跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 20:38 — 2026-11-16 20:38(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,827 已收录论文19,941 AI 相关6,921 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 17,708 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2607.23085

Common-Neighbor-Count-Based Representative Possible World Finding on Uncertain Graphs

Chengjie Gu, Xiaoliang Xu, Yuxiang Wang, Kai Yao, Mengzhao Wang, Tianxing Wu, Yingjie Xia, Xiangyu Ke

原文摘要

Given an uncertain graph $\mathcal{G}$ with probabilistic edges, a representative possible world (RPW) is a deterministic graph that closely preserves the expected value of a designated basic structural feature in $\mathcal{G}$. As a proxy for $\mathcal{G}$, the RPW allows us to directly obtain approximate expectations of the higher-order features related to this preserved basic feature, thereby avoiding expensive enumeration or sampling on $\mathcal{G}$. Existing RPWs preserve per-node features such as degree and triangle degree but overlook common-neighbor counts between node pairs. As a result, they may poorly approximate the expected values of higher-order features that depend on these counts, e.g., Jaccard coefficient. Therefore, we study the \underline{C}ommon-neighbor-count-based \underline{R}epresentative \underline{P}ossible \underline{W}orld (CRPW) problem, extending RPWs from node features to node-pair features. Our problem seeks the possible world that best preserves the expected numbers of common neighbors between node pairs, and we prove that it is NP-hard. To address it, we develop a two-stage basic algorithm that quickly initializes a possible world and then refines it iteratively. We next accelerate the refinement with a counting-based estimation, as the refinement only requires determining whether an edge state change to the possible world is beneficial, rather than computing its exact magnitude. Furthermore, we design a Beta distribution-based adaptive termination method to automatically stop the refinement once the desired quality of the possible world is reached, preventing over- or under-execution. Extensive experiments on five real-world uncertain graphs demonstrate the effectiveness of our algorithms in preserving structural features.

cs.DB

新论文 · v1arXiv:2611.16217

WorldDraft: If Code Builds the World, Can Video Models Just Render It?

Zhiyu Hou, Wen-Jie Shu, Harold Haodong Chen, Weilin Ruan, Chenfei Liao, Liuzhou Zhang, Disen Lan, Xiaogang Xu 等 10 位作者

原文摘要

Multimodal coding agents decouple 4D world construction from visual generation, repurposing video models from world generators toward generative renderers. This division of labor raises a fundamental question: if code builds the world, can video models just render it? A reliable generative renderer hinges on two complementary criteria: (i) world preservation, retaining prescribed 4D kinematics and camera paths; and (ii) visual realization, persistently binding text-specified target attributes over time. To evaluate this capability, we introduce WorldDraft, a benchmark of $432$ strictly paired test cases across $48$ executable 4D world families spanning six dynamic challenge categories. Under a $3 \times 3$ factorial design, WorldDraft orthogonally crosses draft granularity (abstract proxy to previs) and appearance alignment (neutral to conflicting) under identical dynamics. Extensive evaluations across $12$ representative models reveal that: (I) world preservation and visual realization remain in stark operational tension; (II) richer draft scaffolding anchors structure but paradoxically impairs appearance fidelity; and (III) conflicting source cues trigger severe source leakage (up to $64\%$), exposing fragile cross-modal disentanglement. To mitigate these bottlenecks, we propose WorldDraft-Primer, a plug-and-play visual prompting strategy that consistently improves both objectives across frozen video renderers. Together, WorldDraft and WorldDraft-Primer lay a foundation for bridging programmatic 4D simulation with video generation, advancing physically grounded generative rendering.

cs.CV

新论文 · v1arXiv:2611.16215

Guided Generation of Linux Kernel Semantic Patches with Small Local Language Models

Mohanned Ahmed

原文摘要

When a Linux kernel API changes, hundreds of drivers are converted by hand over months, and the earlier conversions are reviewed examples for the later ones. We ask whether small open language models running on a laptop can turn such examples into Coccinelle semantic patches, the rules kernel maintainers already use for tree-wide changes. We adapt guided code generation to this task: the training examples are decomposed by script into a tree of change variants, the model writes one small rule per variant under feedback from applying it to the examples, deterministic components repair SmPL syntax and generalise driver-specific names, rules are composed greedily, and a compile critic repairs or rejects a rule whose output does not build. We evaluate on a pre-registered test set of 7 migrations whose new APIs appeared after the training cutoffs of all three models (Qwen2.5-Coder 7B, Llama 3.1 8B, Gemma 3 4B), with 122 held-out driver conversions, counting a conversion as solved only if the rule's output matches the human fix and compiles. With the framework, Qwen2.5-Coder solves 35.3 conversions on average over three seeds (range 32-41), against 1.0 when prompted directly; Spinfer solves 41 and a frontier LLM agent 66. The local model solves fewer conversions than Spinfer but its rules are the most precise on the test set (0.74 of the files they change are solved, against 0.55 for Spinfer and 0.70 for the frontier agent), and the compile critic removes every output that matches the human fix but does not build. The two general-purpose models stay weak even with guidance (at most 12 solved). All code, prompts, model responses and results are released.

cs.SE · cs.AI

新论文 · v1arXiv:2611.16213

Visibility-Aware Task and Motion Planning with Task-Centric Perception

Sahit Chintalapudi, Xiaoyan Wang, Aryan Zoroufi, Aditya Agarwal, Nancy Kanwisher, Tomás Lozano-Pérez, Leslie Pack Kaelbling

