AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12561v1 Announce Type: new Abstract: Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests. For embodied agents that control robots, visual and spatial observations introduce a broader choice of memory modalities, affecting both the information available for subsequent tasks and the model inference costs of constructing and using memory. We introduce MeMoREval, a benchmark for studying this problem through a controlled experience-request protocol. Agents first experience a sequence of events without knowing the subsequent tasks, and subsequently they use memory to respond to information and action requests without receiving new observations. The benchmark comprises 53 task…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12516v1 Announce Type: new Abstract: Interleaved multimodal in-context learning (ICL) lets frozen large vision-language models (LVLMs) acquire new tasks from a handful of image-text-answer demonstrations, yet it remains fragile: demonstrations bind to the wrong images, redundant exemplars crowd out informative ones, and noisy answers are copied verbatim into predictions. We present AVA, a training-free framework that organizes the demonstration pipeline of multimodal ICL into three composable stages. A Thread-Resolved Decomposer (TRD) segments the interleaved context into per-sample threads and re-stitches them with explicit boundaries, restoring image-text binding. An Influence-scored Demonstration Selector (IDS) estimates each candidate's marginal…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12514v1 Announce Type: new Abstract: Autoregressive video diffusion models maintain a growing attention key-value (KV) cache, making memory a key bottleneck for long video generation. Recently, clustering-based quantization has emerged as an effective method to compress video KV caches by grouping similar key and value vectors then quantizing residual errors. However, when later frames attend to the compressed history, small reconstruction errors can compound as the video grows. Beyond the within-layer similarity exploited by clustering, we find strong dependencies across cache layers in video models. This motivates Coral-KV - Calibrated Offline, Residual-coded, and Adapted Locally - a KV-cache compression framework that uses cache states in each lay…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12582v1 Announce Type: new Abstract: A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing the loop count. At one loop, however, such models typically fall well short of a non-recurrent model of the same size, a one-loop tax that makes a separate non-recurrent model the better choice whenever latency matters. We present Elastic Latent Recurrence (ELR), a recipe for training looped language models without this tax. At one loop, an ELR model costs the same to serve as a non-recurrent model of the same size and, trained on the same data, reaches similar accuracy. Each additional loop then buys more accuracy for more inference compute. Three choices make this…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12570v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target model. Recent diffusion-based drafters make this paradigm particularly attractive: deep attention-based neural backbones provide strong predictions, while drafting multiple future positions in parallel avoids the sequential cost of autoregressive generation. This parallelism, however, comes at a cost. Tokens within a draft block are predicted without access to the realized identities of preceding draft tokens, removing intra-block dependencies that would naturally be available under autoregressive generation. We introduce DCOCO (DFlash Co…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12530v1 Announce Type: new Abstract: Training-free feature reuse accelerates diffusion transformer inference by replacing full denoising computation at selected steps with cached approximations. Existing methods mainly improve the reconstruction of skipped features, but we find that once a stable first-order reconstructor is used, increasing reconstruction complexity brings limited gains, whereas the placement of exact-computation steps has a much larger effect on fidelity. More importantly, absolute shallow-probe variation is jointly affected by input-trajectory displacement and network response strength, and therefore does not directly reflect cache risk. We address this confounding by normalizing probe-output variation with the corresponding input…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12495v1 Announce Type: new Abstract: Small language models trained on a single local machine leave little room for architectural trial and error. Kairos combines bidirectional gated-DeltaNet linear attention and sliding-window attention over shared projections (LiZAttention2), block-wise Attention-Residual aggregation, a sparse Mixture-of-Experts (MoE) feed-forward layer and a multi-scale byte-level codec, trained with a uniform-noise denoising objective over one byte space shared by text, image, audio, video, lidar and control streams; this report asks whether the combination optimizes at all before asking whether it is useful. We give code-derived algorithms for each component, including a cross-session recurrent-state memory gate, then run converg…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12494v1 Announce Type: new Abstract: