agent ignores it when free. On reference-completeness it buys precision but not token savings and cannot raise the recall ceiling set by agent thoroughness; it saves tokens only for the weakest model. Tool choice is task-dependent: models default to grep on localization (0-6% semantic use) but reach for the LSP about half the time on reference tasks, unprompted. On edits scored by real test execution the gap is starkest: grep solves multi-file renames perfectly, a location-only LSP fails three-quarters of them by missing a call site, and even a complete, index-warmed, text-enriched LSP (each reference's line inline, as production LSP-MCP servers do) recovers most of the gap but cannot close it, since a rename must touch comments and strings that semantic references exclude. The implication is not LSP-always but an adaptive router keyed on task class, model capability, and lexical noise.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.13675v1 Announce Type: new Abstract: Between October 2018 and July 2026 AI models progressed from simple systems like BERT to massive agents that solve complex math and write software. The ability to resolve real coding issues improved by nearly six times per year since late 2024. During this time costs dropped sharply with OpenAIs budget model GPT 5 point 6 Luna matching flagship capabilities for just one to six dollars per million tokens beating older versions at a fraction of the price. Top performance is now split across specialized models as Claude Opus 5 leads in frontend coding Claude Fable 5 excels at repository level coding and GPT 5 point 6 Sol dominates terminal tasks. In a grade school math test using the Qwen 2 point 5 model basic methods solved 58 of 100 problems while advanced sampling solved up to 79. A confidence ranking tool correctly identified 47 right answers in its top 50 choices proving highly useful for sorting tasks with all research materials made fully public.

据彭博社报道，Stripe 已同意以超过 70 亿美元收购 AI 推理网关 OpenRouter。这个价格只有在把 OpenRouter 视为 AI 推理市场而非简单 API 代理时才合理。Stripe 押注的是：通过控制请求路由、提供商关系和 800 万开发者，在 AI 成本产生的时刻销售支付、计量、额度和计费服务。

Sentinel Scan 是 Ventrova 推出的一项 LLM 安全审计服务，针对你自己的 LLM 目标运行 15 种对抗性攻击，由独立 LLM 裁判评分，固定价格 249 美元。试点结果显示所有 15 次攻击均被拦截，平均每次扫描成本 0.0013 美元。

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Chinese artificial intelligence developer Z.ai Co. today debuted GLM-5.3, an open-source large language model that set records across several popular benchmarks. The LLM is based on an algorithm called GLM-5.2 that the company released in mid-July. The latter model features a mixture of experts architecture with 753 billion parameters and a context window of 1 […] The post Z.ai debuts GLM-5.3 with long-horizon coding, cybersecurity upgrades appeared first on SiliconANGLE.