原文摘要

Long-horizon manipulation under uncertainty remains a challenging problem in robotics. We present \ourmethod{}, an algorithm for Visibility-Aware Task and Motion Planning. \ourmethod{} extends existing deterministic task and motion planning solvers to partially observable object rearrangement tasks, while still being able to take advantage of the efficiency and compositional generalization over long horizons of the base solver. This extension interleaves sensing actions into a plan skeleton that assumed full observability, and uses a novel persistent object-based memory to fuse observations into object mesh hypotheses and an observed occupancy map. We evaluate \ourmethod{} on real-world tabletop rearrangement tasks which feature heavy occlusion and partial visibility and demonstrate that it outperforms baselines that do not perform active perception or have persistent memory.

cs.RO

新论文 · v1arXiv:2611.16212

SPEM: Scan-Prior Entropy Modeling for LiDAR Point Cloud Compression

Bojun Liu, Yangzhi Ma, Jie Li, Dong Liu, Li Li

原文摘要

LiDAR point clouds exhibit scan-induced spatial regularities that are informative for geometry compression. Existing scan-aware approaches often exploit these regularities by transforming coded geometry into spherical or beam-aligned coordinate systems. However, this couples acquisition priors with geometry representation, altering spatial partitioning and quantization, and potentially preventing exact recovery of the original Cartesian geometry. We argue that acquisition priors should guide probability modeling rather than dictate the coding representation. We propose SPEM, a Scan-Prior Entropy Modeling framework that exploits LiDAR scanning regularities within the entropy model without requiring coordinate transformation. We introduce a multi-frequency spherical rotary positional encoding that captures scan-aligned spatial relationships in both backbone self-attention and decoded-context retrieval. Building upon this encoding, we develop a decoded-memory autoregressive predictor that efficiently exploits previously decoded occupancy information through reusable key/value caches. Experiments demonstrate state-of-the-art performance in both lossy and lossless LiDAR geometry compression, highlighting the effectiveness of scan-prior modeling across different coordinate representations.

cs.CV

新论文 · v1arXiv:2611.16211

One Fuzzer, Many Reasoners: Adaptive Neuro-Symbolic Fuzzing with Reliability-Calibrated and Context-Gated Guidance

Jinghao Wen, Xianglong Yu, Shaohuang Wang, Xun Jiao

原文摘要

Neural-symbolic AI (NSAI) combines learned perception with programs, constraints, and compositional reasoning, but remains difficult to test because small semantics-preserving changes can alter grounded symbols and trigger discontinuous reasoning failures. Existing neural fuzzers mainly rely on neural coverage or representation-space feedback and do not provide a common testing interface for heterogeneous NSAI systems. We introduce NSAI-Fuzz, a unified semantics-aware fuzzing framework that separates task-specific valid mutation from architecture-neutral guided search and represents each candidate using five availability-aware, rank-normalized risk signals: boundary pressure, grounding uncertainty, representation drift, constraint violation, and archive novelty. We further propose Reliability-Calibrated Weighting (RCW), which learns dataset-model-level signal allocations from calibrated reliability, and Contextual Signal Gating (CSG), which adapts signal weights to the current candidate pool. We evaluate four NSAI systems across four reasoning tasks, nine compatible dataset-model cells, 20 policies, and 1,800 on-policy runs. Fixed five-signal guidance outperforms Random and Uniform in every cell, while RCW and CSG further improve over Fixed in all nine cells. Under matched mutation and query budgets, RCW and CSG achieve 16.17% and 16.06% aggregate failure discovery, compared with 6.06% for the strongest neural-fuzzing baseline. Wall-clock evaluation further shows that TensorFuzz requires 1.11x the runtime of RCW while achieving only 0.45x its failure throughput. These results show that effective and efficient fuzzing of heterogeneous NSAI systems benefits from a common neural-symbolic risk interface with adaptive signal allocation.

cs.AI · cs.LG

新论文 · v1arXiv:2611.16207

Core nonemptiness for $2/3$-convex games

Keisuke Bando, Toshiyuki Hirai, Kenzo Imamura, Ryuhei Mizutani

原文摘要

We study the core of $2/3$-convex games, a class of transferable-utility (TU) games that generalizes convex games, which requires at least two of any three distinct coalitions satisfy the supermodular inequality. We show that every $2/3$-convex game admits a marginal worth vector in the core, and hence has a nonempty core. Our proof is constructive and yields a linear-time algorithm for finding such a core allocation. We also show that $2/3$-convexity does not imply permutational convexity in general, while the implication holds under an additional superadditivity condition on pairs of singletons. As an application, we introduce a TU model motivated by the OSCE's consensus-minus-two procedure and show that the resulting game is $2/3$-convex but need not be convex.

cs.GT · econ.TH

新论文 · v1arXiv:2611.16206

Turning Multi-Agent Communication into Token-Level Credit with On Policy Self Distillation

Zixu Wang, Yu Zhao, Xing Zheng, Bingbing Xu, Tian Xueyun, JiaTang Luo, Weiqiang Wang, Bowen Song 等 10 位作者

原文摘要

Reinforcement learning improves problem solving in large language model multi-agent systems. Existing approaches overlook communication knowledge or compress it into scalar rewards, leaving coarse credit with little guidance on which decisions each agent should reinforce or revise. OPSD4MAS converts future communication into fine-grained token-level credit through On Policy Self Distillation (OPSD). An external model extracts facts and assesses their trajectory relations for coarse-grained filtering, followed by fine-grained leave-one-out filtering of target-token influence against agent-wise outcome advantages. The fact-conditioned policy supplies token-level credit, combined with GRPO through a linearly annealed joint objective. Our method improves mathematical pass@4 over GRPO by up to 20.00 percentage points. Ablations support complete filtering, while frozen-history injection diagnostics support fact utility. Together, these results support combining agent-level outcome guidance with communication-derived token-level credit. Code is available at https://github.com/Camel-Prince/OPSD4MAS.

