AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17595v1 Announce Type: new Abstract: In the improving multi-armed bandits problem, each of $k$ arms has an unknown nondecreasing, discretely concave reward curve $f_i$, and pulling arm $i$ for the $t$-th time yields $f_i(t)$. For sufficiently long horizons, Blum and Ravichandran (ALT 2025) proved that randomized algorithms achieve an $O(\sqrt k)$ approximation to the best single arm when the scale $m=f^*(T)$ of the optimal arm is known ($T\ge2k$), and $O(\sqrt k\log k)$ when it is not ($T>4k$), against an $\Omega(\sqrt k)$ lower bound. The logarithmic factor is unnecessary: a one-page \emph{probe-and-commit} algorithm achieves competitive ratio $4\sqrt3\,\sqrt k$ for $T\ge2\lfloor\sqrt k\rfloor$, without any knowledge of the scale, and we determine 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:2609.17594v1 Announce Type: new Abstract: Can gradient-based training learn the rank needed to store and compose associations in a matrix memory? In our earlier study, we used a matrix-augmented reasoner on a task that admits a rank-1 solution, leaving this question open. We train matrix memories on $K$ fresh key-value bindings whose exact linear recovery requires $\mathrm{rank}(Z) \geq K$. A fixed linear readout queries a single matrix state without access to the original bindings. Experiments measure recovery by cosine similarity greater than 0.9, a threshold distinct from mathematical equality. Learned effective rank increases with $K$ across the tested grid (Spearman $\rho = 1.0$ at $d = 16$). Training-time rank caps produce a recovery transition near…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17575v1 Announce Type: new Abstract: Sharpness-aware minimization (SAM) doubles the cost of every training step, yet its benefit concentrates where training ends. We study where an expensive training mode should be spent and propose Temperon: a plain-SGD explorer for the first 43% of the epoch budget, then one scheduled hand-off that gives the entire final cosine anneal to a SAM-wrapped Muon refiner. On CIFAR-10/100, SVHN and Tiny ImageNet (five seeds, times reported as epochs-to-target times an idle-GPU-calibrated epoch cost), Temperon matches the best full-time-SAM recipe on accuracy everywhere while reaching the hardest common target 35%, 34% and 32% sooner on three of the four, and sits a tier above the published SAM+SGD recipe at level cost. Abl…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17572v1 Announce Type: new Abstract: Auditing vision-language models (VLMs) for societal bias requires distinguishing direct algorithmic valuation disparities from confounders embedded within archival metadata. In this study, we audit Contrastive Language-Image Pretraining (CLIP) models using historical artwork metadata from the Metropolitan Museum of Art Open Access collection (N = 1,500 total objects; N = 743 attributed works: Male n = 534, Female n = 209; n = 618 anonymous). We establish a quantitative audit framework evaluating zero-shot CLIP logit differential scores across three semantic prompt pairs (masterpiece, quality, and influence). Unadjusted evaluations demonstrate high score convergence without a statistically significant main gender e…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17571v1 Announce Type: new Abstract: Where in a Transformer is the change from memorization to generalization functionally expressed? We introduce Transition Games--behavior-aligned exact activation games with paired non-generalizing controls--and find distributed utility gain with a prospective block-0 attention bias; selected degree-two modes account for 67--92% of its addition contrast across replacement games, and a disjoint exact path study confirms that block-1 MLP mediates more of their effect than all other tested downstream paths in 12/12 pairs. The sharper "MLP memorizes, attention generalizes" prediction instead reverses (-.331 bits/example at the memory anchor; 0/12 in the predicted direction), while routing onset, global rank collapse, 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:2609.17564v1 Announce Type: new Abstract: Deploying retrieval-augmented generation (RAG) on commodity GPUs such as the NVIDIA T4 (16 GB VRAM) exposes a practical failure mode we call the Compression Paradox: neural prompt compression can add key-value (KV) cache contention and preprocessing latency that outweigh generation-time savings, while skipping compression can cause out-of-memory (OOM) failures on long contexts. We identify two distinct failure mechanisms when a vLLM-served LLM and a PyTorch-based compressor are co-deployed under tight memory budgets, and introduce the Tri-Metric Router, a deterministic, training-free policy that selects among Raw, Neural (LLMLingua-2), and Lexical (BM25) pipelines. The router uses three CPU-side signals: spatial c…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17560v1 Announce Type: new Abstract: Every production model is updated, by retraining, fine-tuning, quantization, or a silent vendor swap, and each update risks being worse than what it replaced. We formalize update promotion as certified paired risk-difference auditing. Our starting point is a support identity: the risk difference between two models lives on the inputs where they disagree, observable without labels. We build DISCERN, a sequential two-tier protocol. A zero-label tier certifies benign updates whose disagreement rate is below tolerance from unlabeled traffic alone. An audited tier labels only sampled disagreements through an anytime-valid confidence sequence, valid at every stopping time and under any label-routing rule, even an advers…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17731v1 Announce Type: new Abstract: High-resolution land use and land cover (LULC) products derived from Sentinel-2 imagery are widely used for environmental monitoring