In this article, we propose algebraic integer number formats (AINF) as a framework for highly configurable and accurate compressed computation. A key property of AINF is its straightforward reduction to purely integer arithmetic, enabling error-free multiply-accumulate operations. We develop a matrix multiplication engine that exploits this property, obtaining performance within a predictable factor of the most efficient numerical counterparts on modern hardware accelerators. Another key advantage of AIQ is the freedom to select algebraic integers tailored to the numerical characteristics of a given use case, offering optimization opportunities that are fundamentally unavailable in floating-point or fixed-point fo…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Today’s engineers face an unprecedented acceleration in AI hardware complexity, as explained in the recent research article “Revisiting Edge AI: Opportunities and Challenges.” The article examines the rapid growth of edge AI and the challenges it creates, including resource constraints, model architecture limitations, and network demands across edge-AI deployments. The acceleration is driven by a fundamental shift in how modern AI models are built and scaled. As the models have become much larger and more complex, they are computationally more demanding because they contain more parameters and require more calculations. To meet the demands of scaling deep neural networks, the industry is increasingly developing AI chips that are designed for specific tasks. One…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.10787v1 Announce Type: new Abstract: Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the ceiling on what an embodied agent can understand and decide. Physical interaction, however, remains the domain of action policies, which provide dense, low-latency control. We present NavGPT-3, a harness that connects the two models, with an OS-like runtime built above it: reasoning, acting, and monitoring run as threads with their own context, tools, and permissions, while the runtime schedules them and decides which thread controls the robot's motion, so that the robot can react to sudden real-world events through interruption…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.10563v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) often answer visual reasoning questions by relying on linguistic priors rather than task-relevant visual evidence. Textual chain-of-thought reasoning can partially mitigate this issue by encouraging models to decompose visual questions into intermediate evidence-seeking steps, but generating these steps autoregressively increases inference cost. Latent reasoning avoids explicit rationale generation, but existing approaches provide limited control over what intermediate states encode, making it difficult to impose separate supervision for planning, grounding, and evidence selection. We propose Structured Latent Visual Reasoning (SLVR), a training framework that bridges expli…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.10738v1 Announce Type: new Abstract: Our work explores learning a compressed latent representation of text, at the intersection of data compression and representation learning. We propose an autoencoder architecture that performs residual downscaling and upscaling of hidden representations along the time axis, with a residual low-dimension discrete bottleneck. We analyze our approach for different quantization methods, training objectives, and datasets. For different levels of compression, we evaluate the similarity between the original and reconstructed text both at the surface-level (BLEU) and at the semantic-level (LLM-based judge). Additionally, we evaluate our models on downstream question-answering and semantic text similarity benchmarks. Our a…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.10552v1 Announce Type: new Abstract: Comparing parameter-efficient fine-tuning recipes under a single, shared learning rate is a common but flawed practice: when the arms being compared have very different trainable-parameter counts, a shared rate can simultaneously depress the larger arms' means and inflate their variance, manufacturing a large, seemingly multi-seed-significant advantage for the smallest arm that is not a real effect. We document this confound in a concrete setting: post-hoc SVD-based KV-cache compression, where an already-pretrained model is converted to a low-rank (multi-head-latent-attention-style) cache by factorizing its key/value weights into a down-projection ("encoder") and an up-projection ("decoder"), after which a short f…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.10786v1 Announce Type: new Abstract: Planning is increasingly important for long-horizon agents, where successful execution requires coordinating subgoals, tool use, and intermediate outcomes over many steps. Yet assumptions made during planning may be invalidated by the environment, tools may return unexpected results, or actions may fail. Effective agents must therefore not only generate plans, but also revise them. Such revisions often affect only part of a plan, leaving the preceding and subsequent structure intact. Rather than regenerate the entire plan and risk unnecessary changes, repair can regenerate the affected region conditioned on the preserved prefix and suffix. We introduce Plan-and-Patch, a plan-and-act framework in which a