cs.AI

版本更新 · v2arXiv:2611.05618

When can multi-fragment 2D/3D registration be trusted? Calibrated certification and uncertainty-driven view planning for pelvic fracture fluoroscopy

Bowen Xiang

原文摘要

Registering a segmented CT to fluoroscopy can locate every fracture fragment but can guide surgery only when trusted. After each shot, our closed loop registers all fragments, bounds their errors with a calibrated sandwich covariance, flags implausible or ambiguous ones, and stops or plans the next view. On simulated fluoroscopy of 60 held-out fracture CTs with realistic image uncertainty, 95% bounds covered 83% of unflagged fragments and 91% of those within 5mm, but from the second view on 14% failed by over 5mm, a third with bounds of at most 2mm. A fragment's shift when a view was added separated tightly bounded failures best (exploratory; AUC 0.94, bound 0.81). Requiring that the newest view moved no fragment beyond its bound, preferred post hoc, lowered false stops at 2mm from 23% to 6% overall, with 345 instead of 362 correct ones but more trajectories uncertified; delaying the stop did not, and other signals at equal acceptance left 10-15% false. With a segmentation error shared by all views (median Dice 0.89), 21% of this rule's stops were false against 10% without it (15 cases; exploratory). Minimax planning certified sooner than the clinical protocol without the check (4.20 versus 4.72 shots, Holm p <0.001), but no criterion reached the pre-specified endpoint, a true 2mm error, significantly sooner, even in the true basin. On real fluoroscopy of five intact pelves no 2mm certificate was false. Trust takes evidence across views, not only a calibrated local bound.

eess.IV · cs.CV

版本更新 · v2arXiv:2610.19423

Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training

Anshu Raina, Peyman Razaghi, Yuankai Chen, Cheng Yao, Yao Fu, Vidushi Goyal, Devang Patel, Wen Xie 等 10 位作者

原文摘要

Configuring distributed LLM training across hundreds of GPUs requires jointly optimizing tensor, pipeline, expert, context, and data parallelism alongside micro-batch size, recomputation, sharding, and overlap, a combinatorial space where memory legality can hinge on a single byte of activation accounting. Today, teams navigate it through expensive multi-node trial and error, burning GPU-hours on crashes and suboptimal recipes. We present Primus Projection, which closes this loop with two coupled components. First, a hybrid projection engine that measures what it can and simulates what it cannot: GPU microbenchmarks on as few as a single device capture compute kernels and any in-scope communication; a sub-node downscale-measure-upscale workflow analytically restores out-of-scope collectives, FSDP overlap, and the full pipeline schedule at the multi-node target. A pure simulation mode runs entirely on CPU, enabling pre-silicon planning without any GPU. Second, the Primus Tuning Agent treats the projection engine as a fast scoring oracle (seconds per candidate instead of tens of minutes) and uses it to drive an intelligent search over the configuration space. A deterministic seed planner sweeps single axes; an LLM investigation loop proposes cross-axis combinations the planner cannot reach, with an analytic memory pre-filter that rejects infeasible candidates before any GPU time is spent. Validated on Llama 3.1 (dense) and Mixtral 8x22B (MoE) across two GPU generations, all projections stay within ~10% of measured multi-node throughput, and fidelity holds at production scale: 4.7% error on DeepSeek V3 671B at 1,024 GPUs and 1.9% on Qwen3-235B-A22B at 256 GPUs. In a Mixtral 8x22B case study, the Primus Tuning Agent discovers a configuration delivering +27% throughput over the published 4-node BF16 reference at the same scale, in under 30 minutes of single-node exploration.

cs.AI · cs.DC

新论文 · v1arXiv:2611.16202

An Agentic Python Framework for LLM-Driven UVM Testbench Synthesis with Closed-Loop Compiler Feedback

Vikash Kumar

原文摘要

Protocol bridge verification is a persistent bottleneck in SoC development: for every new bridge instance, engineers hand-craft a full UVM testbench from scratch, consuming 40--100 engineering hours of bring-up effort. We present an agentic Python framework that generates complete, protocol-aware UVM testbenches for arbitrary IP and subsystem configurations from a structured Verification Manifest---a JSON specification encoding interface topology, protocol semantics, and coverage intent. The framework employs a dual closed-loop architecture: an inner compiler feedback loop that injects categorised UVM diagnostics rather than raw tool output, and an outer coverage loop driven by intent-gap analysis against the Manifest. Validated on the AMBA AHB-to-APB bridge---a representative production protocol bridge with a 7-state control FSM, two-phase APB handshake, and non-trivial burst serialisation logic---the framework achieves 96.8% functional coverage, a $4.7\times$ bring-up speedup, and a Protocol Verification Completeness score of 0.87, with only 2.1% of the generated 4,623-line testbench requiring human correction. The generated scoreboard independently identified a critical RTL functional fault that the manual baseline missed entirely. Generalisation across four protocol families confirms that speedup increases with protocol complexity, ranging from $3.1\times$ (APB Subordinate) to $6.1\times$ (CHI Subordinate).

cs.AR

新论文 · v1arXiv:2611.16201

An Extensive Evaluation of Machine Learning and Deep Learning Approaches for Sentiment Analysis: Insights from Amazon Customer Reviews