谷歌正关注 AI 模型价格战，通过下调 Gemini 3.7 Flash 的入门价格来吸引开发者，并突出编程等应用场景。

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Google has released Gemini 3.7 Flash, a refinement of Gemini 3.6 Flash with algorithmic improvements to its reasoning core. It handles text, images, audio, and video across a 1M-token context window with 64K-token output, and supports customizable thinking configurations. Coding results move notably: 43.6% on FrontierCode 1.1 Main versus 34.4%, 65.3% on DeepSWE v1.1, and 1588 Elo on WebDev Arena. Document and workflow evals gain more — GDP.pdf goes from 22.0% to 34.0%, AutomationBench from 17.0% to 30.4%. GPT-5.6 Terra still leads on terminal and computer-use agents. The model is API and enterprise only, with no open weights, at an introductory $0.75/$3.75 per 1M tokens through December 31, 2026. The post Google AI Just Released Gemini 3.7 Flash: A Coding and Agent Model at $0.75/1M Input Tokens appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Liquid AI released LFM2.5-VL-3B, a 3.1B-parameter vision-language model built for on-device deployment. It averages 80.7 on ScreenSpot-v2 and lifts RefCOCO grounding from 57.1 to 87.9. Function calling is new to the VL line, with ToolSandbox moving from 26.4 to 59.5. The model fits in roughly 3 GB and decodes 228 tokens/s on an Apple M5 Max. The post Liquid AI Releases LFM2.5-VL-3B: A 3B Vision-Language Model That Reads Screens, Grounds Objects, and Calls Tools On-Device appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：DeepSeek (@deepseek_ai): "API pricing update 💰 With the V4 lineup release, we’re updating our API pricing and introducing peak and off-peak rates. Off-peak rates are 50% lower than peak, enabling more flexible workload…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Preview Ultrafast, a new OpenAI API service tier that runs GPT-5.6 Sol up to 14× faster. Powered by Cerebras, it delivers up to 750 output tokens per second.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：SpaceXAI released Grok 4.6 on August 12, 2026 — a post-training upgrade over Grok 4.5, not a larger base model. It ties GPT-5.6 Sol Max at 61 on the Artificial Analysis Intelligence Index, ships 500K context and a new xhigh reasoning level, and holds pricing at $2/$6 per million tokens. The coding benchmarks are where it still loses. The post SpaceXAI Releases Grok 4.6: A 500K-Context Frontier Model Tuned for Long-Running Agents, Coding, and Knowledge Work appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.11242v1 Announce Type: new Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks. We identify a class of user-issued instructions, Session Constraints (SCs), such as "do not delete any emails until I confirm," that are meant to constrain LLM's behavior for the remainder of a session but are silently dropped during compaction. To quantify this loss, we introduce COMPINT, an evaluation suite that evaluates compactors across three long-context scenarios: multi-turn chat, agentic trajectory, and long-horizon research. Current compactors retain only 17% of injected SCs on average, and most perform worse than running the same task without compaction. Retention varies sharply with compactor, prompt, context length, SC phrasing, and injection location, showing that the loss is systematic rather than tied to any single setting. We propose an SC-aware extractor that runs alongside the compactor as a plug-and-play module, achieving over 90% retention across all three scenarios without modifying the compactor or LLM. The COMPINT evaluation suite and accompanying implementation are available at https://github.com/ZhiqiEliWang/compaction-integrity.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.11212v1 Announce Type: new Abstract: Top-k Mixture-of-Experts (MoE) routing is discontinuous, so a deployment-motivated numerical disturbance -- simulated 4-bit KV-cache quantization read by a protected BF16 gate -- pushes tokens across decision boundaries and flips which experts fire. This paper proposes no new mitigation; it supplies a causal apparatus, empirical findings, and a detection-limit result. A four-run apparatus prices the route-mediated fraction (RMF) of quantization damage, a token-level attribution decomposes it by mechanism, and pre-registered probes carry the findings across three architectures. On OLMoE-1B-7B at 4-bit KV (pilot), about a third of the damage is routing-mediated: RMF ~ 0.31 (discovery 0.31 [0.20, 0.41]; process-replicated mean 0.313 +/- 0.020; pre-registered re-execution 0.231). The deployable router margin detects that a flip occurred (AUC 0.772) but cannot tell a harmful flip from a helpful one (at chance): among the tested local, inference-observable router statistics we find no predictor of a flip's loss sign above chance -- an empirical benefit-detection barrier bounding selective repair restricted to this feature family. The signed-flip tax and sign-inseparability carry cross-model; the clean-reference remedy's payout is architecture-modulated; a controlled same-checkpoint flag-swap re-scopes the gate's normalization convention to a damage-magnitude moderator, not a route-recoverability mechanism. A real int4 KV kernel yields a fraction compatible with the fake-quant dose curve but underpowered (95% CI [-0.111, 0.394] includes zero) -- ruling out gross disagreement, not an independent replication. Hypotheses, thresholds, and evaluations were pre-registered before measurement, with misses reported; a pre-registered held-out read replicates the partition and the near-cancelling tax out of sample, while the strict impossibility exclusion narrowly misses.