diffusion…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.08858v1 Announce Type: new Abstract: Low-rank compression reduces the cost of pretrained language models by replacing linear transformations with low-rank factorizations. However, conventional methods use a fixed rank allocation during inference, assigning the same amount of compute regardless of the input token. We introduce Low-Rank Conditional Computation (LRCC), which adds token-dependent computation to pretrained models by training one lightweight router per Transformer block to select among a small set of nested low-rank paths. During training, the low-rank factors remain frozen, and only the routers are optimized. We evaluate LRCC on Llama and Qwen models for language modeling and zero-shot downstream tasks. Within the same average active-para…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.08829v1 Announce Type: new Abstract: Jev offers an alternative interface for language understanding: given an input and predefined questions, it returns probabilistic decisions rather than free-form responses. Whether this interface can support effective reasoning for text classification against leading LLMs remains an open questions. We introduce Emo-Jev, a training-free framework with two complementary implementations. Emo-Jev-D decomposes classification into task-specific atomic judgments and composes their probabilities into a final prediction. Emo-Jev-SC constructs multiple judgment paths from complementary perspectives and aggregates their predictions into a consensus decision. We evaluate Emo-Jev on eight datasets spanning sentiment analysis,…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.08820v1 Announce Type: new Abstract: Large language model-based multi-agent systems improve complex problem solving through collaboration, while latent communication directly transmits model internal states to avoid the high inference costs of natural language. However, existing KV-based latent communication methods prioritize sender-side state fidelity, leading to substantial communication and computation overhead and potentially introducing redundant information. To address these limitations, we revisit latent communication from a task-oriented perspective, shifting its objective from sender-side state fidelity to receiver-side task sufficiency. Under this formulation, we propose KITE, a training-free framework for task-oriented key-layer KV commun…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.08811v1 Announce Type: new Abstract: As context windows scale to tens or hundreds of thousands of tokens, KV cache compression has become essential for efficient LLM inference. Existing methods fall into three families: score-based eviction, summary compensation, and offload-and-recall. Yet all three decide what to keep or recall by content relevance to the current query. We show this shared design is structurally incomplete. A cache supports two access modes: associative lookup by content and sequential traversal by position; current compressors implement only the first. The gap matters in practice: retrieval-augmented generation, code completion, and structured-data extraction all require the model to reproduce identifiers, field values, or code to…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： As previously promised, here's Anthropic's new fast, low cost model: Introducing Claude Haiku 5.5. The previous Haiku, 4.5, was very much showing its age. It came out almost a year ago, and was priced at $1/million input and $5/million output - relatively expensive even back then, and a full 10x the price of OpenAI's GPT-6 Luna, released last month. The new Haiku exactly matches the price of GPT-6 Luna - $0.10/$0.50 - up to 100,000 tokens. Beyond 100,000 tokens the price increases 5x to $0.50/$2.50. Luna itself has a price increase at 272,000 tokens but only to $0.20/$0.75. Haiku 5.5 also uses a new, less generous tokenizer. My Claude Token Counter tool shows that the same long prompt uses around 1.25x as many tokens with Haiku 5.5 compared to Haiku 4.5, so th…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.06932v1 Announce Type: new Abstract: Cache-based test-time adaptation (TTA) for vision-language models is often hindered by background bias in global representations and unreliable entropy-based cache admission under representation variations. To address these limitations, we propose RADC, which enhances prototype learning through reliable dual caching. RADC introduces a Semantic Foreground Cache that aggregates category-consistent spatial evidence from CLIP representations, yielding foreground prototypes that complement the global cache while mitigating background interference. To reliably manage both caches, Gaussian Risk Admission models multi-view representations as diagonal Gaussian distributions and jointly considers class separation and featur…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.07032v1 Announce Type: new Abstract: Large-scale pretrained transformer models have achieved state-of-the-art performance across diverse machine translation tasks, including multilingual settings. Knowledge distillation has emerged as a sustainable approach for model compression, transferring knowledge from large teacher models to smaller, more efficient student models. Similarly, quantization, which reduces the numerical precision of model weights and activations (e.g., from 32-bit to 8-bit representations) is