Muhammed Ihsan Corak, Cuiyuan Wang, Xiaowen Zhang

原文摘要

The rapid growth of user-generated text on online platforms creates opportunities for understanding customer opinion and supporting data-driven decisions. This study compares five traditional machine learning classifiers (Random Forest, Logistic Regression, Bernoulli Naive Bayes, Linear Support Vector Classifier, and Multinomial Naive Bayes) and six deep learning architectures (LSTM, Bi-LSTM, GRU, RNN, Attention, and FastText) for three-class sentiment classification of 568,454 Amazon Fine Food Reviews. Machine learning models used Bag-of-Words (BoW) and TF-IDF features limited to 5,000 terms; deep learning models used learned embeddings over a 20,000-word vocabulary. Models were evaluated on the original imbalanced data and on a random-oversampled balanced set of 1,070,469 reviews, using accuracy, macro and per-class precision, recall, and F1-score, and training time. On the balanced set, Random Forest with BoW achieved 99\% accuracy and the Attention model achieved 98.7\%. Linear SVC reached 89\% accuracy in 1 min 15 s, and Logistic Regression reached 90\% in 3 min 37 s. On the imbalanced set, the Attention model achieved 97.8\% accuracy, and FastText achieved 95.3\% in 3 min 26 s, while the RNN reached 91.9\% with a neutral-class F1-score of 0.08. Deep learning models were more stable across class distributions, whereas the best classical model depended on balancing. We also report a user-facing application that applies the trained Random Forest and Attention models to new review text. Because the labels are derived from star ratings, the results measure agreement with rating-derived sentiment classes rather than annotated sentiment; the dataset is a single source, and the findings should be read with that limitation in mind.

cs.LG

版本更新 · v4arXiv:2610.16102

Where Polanyi Meets Galois: Tacit Knowing as an Algebro-Deterministic Operation, Toward Re-rooting AI-Generated Science

Hiroyuki Chuma, Kanji Otsuka, Yoichi Sato, Kodo Yamauchi

原文摘要

Tacit knowing is an operating regime of one memory substrate, not a separate kind of content. In VaCoAl (CASRAM, PyVaCoAl), an algebro-deterministic hyperdimensional memory over GF(2), one DAG of bound records is read in two ways. With every collision repaired (Rescue), the trace is exactly auditable but no path outranks another; with collisions tolerated (Don't Care), a path-integrated confidence $CR_2$ ranks direct over circuitous routes without being stated. This audit-valuation complementarity formalizes Polanyi's claim that tacit and explicit knowledge are not sharply divided. (1) Polanyi's from-to structure reads as non-commutative binding. (2) Full explication destroys the valuation (Lemma 1), as with Polanyi's pianist; tacitness is contingent or regime-bound, placing Polanyi, Nonaka, Tsoukas and Collins on one substrate. (3) The same lemma answers the popular dual-process moral ("train slow System 2 to tame fast System 1"), which mirrors the two-store reading of knowledge Polanyi rejected; Mercier and Sperber's reply, that reasoning is intuitive inference about reasons, matches his. (4) To know a large DAG is to cull it. Simon answered Polanyi's Meno argument: a test and a generator suffice. The AlphaGo-to-AlphaProof lineage builds that answer, yet a checker audits an endpoint and values no path: the tacit is relocated, not removed, and results are verified yet rootless. (5) Collins's three tacit knowledges map to bound structure, substrate valuation and value binding. (6) Our mentor-student DAG charts tacit transmission. (7) AI-solved problems with few follow-ups (Tao) are rootless explicit knowledge, re-rooted when LLMs generate, VaCoAl keeps the trace and the community values. (8) On Mercier and Sperber's theory an LLM is a sophist; truth-seeking lies in collective tacit knowing, Polanyi's conviviality, which we conjecture extends beyond humans. Testable predictions follow.

cs.NE · cs.AI

新论文 · v1arXiv:2611.16198

"We Are the Dirty Hands": Reimagining an Ambient Intelligence Care System with Professional Caregivers

Andrea Green, Jane L. E, Sneha Jain, Parker Ruth, Matthew Jörke, Sarah L. Billington, James Landay, Andrea Cuadra

原文摘要

While ambient assisted living (AAL) sensing systems offer promise for aging in place, their impacts on professional caregivers are overlooked. We conducted two collective speculation workshops (N=24) with personal health aides (PHAs, n=18) and certified nursing assistants (CNAs, n=6) to examine the ethical implications and value tensions of a care system with ambient intelligence (CSAI), our conceptualization of an AAL. Participants anticipated different implications across care roles and settings. PHAs anticipated additional responsibilities from CSAI, including learning how it operates and supporting older adults in its use. CNAs, who had greater access to workplace resources and protections, similarly noted that CSAI could create additional work. Participants also identified tensions around visibility, as sensing could support caregivers by documenting difficult working conditions while simultaneously making their behavior more vulnerable to misinterpretation. Through their modifications and surfaced discussions, we propose design guidelines for AAL systems, such as integrating context-aware sensing.

cs.HC

版本更新 · v2arXiv:2611.12048

Evaluating AI Agents for Industrial-Level Chip Floorplanning: A Framework and Empirical Study