and land management, yet their performance can vary across regions with complex ecological gradients and heterogeneous surface conditions. In Quebec, these limitations motivated the development of a provincial 10-m land-cover product, the COTQ, designed to support annual monitoring of land occupation and soil artificialisation. This study presents a systematic evaluation of the COTQ product relative to three global 10-m LULC datasets: ESA WorldCover, ESRI LandCover, and Google DynamicWorld. This paper does not introduce a new mapping methodology but focuses on analysing the behaviour…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17699v1 Announce Type: new Abstract: We present NeMo Data Designer (NDD), an open-source, general-purpose framework for multi-modal synthetic data generation (SDG). Designed to be intuitive to use, NDD provides a declarative configuration format in which human and/or agent users define each dataset column, with column types spanning text, code, structured outputs, images, embeddings, and statistical samplers that are explicitly configured to steer dataset diversity. Additional column types and functionality can be introduced using the framework's flexible plugin system. NDD's configuration is an inspectable artifact, supporting workflow sharing and reproducibility. SDG is an inherently iterative process. NDD therefore builds a preview-and-revision lo…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17696v1 Announce Type: new Abstract: Document repositories evolve continuously. Guidelines and policies are revised, superseded, and re-uploaded, so the same content recurs in different wording and newer versions refine or contradict earlier ones. These inconsistencies belong to the growing collection rather than to any single document, yet existing work treats versioning, duplicate detection, and contradiction detection as isolated pairwise tasks and stops once a pair is labeled. We present GVD (Governed Versioning and Deduplication), a framework that unifies cross-document version linking with rule-level conflict resolution under an auditable update policy. Incoming documents are assigned to version families through bidirectional rule alignment, an…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17695v1 Announce Type: new Abstract: A large language model (LLM) agent can follow more graph paths without acquiring more independent evidence. GraphEcho tests whether agents mistake these repeated encounters for additional corroboration. The benchmark varies path counts and evidential origins while holding evidence content fixed, and evaluates both judgments and active exploration. Controlled synthetic experiments reveal model-dependent judgment shifts, but redundant supporting paths increase the share of repeated walks across all evaluated frozen agents. Provenance-aware post-training (PAPT) reduces revisits and improves synthetic accuracy, yet covers fewer distinct sources. On scientific claims, it continues to reduce repetition while accuracy de…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17688v1 Announce Type: new Abstract: Wearable assistants require episodic memory over egocentric video, yet current vision-language models face bounded frame budgets, growing visual-token costs, and long-context retrieval failures. Under these practical constraints, we study whether textual captions can serve as reusable episodic memory. We define the Episodic Memory Video Caption QA task and introduce CapMem, a human-annotated benchmark with 75 videos totaling 33.7 hours, and 1,000 multiple-choice questions across 16 scenarios. On long videos (>20 min), full-coverage CaptionQA with 30s and 60s caption windows outperforms direct VideoQA for 10/12 and 8/12 models, respectively. On the same video subset, a matched-frame control across six Qwen models r…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17637v1 Announce Type: new Abstract: Restricting what a module can read may improve what a system learns to compute. We test this in a preregistered confirmation with sixty four-cell systems sharing a frozen language-model backbone and communicating through learned continuous packets. Five conditions vary evidence masking, ownership markers, and replacement of foreign evidence with neutral filler, across six initialization clusters, each with two data orders, on one fresh task world. With markers available in both regimes, masking improved accuracy on held-out two- and three-operation compositions by median paired differences of 0.846 and 0.859; all twelve pairs cleared the required margins, and the full preregistered behavioral criterion passed. 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:2609.17635v1 Announce Type: new Abstract: City pedestrian counting systems now feed economic indicators, planning decisions and safety operations, yet the twins built on top of them treat the incoming stream as ground truth. We study what happens when it is not. We formalise stealthy false data injection for city-scale pedestrian sensing, where the map from latent flow to observation is far more rank deficient than in the power and water networks for which stealth has been characterised. Our twin estimates directed flows on the pedestrian street graph, assimilates counts through a learned graph-localised gain, and is trained against a flow conservation residual that couples metered and unmetered segments. Detection combines the innovation with that residu…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17633v1 Announce Type: new Abstract: The Graph Coloring Problem (GCP) is NP-hard and DSATUR stands as one of the fastest heuristics for it despite producing colorings that typically use more colors than state-of-the-art coloring algorithms. We propose SSLD (Semidefinite Spectral Learning with DSATUR), which improves DSATUR by preprocessing a first good color class before letting DSATUR