widely used to accelerate inference, enabling models to run several times faster during deployment. However, both techniques face limitations when applied to specialized domain data, particularly under low-resource conditions. In knowledge dis…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.06927v1 Announce Type: new Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free remedies evict low-importance tokens, an irreversible choice along the sequence axis. We instead keep every token and store it more cheaply along the "feature" axis. We therefore propose AttSVD, a new "interpretable" low-rank compression whose basis is derived from each prompt's own attention geometry: an online, per-prompt truncated SVD that keeps only the directions attention actually reads, cutting persistent per-head KV memory in proportion to the retained rank. We propose two decode-time caching strategies, accumulating and streaming, for short and long generation…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.06890v1 Announce Type: new Abstract: We present an industry experience report on three years of operating an event-driven cloud infrastructure for continuous machine learning training in automotive manufacturing. Our system orchestrates GPU-accelerated training of product-specialized model pairs, a physics prediction model and a reinforcement-learning control policy, across multiple plants, coordinating long-running GPU workloads triggered by manufacturing events. The architecture combines Amazon ECS with EC2 GPU capacity providers, SQS-based messaging with dead-letter queues, and an admission-controlled Lambda dispatcher that enforces cluster concurrency limits. A Conductor orchestrator on ECS Fargate initiates dependency-aware retraining chains on…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.06917v1 Announce Type: new Abstract: Prefill-decode disaggregation is becoming a common architecture for LLM serving because it separates two phases with distinct execution patterns and SLO objectives. Existing systems typically combine a fixed prefill/decode worker ratio with request routing across workers. However, real-world workloads exhibit both short bursts and sustained shifts in the prefill-to-decode demand ratio. As a result, a configuration that is well provisioned at one time may quickly become mismatched, causing latency SLO violations even when idle capacity exists elsewhere. Existing autoscaling mechanisms can add capacity, but they react slowly, require spare GPUs, and do not directly address short-timescale phase imbalance. We present…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：GLM 5.3 from Z.ai is now available on Amazon Bedrock: a 753B-parameter mixture-of-experts model built for coding and long-horizon agentic tasks. Learn how to invoke it with the OpenAI-compatible APIs, cut cost and latency with prompt caching, and run an authorized security test with the open-source Strix agent.
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.02360v1 Announce Type: new Abstract: Vision-language-action (VLA) policies enable diverse robotic manipulation but can fail during execution without recognizing their own errors. Human observers provide complementary signals, as unexpected robot behavior can trigger rapid vocal, facial, or verbal reactions before failure is completed. We introduce SocialVLA, a local, policy-agnostic social perception gateway that converts spontaneous human reactions into runtime intervention signals for VLA manipulation. SocialVLA combines causal paralinguistic audio detection, visual reaction recognition, explicit stop phrases, and robot-relevance estimation. An asynchronous first-event fusion mechanism triggers a VLA hold from the earliest sufficiently confident si…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.02323v1 Announce Type: new Abstract: Flow-based Vision-Language-Action (VLA) policies generate action chunks by transporting samples from a task-agnostic isotropic Gaussian source. As this source is conditioned on neither recent execution nor predicted future evolution, (i) it discards the local continuity established by recently executed motion. (ii) Even when predictive world representations are introduced, they often only condition the transport dynamics rather than determine where generation starts, how far it may deviate, or along which action directions it may expand. Building on this observation, we introduce ProAct, a world-calibrated proposal-to-action framework that makes the generative source itself predictable. (i) To preserve motion cont…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.02612v1 Announce Type: new Abstract: Simultaneous speech translation must emit useful target text before the source is complete while preserving every committed token. We adapt a full-utterance speech language model using prefix supervision derived from its own complete- and partial-waveform translations, requiring neither transcripts nor human translations. We compare single-turn forced-prefix and multi-turn append-only decoding, use a confidence threshold to control the inference-time quality--latency trade-off, and vary the density of training prefixes with a separate synthesis margin. On FLEURS and CoVoST2 in three language directions, prefix training improves quality--latency frontiers over the unadapted model, and confidence provides the broade…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.02267v1 Announce