Nova-Silicon Team

原文摘要

Floorplanning is an early step in turning a logical circuit into a physical chip: it positions large circuit modules and constrains the space available for subsequent logic placement and wiring. These decisions affect congestion and timing, but their physical consequences emerge through downstream implementation. For AI agents, the task requires translating engineering constraints into spatial decisions whose quality cannot be judged by successful tool execution alone. We present an evaluation framework that connects submitted layouts to a prescribed downstream implementation flow, checks geometric validity, measures physical quality, and reports resource use. On one industrial design whose 99 macros occupy approximately 71\% of a fixed L-shaped layout region, we compare our specialized system Nova-SI with general-purpose engineering agents and agents restricted to file access, obtaining complete physical measurements for 39 layout outputs. Under our 0--100 composite quality score, Nova-SI achieves a mean of 57.97 without online feedback from the prescribed power-grid and placement evaluation, compared with 31.17 for the strongest measured general-purpose configuration, GPT-6 Astra. The difference is supported by raw congestion and timing measurements and persists across scoring-sensitivity checks. Layout-level analysis further shows that similar global utilization can conceal substantially different local congestion. Together, the protocol and case study assess agents through the physical consequences of their delivered layouts and provide evidence about system performance on this industrial instance.

cs.AI

新论文 · v1arXiv:2611.16194

GA-HEL: A Knowledge-Driven Expert System for Open-Set, Granularity-Aware Hierarchical Event Linking in Social Media

Shengqi Zhou, Zhigang Liu, Wenxiang Zhu, Zhentao Cang

原文摘要

Social-media event intelligence requires a system to determine whether a post belongs to a registered event space, identify the supported hierarchy path, and stop at the deepest level warranted by the evidence. We formulate this requirement as open-set hierarchical event linking over frozen Storyline--Episode--Atomic Event Cards. GA-HEL implements a three-stage, knowledge-driven expert-system funnel: open-set scope control limits candidate exposure before hierarchical reasoning, hierarchy-aware decoders select a supported path and depth, and deterministic legal-path validation checks each record before database-compatible use. A 200-post Pilot supports task and mechanism development, while a separately annotated 497-post Expansion set evaluates transfer across four held-out Storylines and a hard-negative pool. Method implementations, prompts, Event Cards, candidate order, and six systems' predictions were frozen before Expansion Gold annotation. The resulting evaluation combines end-to-end hierarchical matching, open-set rejection, structural validation, ablation, cross-Storyline analysis, and an independent expert reannotation of a fixed audited subset. GA-HEL remains competitive with strong global full-card reasoning while providing explicit scope control and hierarchy-valid structured records. Error analysis identifies unsupported descent from Episode-level evidence to Atomic Events as the dominant remaining challenge. The task definition, frozen resource, and auditable protocol provide a reproducible foundation for scope-aware event intelligence. Code, Event Cards, labels, frozen predictions, and evaluation scripts are available at https://github.com/SHbiao/GAHEL_release.

cs.IR

新论文 · v1arXiv:2611.16192

Weak Composition Theorems for Randomized Communication

Pachara Sawettamalya

原文摘要

We present two results towards the randomized communication complexity of composed functions. Our contributions include: - \textbf{Lifting-by-Influence.} For any binary function $f$ and any outer gadget $g:\{0,1\}^n \rightarrow \mathbb{R}$, we show that up to additive terms, computing $g \circ f^n$ information-theoretically requires solving at least $\operatorname{Inf}(g)$ instances of $f$, where $\operatorname{Inf}(g)$ denotes the total influence of $g$. To our knowledge, this is the first composition lower bound for randomized communication that applies to \emph{every} choice of $f$ and $g$. - \textbf{Symmetric Composition.} When $g$ is a symmetric function with a value transition at Hamming weight $d$, we strengthen the number of required instances to $\min\{d,n+1-d\}$. As an implication, this recovers the previously known direct-sum theorem, XOR lemma, and majority lemma. Our proofs develop novel and distinctive usages of the classical \emph{input embedding} argument of Barak, Braverman, Chen, and Rao (SICOMP 2013). As an additional ingredient, we introduce a new public sampling framework that avoids auxiliary communication during the recovery phase of the protocol, ultimately reducing the extra cost from $O(n)$ bits of information to just $O(1)$.

cs.CC

版本更新 · v2arXiv:2611.03093

An Experimental Study of Hybrid Retrieval, NLI and Open-source LLMs for Scientific Claim Verification

Lakshmi Narayanan P, Narenkarthik K, Naren Kumar C

原文摘要

Claim verification is the task of deciding whether a source text supports a claim, contradicts it, or lacks sufficient evidence. Natural Language Inference (NLI) models can judge whether a single sentence supports or contradicts a claim, but they struggle when the evidence is spread across several sentences. Conversely, Large Language Models (LLMs) can reason across sentences, but may draw conclusions the text does not support. In this experimental study, we test whether a conservative fusion rule, labeling a claim Support or Contradict only when both models agree and defaulting to Not Enough Evidence otherwise, combines their strengths. We construct a benchmark of 2,035 claims from SciFact and CliniFact (858 Support, 152 Contradict, 1,025 Not Enough Evidence). We retrieve the top five most relevant sentences per claim using a hybrid of semantic and lexical (BM25) retrieval, which slightly outperforms either method alone. These retrieved sentences are then provided to every verification model. We then compare a DeBERTa-v3-base-mnli-fever-anli NLI baseline against Llama 3.1 8B, Qwen3 8B, and Mistral 7B. Qwen3 achieves the highest Macro-F1 (0.7937), followed by Llama 3.1 (0.7204) and Mistral (0.6388), while the NLI baseline reaches only 0.3157. Contrary to our hypothesis, fusion degrades performance, dropping Macro-F1 to 0.7392, 0.6730, and 0.5991, respectively. To understand this decline, we analyze agreements, disagreements, and common error patterns between the NLI and LLM verifiers. Our error analysis shows that NLI and LLM disagreements often result in correct LLM predictions being overturned.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.16190