complete coloring the rest of the given graph. We obtain this color class from a Semidefinite Programming (SDP), similar to an SDP used to compute the Lov\'asz theta number. To the best of our knowledge, SSLD is the first approach to improve DSATUR by preprocessing through fixed color classes. We evaluate SSLD against DSATUR and against a naive 1-color-class preprocess…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17632v1 Announce Type: new Abstract: Large language model (LLM) trading agents can combine market data, news, and executable analysis, but their behavior is often controlled by static hand-written tool-use policies that are fixed before deployment. This limits their ability to adapt how they gather evidence, invoke tools, verify signals, and manage risk under changing market regimes. We introduce EvolveTrade, a self-evolving framework that treats the system prompt of a tool-using trading agent as a text-parameterized policy. After each update interval, a Policy Agent revises this policy using accumulated decision traces and realized portfolio feedback, while keeping the backbone LLM fixed. The updated policy is then used for the next batch of trading…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.17631v1 Announce Type: new Abstract: AI-assisted claims can appear authoritative when evidence, analysis, human authorization, presentation, and correction history refer to different states. Provenance, attestation, and transparency expose history but alone do not specify the publication transition examined here. We develop Publication Authority as an exact-state, non-transferable, single-use publication capability and instantiate it in PAC-2026 (Publication-Accountability Calculus), a machine-readable AIJIM Protocol candidate. We evaluate its fourth bounded semantic freeze (SF-4), a fixed-profile specification designed for replaceable bindings. Six obligations govern evidence, runs and artifacts, measurement disclosure, authorization, surface corres…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Nunchux AI has released VC-Attention, a training-free low-bit attention kernel built for video Diffusion Transformers (DiTs). It targets 2 problems at once: value quantization error and a slow softmax stage. Why Attention is the Video Bottleneck Video DiTs flatten a clip into 1 sequence of spatiotemporal tokens and run full self-attention at every layer. A […] The post Nunchux AI Introduces VC-Attention: A Training-Free Low-Bit Attention Kernel That Speeds Up Video Diffusion Transformers 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：A rewrite this size wasn't affordable before agents. Here's what porting the Copilot agent runtime to 800,000 lines of production Rust actually took. The post Migrating the GitHub Copilot runtime to Rust, using Copilot appeared first on The GitHub Blog.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：OpenAI for Law brings frontier intelligence for law, custom firm workflows, connected legal data sources, and legal-grade controls for confidential client work.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：4-bit Rotational Quantization in Weaviate 1.39: the SIMD performance work, a centered tier, scaling analysis and a TurboQuant comparison.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： Release: datasette 1.0a40 Same security fix as 0.65.5, plus some neat new features and bug fixes: Plugins can now launch and manage background tasks using the new datasette.add_background_task() method. Thanks, Alex Garcia. I've migrated Datasette to httpx2 for features like the internal datasette.client.get() method. A whole lot of bug fixes, many of them stemming from a recent effort to triage issues for a 1.0 stable release. Tags: security, datasette

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： Release: datasette 0.65.5 Security fix for an issue where a trailing newline in a requested table name could bypass table permissions and expose private rows, reported by dpfkdlemtp in GHSA-h547-rmjf-5m2m. Tags: security, datasette

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Snap is introducing "Specs Intelligence," a new AI assistant that can connect other digital accounts to help you with things like work tasks and keeping track of travel information. It seems similar to AI assistants like Meta's Muse and Gemini's Spark, though Snap is pitching Specs Intelligence as an "anticipatory AI service" that "helps you manage what needs attention today, so you can make progress toward your longer-term goals." Like with other AI assistants, you can also chat with it. Specs Intelligence is being launched alongside Specs, Snap's first consumer pair of augmented reality glasses. But it's also available on iOS today in pre … Read the full story at The Verge.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Paper2Agent, published in Nature, converts papers into validated MCP tools, scoring 91.2% on 300 questions across 74 papers. The post Stanford Researchers Release Paper2Agent: Turning Research Papers Into AI Agents That Reproduce Results and Run on New Data 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：Perplexity decided it was paying too much for DynamoDB and wasn’t getting the control it wanted over read performance. So The post Perplexity’s AI agents helped build a database. They weren’t allowed to run it. appeared first on The New Stack.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：GLiFormer Large scores 91.10 F1 on nested JSON, near GPT-5.6-luna's 91.96, while grounding every value in source spans. The post Knowledgator Releases GLiFormer: A 575M-Parameter Encoder That Hits 91.10 F1 on Nested JSON Extraction Without Generating Tokens 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：The robot maker says its latest humanoid is designed to work alongside people, but analysts warn that industrywide safety standards remain underdeveloped.