Type: new Abstract: Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input carries an injection. System-1 decision models answer such questions in a single forward pass with class probabilities, promising large cost and latency savings over LLM calls. We present a paired evaluation of an open-weight (Laya) and a hosted (Jev) System-1 model on 11 agent decision points built from 18 public sources: 7,283 base cases plus 6,640 robustness variants, with byte-identical inputs, paired tests, and cross-hardware and cross-day reproducibility checks. Jev is significantly more accurate on 9 of 11 decision points (+10.8 to +46.0 pp). Neither model b…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.00053v1 Announce Type: new Abstract: Four-bit floating-point (FP4) Tensor Cores accelerate matrix multiplication, but scale computation, operand packing, layout construction, and saved backward state can erase the gain. We present \emph{format-aware fusion}, which co-designs each quantization producer with its scale domain and consumer layout for native \mxfp{}, global \nvfp{}, and cooperative-thread-array-local \nvfp{}. We evaluate Llama-3-family 8B pretraining through 160 billion tokens using bfloat16 output projections and compiled cross entropy. In matched same-accelerator probes, bfloat16 and Transformer Engine \nvfp{} reach 18.8K and 27.6K tokens/s/GPU, while our fastest custom route reaches 37.9K. \mxfp{} with row-gradient stochastic rounding…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.00049v1 Announce Type: new Abstract: Graphics processing unit (GPU) generations scale matrix, special-function, and memory pipelines at different rates, so kernel bottlenecks move as hardware evolves. FlashAttention-4 exposed this imbalance inside attention on NVIDIA Blackwell. We test whether short polynomial programs can accelerate other special-function-unit (SFU) operations in large language models (LLMs). We first compare native PyTorch evaluation with packed fused multiply--add (FMA) programs in an isolated IEEE binary16 (FP16) sweep spanning L2-resident and high-bandwidth-memory (HBM)-resident working sets. We then replace native sigmoid, tanh, and sigmoid linear unit (SiLU) with degree-3 or degree-4 bfloat16 (BF16) programs in four GB200 inte…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Fine-tuning teaches a small search agent your tools and environment, giving it the reliability of a frontier model at lower latency and cost. In this post, we fine-tune an LLM-powered search agent with multi-turn reinforcement learning (MTRL) on Amazon SageMaker AI and share the gains we measured in retrieval quality and reliability.
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.00355v1 Announce Type: new Abstract: Efficient indoor LiDAR perception is challenging because mobile robots must understand cluttered three-dimensional environments under strict latency and memory constraints. Existing point-based and voxel-based methods often incur substantial computational overhead, whereas conventional bird's-eye-view (BEV) representations improve efficiency at the cost of discarding vertical geometric information. We present IndoorBEV, a lightweight LiDAR perception framework that mitigates this tradeoff through a height-aware BEV representation and geometry-conditioned feature fusion. IndoorBEV summarizes the vertical point distribution in each BEV cell using statistical height features and multi-frequency height encoding, allow…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.38197v1 Announce Type: new Abstract: Financial time-series forecasting must capture price dynamics across heterogeneous assets while incorporating news available at prediction time. We introduce DualCast, a dual-path framework that extends a frozen language model with a discrete financial vocabulary. Each log-return patch is represented by a learned summary token and three residual shape tokens, preserving local drift and volatility while allowing shape patterns to be shared across assets. To improve codebook utilization, we develop adaptive frequency-equalizing residual vector quantization, which rebalances overloaded codewords without compromising reconstruction accuracy. The fast path trains only the new financial-token embeddings and output heads…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.00025v1 Announce Type: new Abstract: Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-approving shell commands, writing memory, selecting tools, ranking past turns. We ask whether off-the-shelf SLMs meet practitioner-defined thresholds and, when they fail, why, and whether quantization changes the answer. We build a benchmark of 4 such microtasks with fixed prompts and automatic metrics, each with a pre-specified threshold $\tau$ anchored to a cheap non-LLM baseline and a CI-aware eligibility rule (a configuration passes only if its confidence bound clears $\tau$). Sweeping Qwen3 0.6/1.7/4/8B at their best (FP16, greedy, one frozen prompt, no tuning), we…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Cloudflare has released Clef (27B) and Clef-flash (9B), open-weight decision models that return typed probabilities instead of text. They are Jev-API compatible, accept images, and run on Workers AI at 209.3 ms and 38.8 ms median latency. The post Cloudflare Releases Clef and Clef-flash: Open-Weight Decision Models That Return Typed Probabilities Instead of Text appeared first on MarkTechPost.