When can an interpretability claim be trusted? Stability and certification of feature dimensionality, ridge leverage and the feature recovery rate

Ali Tajfar, Behnam Tajfar

原文摘要

Interpretability tools increasingly support safety claims, such as that a sparse dictionary has recovered most of a model's features. Such claims rest on measurements with arbitrary thresholds, and small changes to the model weights, a different training seed or a different threshold can reverse them. We study two widely used measurements in toy models and synthetic dictionaries with known ground truth: the feature dimensionality of Elhage et al. and the feature recovery rate (FRR) with a cosine threshold. We characterize exactly where feature dimensionality is discontinuous and replace it with a regularized (ridge) version with sharp stability bounds: the ridge leverage score changes by at most $3\sqrt{3}/(8\sqrtλ)$ times the operator-norm change of the weights, and this constant cannot be improved; for the regularized dimensionality the stability constant grows like $ρ/4$ in the scale $ρ=R/\sqrtλ$, with explicit upper and lower bounds. We also prove certificates stating when a claim "feature $i$ is recovered" must survive a given change of the dictionary. The certificates held in every test and are informative for small perturbations, but certify no feature non-trivially across independently trained dictionaries; at the standard threshold, whether a feature counts as recovered changed with the training seed for 55 percent of features. Experiments use toy models only. The proofs, code and text were drafted by AI agents directed by the authors and checked by an independent blind AI reviewer and by numerical tests; the authors take full responsibility for the content.

cs.LG · cs.AI

新论文 · v1arXiv:2611.16189

SBA: A Practical Memory Performance Denial-of-Service Attack

Amin Mamandipoor, Connor Rudy Sullivan, Cole Ridge Strickler, Mohammad Alian, Heechul Yun

原文摘要

Modern cloud platforms use memory bandwidth regulation to isolate co-located workloads, implicitly assuming that high aggregate bandwidth consumption implies high interference. We show that this assumption is fundamentally flawed. We present the Single-Bank Attack (SBA), a practical memory denial-of-service attack that induces extreme cross-core slowdowns---over three orders of magnitude on memory-intensive victims (e.g., LLM decode)---while consuming less than 1 GB/s of memory bandwidth. SBA exploits the gap between peak and worst-case DRAM throughput by concentrating memory write operations on a single bank, forcing persistent row conflicts and frequent write draining, thereby collapsing the memory service rate. Across Intel and AMD systems, including DDR5- and HBM2E-based platforms, SBA consistently causes orders-of-magnitude slowdowns under realistic multi-tenant settings, revealing a fundamental limitation of bandwidth-centric memory isolation. We further show that this localized contention propagates system-wide: single-bank congestion saturates memory controller queues and induces back-pressure into shared cache and coherence structures, ultimately throttling memory request injection across cores. Consequently, severe interference can arise even at low aggregate bandwidth, evading existing bandwidth-based QoS mechanisms such as Intel RDT MBA. To address this limitation, we propose IQ-MemGuard, a lightweight, software-based memory bandwidth regulator that detects sustained contention using microarchitectural signals and selectively throttles pathological request injection. Our implementation on an Intel platform effectively mitigates SBA, whereas Intel's hardware QoS mechanism fails completely.

cs.AR

新论文 · v1arXiv:2611.16188

PERA: Plug-in Experts for Robotic Actions in Continual Whole-Body Control

Shangchao Hu, Yadan Sun, Xibo Yu, Wei Huang

原文摘要

Motion imitation enables humanoid robots to acquire whole-body skills such as walking and dancing. However, fine-tuning an entire policy for a new skill can affect existing behaviors, while training a separate policy for each skill increases training and maintenance costs. We present PERA, a method for learning new skills by reusing existing motion capabilities. PERA freezes a pretrained mixture-of-experts policy and trains an additional task expert and its routing score using task rewards or teacher-action supervision. In Unitree G1 simulation, each added task module contains approximately 1.03% of the parameters of the base actor. Built on our pretrained policy, PERA successfully completes all ten new tasks. Disabling the expert restores the original computation path of the base policy, which still fully executes all 126 original motions. Enabling the expert also improves the execution of some dance motions not used to train that expert, indicating that its benefits extend beyond its training motions. Experiments with HoloMotion further demonstrate the applicability of PERA to different base policies.

cs.RO

版本更新 · v4arXiv:2511.03398

A Class of Self-Orthogonal, NMDS, or LCD MDS $(\mathcal{L}, \mathcal{P})$-Twisted Generalized Reed-Solomon Codes

Zhonghao Liang, Chenlu Jia, Dongmei Huang, Qunying Liao, Chunming Tang

原文摘要

Maximum distance separable (in short, MDS), near MDS (in short, NMDS), linear complementary dual codes (in short, LCD) and self-orthogonal codes play a pivotal role in algebraic coding theory, particularly in applications such as quantum communications and secret sharing schemes. Recently, the construction of non-generalized Reed-Solomon (in short, non-GRS) codes has emerged as a significant research frontier. This paper focuses on a class of $(\mathcal{L}, \mathcal{P})$-twisted generalized Reed-Solomon (TGRS) codes $\mathcal{C}_{k-1}\left(\boldsymbolα,\boldsymbol{v},\boldsymbolη\right)$ characterized by $\ell+1$ twists. By considering a special class of parity-check matrices derived from existing results, we derive the corresponding necessary and sufficient conditions or sufficient conditions for $\mathcal{C}_{k-1}\left(\boldsymbolα,\boldsymbol{v},\boldsymbolη\right)$ to be self-orthogonal, and then generalize the corresponding results given by Liu et al. (2021), Sui et al. (2021), and Zhang et al. (2025). As applications, leveraging these self-orthogonal structures, we can obtain several families of LCD MDS codes. Secondly, we provide a characterization of the NMDS property for the codes $\mathcal{C}_{k-1}\left(\boldsymbolα,\boldsymbol{v},\boldsymbolη\right)$, offering a partial solution to the open problem concerning general $(\mathcal{L}, \mathcal{P})$-TGRS codes posed by Hu et al. (2025). Finally, we rigorously prove that the codes $\mathcal{C}_{k-1}\left(\boldsymbolα,\boldsymbol{v},\boldsymbolη\right)$ are of non-GRS type when $2k > n>k+\ell+2$.