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Cohere has released Embed 5, a new embedding model family. It targets enterprise search, RAG, and agentic retrieval. The model family ships in 2 tiers. Embed 5 Pro targets maximum retrieval quality. Embed 5 Fast targets latency and cost on the live query path. Both accept text, images, and fused text plus image inputs. Both […] The post Cohere Releases Embed 5: How It Compares to Voyage 4 Large, Gemini Embedding 2, and OpenAI appeared first on MarkTechPost.
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： [...] Put these pieces together and you have the two halves of a worm: a payload that hijacks the agent, and an agent that will carry the payload to the next agent. Agents in separately-isolated sandboxes discovered that they could leave instructions for each other in a shared package cache, and those instructions changed what the recipients did. Replace the package cache with email, Slack and shared documents or WhatsApp, and replace independently-sandboxed training runs with independently-deployed personal agents like Muse, and you have exactly the ingredients that a worm needs. — Matthew Green, Is sandboxing sufficient to contain rogue agents? Tags: accidental-cyberattacks, ai-misuse, generative-ai, ai-security-research, sandboxing, ai, llms
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.38261v1 Announce Type: new Abstract: In this paper we propose NinaXander, a series of composed language models obtained by connecting layers of frozen language models from different architecture families with a single trained shared-latent adapter. A composed model runs the first layers of one model, converts the resulting intermediate representation once with the adapter, and then runs the remaining layers of the other model. Once the adapter is trained, several composed models that connect at different layers are obtained without retraining. Using the recurrent RWKV-4-Raven-7B and the Transformer-based Tulu-Pythia-6.9b, abbreviated as RWKV and Pythia, this study examines whether frozen models from different families can be recombined post hoc. The…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.38201v1 Announce Type: new Abstract: Long-running tools can dominate coding-agent latency: compilers, test suites, and repository commands take seconds to minutes while the agent idles. This observation stall presents the same tension that drove out-of-order processors -- asequential interface hides work that can be predicted and started early, but a speculative result may become visible only after it and every earlier step have been validated. We present TomasuLLM, a runtime that executes agent tool calls out of trajectory order while preserving task-execution correctness. It drafts future actions, runs them in isolated copy-on-write sandboxes, traces their dependencies and effects, and commits results in trajectory order only after validation again…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：OpenAI released GPT-6.1 Sol on September 29, 2026, an upgrade to GPT-6 Sol. It reaches near-Astra results on agentic coding, computer use and professional work at one-fifth of Astra's token prices. It costs $2 input and $10 output per million tokens, and cached input drops to $0.10. It is available now through the OpenAI API, ChatGPT Work and Codex. The post OpenAI Releases GPT-6.1 Sol: Near-Astra Coding and Computer Use at One-Fifth of Astra’s Token Price appeared first on MarkTechPost.
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.36134v1 Announce Type: new Abstract: Functional Kolmogorov-Arnold Networks (FunKAN) achieve state-of-the-art accuracy on MRI Gibbs artifact removal and anatomical segmentation, but their 11.6 M parameters and 8.7 GFLOPs are too large for edge medical devices. We present FunKANLite, a two-stage, hardware-aware compression of FunKAN for point-of-care use. FunKANLite-TR reduces the spatial prior and replaces the ResBlock offset predictor with a depthwise-separable block. It has 1.9x fewer parameters than FunKAN and no loss in accuracy. We then distill FunKANLite-TR into FunKANLite-ST, which lowers the Hermite basis rank, factorizes the spatial prior into a low-rank form, and halves the filter widths. FunKANLite-ST has 5.6x fewer parameters and 3.7x fewe…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.35806v1 Announce Type: new Abstract: Automated skill extraction underpins workforce planning, yet most systems represent skills as flat labels with no notion of the responsibility level at which a skill is practiced. The Skills Framework for the Information Age (SFIA) captures exactly this dimension, defining 147 professional skills across seven responsibility levels, but no automated LLM-based extraction targeting SFIA has been reported. We formalize the task as structured prediction of (skill, level) pairs from free text and ask three questions: how accurately can text be mapped onto SFIA's closed vocabulary, which strategies reliably predict the level alongside the skill, and do agentic designs improve on simpler retrieval and prompting? We evalua…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.35800v1 Announce Type: new Abstract: Low-bit key-value (KV) cache quantization saves storage but can sharply degrade vision-language model (VLM) accuracy. We introduce HeadGuard, a composable head-protection method that augments a base KV-cache quantizer with a fixed high-precision mask. Image-sensitivity and output-sensitivity scores select physical KV heads offline, with approximately 1/8 protected in the main experiments; their image keys and optionally values remain in bfloat16 (BF16), while the base quantizes unprotected image entries. Across eight VLMs, three base quantizers, and eight benchmarks (six discriminative and two generative), HeadGuard recovers a substantial fraction of lost accuracy on weaker quantizers, with the strongest gains for…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.35833v1 Announce Type: new Abstract: Running a language model on edge hardware provides private and low-latency reasoning without a network connection, and yet the small models that fit on such devices are unreliable on the tasks computers are expected to handle well, such as arithmetic, algebra, and formal logic problems. We argue that much of this unreliability is avoidable. Many queries appearing to demand reasoning are in fact structurally deterministic and permit fast and exact symbolic solutions. Therefore, forcing a probabilistic model to approximate them sacrifices accuracy and energy for little benefit. We present a neurosymbolic router that classifies each incoming query and dispatches it to the cheapest correct solver, sending structured t…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.30275v1 Announce Type: new Abstract: A statistic reported without the quantity needed to interpret it is not evidence. We develop that thesis for a concrete practice in AI safety. Interpretability artifacts are calibrated on full-precision weights, deployed on quantized ones, and certified as surviving the change by scale-invariant statistics (cosine similarity, correlation, AUROC) that are reported without their noise floor. For the difference-in-means direction estimator, the split-half floor is governed by one dimensionless number, $\kappa = n\rho^2/d$. The closed form $\mathbb{E}[\cos] \approx (1+4/\kappa)^{-1}$ is classical; the missing input is the class separation $\rho$, which we measure on real activations; no compression-transfer study we k…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.30270v1 Announce Type: new Abstract: On-device inference with small language models keeps user data local, works offline, and incurs no per-query cost, so the on-device tier is preferred when it is adequate. It is thermally constrained, however, and I find the constraint is sharper than a slowdown: on a flagship Snapdragon device, sustained on-device generation destabilizes the GPU inference runtime, which crashes or silently wedges after a few consecutive queries. The failure lies in the current toolchain (OpenCL kernel compilation and long-prompt prefill on the mobile GPU), recurs even when the device is cool, and is worst for long generations. Multi-tier routers across on-device, edge, and cloud models can relieve this pressure, but existing route…
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Ollama now supports decision models, based on TypeSafe's Jev API for fast, typed decisions. Decision models can now be run at no cost with low latency. Based on text, decision models answer yes-or-no questions, choices and scores about it, with a probability for every option.
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.30459v1 Announce Type: new Abstract: Perception in robotics and XR fundamentally relies on good state estimation. Visual-inertial odometry (VIO) and Simultaneous Localization and Mapping (VI-SLAM) are proven ways of achieving this goal in a cost-effective and accurate manner. Efficiency in these systems allows for smaller, cooler, and lighter devices. GPU acceleration is a natural approach for reducing latency, thanks to their wide availability in platforms like embedded computers, mobile phones, and XR headsets. However, previous works in the literature have limited themselves to the use of CUDA for this task, significantly reducing deployment options to a single vendor. We instead leverage the vendor-agnostic Vulkan API, originally designed for the…