cs.IT

新论文 · v1arXiv:2611.16184

Flow-CAD: Flow Matching for Contextual Anomaly Detection and Explanation in Tabular Data

Zhong Li, Qi Huang, Yuhang Wang, Yang Cao, Thomas Bäck, Niki van Stein, Matthijs van Leeuwen, Lincen Yang

原文摘要

Contextual anomaly detection in tabular data aims to identify objects whose behavior is unexpected under their contextual conditions. In data-engineering pipelines, this task screens table rows whose measurements violate context-dependent integrity relationships. Most existing approaches rely on either shallow conditional models with limited distributional expressiveness or localized estimators that require per-context modeling, making it difficult to capture complex conditional relationships and scale to high-dimensional settings. We propose Flow-CAD, a new framework for contextual anomaly detection based on Flow Matching. Flow-CAD learns a single global and amortized conditional generative model that flexibly represents behavioral distributions conditioned on context, without assuming simple parametric forms or retraining local models. To enable robust and interpretable anomaly scoring, we introduce a scale-normalized and truncated residual energy derived from the learned conditional flow, which stabilizes anomaly scores, mitigates domination by extreme deviations, and supports feature-wise attribution. We further provide theoretical insights showing that the proposed residual-based anomaly score is stable under velocity estimation error, and that its Monte Carlo estimator satisfies concentration bounds. Experiments on 20 benchmark datasets with 13 competitors demonstrate that Flow-CAD has the best average rank for PR AUC, ROC AUC, and P@n, highlighting its effectiveness and practicality for contextual anomaly detection in tabular data. We provide the source code at https://github.com/ZhongLIFR/FlowCAD.

cs.LG

新论文 · v1arXiv:2611.16183

Data-Efficient LLM Safety Alignment Guided by Interpretable Features

Hongyu Li, Zhan Yu, Zhe Zhao, Kimmo Yan, Xiong Kuang, Renfen Hu

原文摘要

Existing large language models typically rely on massive fine-tuning datasets for safety alignment, which results in higher costs for safety alignment and often leads to the problem of over-refusal. We propose Less is Safer (LIS), a compact yet highly effective dataset for safety alignment, constructed through interpretable feature-guided selection and adversarial synthesis. Specifically, we leverage Sparse Autoencoder (SAE) activations to efficiently select prompts that cover diverse and interpretable safety features. Then, we employ a multi-agent adversarial synthesis framework to generate harmless prompts that nevertheless elicit unnecessary refusals. LIS contains only 2.4K samples, yet outperforms much larger datasets, e.g., TRIDENT-Core (26K), TRIDENT-Edge (19K) and WildJailbreak (262K), in overall performance on four safety and five over-refusal benchmarks. Through ablation experiments, we demonstrate that neither safety data nor over-refusal data alone can achieve optimal results. We also used safety features from SAE, annotated by an LLM, for data filtering, but the results were inferior to those obtained using the pipeline proposed in this paper.

cs.CL · cs.AI

新论文 · v1arXiv:2611.16180

Fast Serverless LLM Cold Starts by Sharing and Prewarming Startup Work

Hongjin Kim, Igjae Kim, Kwanghoon Choi, Minho Ha, Jaehyuk Huh

原文摘要

When a serverless LLM platform launches a model worker on demand, the cold start lasts roughly a minute, yet only 5-11% of it is spent loading weights. Most of the remainder goes to compilation, memory profiling and runtime setup, which each server performs again even though the outcome is identical across servers or independent of the model. We present Cairn. The server that is first to start a model publishes the weights and engine artifacts to a CXL memory pool shared across the cluster, and the remaining servers read them in place. Model-independent setup is completed ahead of time inside warm containers, and a template process replaces each container as soon as it is used. With ServerlessLLM on vLLM v0.20, six models from 1B to 14B, and two servers that share an emulated CXL pool, Cairn speeds up cold starts by 4.1-5.2x on servers without a checkpoint of their own and reduces median TTFT on a request stream by 64%.

cs.DC

新论文 · v1arXiv:2611.16176

A One-Sided Sublinear-Query Tester for Bounded-Degree 2SAT

Yuichi Yoshida

原文摘要

We give a one-sided tester for satisfiability of 2CNF formulas in the bounded-degree model. For every degree bound $Δ$, distance parameter $\varepsilon>0$, and $ν\in(0,1/2)$, its query complexity on $n$-variable formulas is $\widetilde O_{\varepsilon,Δ,ν}(n^{1/2+ν})$.

cs.DS

版本更新 · v2arXiv:2604.21260

Calibeating Prediction-Powered Inference

Lars van der Laan, Mark Van Der Laan

原文摘要

We study semisupervised mean estimation with a small labeled sample, a large unlabeled sample, and a black-box prediction model whose output may be miscalibrated. A standard approach in this setting is augmented inverse-probability weighting (AIPW) [Robins et al., 1994], which protects against prediction-model misspecification but may be inefficient when the prediction score is poorly aligned with the outcome scale. We introduce Calibrated Prediction-Powered Inference, which post-hoc calibrates the prediction score on the labeled sample before using it for semisupervised estimation. This simple step requires no retraining and can calibeat the original score, improving it both as a predictor of the outcome and as a regression adjustment for semisupervised inference. We study both linear and isotonic calibration. For isotonic calibration, we establish first-order optimality guarantees: isotonic post-processing can improve predictive accuracy and estimator efficiency relative to the original score and simpler post-processing rules, while replacing the fitted isotonic score by its conditional-mean oracle yields no additional first-order variance reduction. For linear calibration, we show first-order equivalence to PPI++. We also clarify the relationship between existing estimators, showing that the original PPI estimator is a special case of AIPW and can be inefficient when the prediction model is accurate, while PPI++ is AIPW with empirical efficiency maximization [Rubin and van der Laan, 2008]. In simulations and real-data experiments, our calibrated estimators often outperform PPI and are competitive with, or outperform, AIPW and PPI++. We provide an accompanying Python package, ppi_aipw, at https://larsvanderlaan.github.io/ppi-aipw/.

stat.ML · cs.AI · cs.LG · econ.EM · q-bio.QM · stat.ME

新论文 · v1arXiv:2611.16173

Between Niti and Nyaya: A Society-Centered Framework for AI Governance

Snehalkumar `Neil' S. Gaikwad, Punya Aragula, Shiva Kruthi Palpanoori, Pratik Patekar

原文摘要

Governments are making decisions about AI before they can measure its public effects, and those decisions determine whether a person can learn that AI influenced an outcome, challenge it, and see it corrected. Research has documented what AI governance produces: principles, strategies, registers, and audits. However, we lack shared language for understanding AI policy while it is still being made. We introduce the Society-Centered AI Governance Framework, which gives policymakers, researchers, and the public a way to assess instruments in any jurisdiction by whether a person can get notice, challenge a decision, and see it corrected. It reads a jurisdiction's instruments together by date and binding status, separates an agency duty from a right a person can invoke, and traces which later instrument must enforce each commitment. We evaluated it in North Carolina using interviews with nine AI Leadership Council members, conducted before and after the state's 2026 AI roadmap, and a provision-level reading, with human-reviewed model-assisted coding, of 49 AI governance documents from 19 states. For the state's own AI systems, we find visibility-first governance: visibility duties are in effect, notice exists as an agency duty with no right a person can invoke, and AI-specific challenge and correction remain advisory. The roadmap assigns owners and dates to the missing protections, so the gaps are documented but not yet closed. Recent federal preemption proposals focus on AI development, so recourse for a state's own systems is likely to remain a state decision. We identify "legitimacy before protection" as a testable risk of visibility-first governance and name the milestones that would test it. More broadly, judging AI policy by who can act on what it makes visible lets the field assess recourse while policy is still forming, before harm occurs.

cs.AI · cs.CY · cs.HC

新论文 · v1arXiv:2611.16172

Self-Supervised Attention-Based Virtual Metrology for CMP MRR Prediction

Jonathan Adam Rico, Nagarajan Raghavan, Senthilnath Jayavelu

原文摘要

Chemical mechanical planarization (CMP) is a critical semiconductor manufacturing process where material removal rate (MRR) is a key metric for process monitoring and advanced process control (APC). Virtual metrology enables MRR estimation from process time series signals, supporting run-to-run(R2R) control and process optimization while reducing reliance on physical metrology. Existing approaches typically rely on simplified linear assumptions or require handcrafted feature engineering. In this paper, we propose Global Regression Pretraining(GREP), a self-supervised, attention-based framework for CMP MRR prediction. GREP learns temporal representations from unlabeled sensor signals through global proxy-target regression, followed by supervised fine-tuning for MRR estimation. The framework is evaluated against a feature-engineered supervised baseline under three conditions: limited labeled data, sensor noise, and temporal process drift. Experiments on the PHM 2016 CMP dataset demonstrate competitive performance under limited labeled-data conditions, with improvements in selected cases and performance largely comparable to the baseline across different labeled-data fractions. Both models exhibit relatively small changes in prediction error with increasing noise, while GREP achieves a 17.0% RMSE reduction in the final temporal interval.

cs.LG · cs.AI

新论文 · v1arXiv:2611.16171

MRxD: A Usage-Pattern Framework for Mixed-Reality Cross-Device Interaction

Yang Zhan, Yuxuan Huang, Yuchen Cai, Yichen Andy Yu, Xiaoran Yang, Ye Yuan, Qiao Jin

原文摘要

Mixed reality (MR) cross-device experiences often combine MR headsets with non-immersive devices such as laptops, tablets, and phones. Yet such cross-device design remains challenging because users must coordinate workflows across heterogeneous devices with different roles. This motivates our focus on usage patterns: recurrent ways in which people distribute and coordinate work across devices. Through a systematic analysis of 238 MR cross-device papers, we developed MRxD, a usage-pattern framework organized around three dimensions: user attention, task relatedness, and cognitive symmetry. Using these dimensions, we identified six usage patterns and synthesized the design strategies commonly used within each pattern. We further investigated the framework's application in design practice through a workshop (n=6) and the results suggest that MRxD can guide pattern-based design exploration and identify blind spots. We further discuss how usage patterns may shift or combine, and outline research gaps and design implications for future MR cross-device systems.

cs.HC