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

+0新增论文
+0其中 AI 相关
+0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:2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 09:11 — 2026-11-16 09:11(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:2026-11-14 15:09库内论文最新更新时间:2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 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 23,348 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)
新论文 · v1arXiv:2611.14937

Caprese: Change Impact Recommendation Using History and Runtime Analysis

Sadjad Tavakoli, Saba Alimadadi

原文摘要

Change impact recommendation identifies program entities potentially affected by source code changes. Historical co-changes and runtime dependencies provide complementary evidence, particularly in JavaScript, where dynamic and asynchronous behaviour complicates dependency analysis. We present Caprese, an open-source framework for function-level change impact recommendation in Node.js. Given a change set, it produces a ranked impact set of potentially affected functions. It supports repository-based recommendation through confidence-guided mining of recurring, change-set-relevant co-change patterns of varying lengths; dynamic recommendation through execution-derived dependencies involving calls, callbacks, events, timers, and shared state; and hybrid recommendation integrating both analyses. Its modular implementation supports reusable analyses. Evaluation on ten open-source applications and 100 selected change sets shows that, on average across projects, 77.4% of the relevant functions among the top 60 hybrid recommendations are identified exclusively by one analysis, demonstrating substantial complementarity. Dynamic recommendation achieves the highest mean precision among the top five recommendations (0.65), while repository-based recommendation performs best when the ranking is extended to 60 recommendations (0.42). Hybrid recommendation outperforms TARMAQ on average but does not consistently outperform the individual modes. Caprese is publicly available with source code, documentation, and evaluation artifacts.

cs.SE

新论文 · v1arXiv:2611.14935

Do Large Language Models Show Racial and Sex Bias in Pain Management? A Counterfactual Audit of GPT, Claude, Gemini, Llama, DeepSeek and Qwen

Richard J. Young, Alice M. Matthews

原文摘要

Racial and ethnic minority patients receive less pain treatment than non-Hispanic White patients, and large language models (LLMs) used as medical AI could reproduce that bias. Prior audits tested a few proprietary models, stated race explicitly and rarely measured the models' own response instability. In exploratory, non-preregistered analyses, Study 1 had four open-weight LLMs assess six acute-pain vignettes in every combination of four races and two sexes, with identity stated or cued only by a name (two names per group), comparing each identity with a White male reference on the same case and sampling seed. In Study 2, 24 configurations of 17 models, including OpenAI's GPT-4.1 mini and gpt-oss, Anthropic's Claude Haiku 4.5, Google's Gemini 2.5 Flash, Meta's Llama, DeepSeek and Qwen, with reasoning on and off and at two precisions, answered the same vignettes and the 50 clinician-written Q-Pain cases. In this single-prompt, JSON-constrained task, no difference survived correction in Study 1, none of 1,386 comparisons survived the false discovery rate in Study 2, and every pain-severity difference was equivalent to zero within one point on a 0-10 scale (within a quarter point for 237 of 238 Q-Pain comparisons). Opioid decisions were bounded less precisely (Study 1 could not exclude differences of about 20 percentage points), so they show no detected difference, not proof of none. The few differences surviving correction within a model favoured Black patients. Models differed far more from one another and across their own settings than between patients (the reference patient received the high opioid dose in 6% to 93% of responses), although serving software, provider and prompt format also differed. Fairness audits of clinical AI should use several names per group, pair comparisons on the seed, report the noise floor and test each deployed configuration.

cs.CL · cs.AI · cs.CY

版本更新 · v3arXiv:2611.02433

Blueprint2CAD: Benchmarking Foundation Models on Engineering Drawing-to-CAD Render Correspondence

Alexander Valverde, Danny Xie-Li, Zhichao Wang, Marcos V. Conde

原文摘要

Engineering drawings specify mechanical parts through orthographic projections. Recognizing which part a drawing depicts underlies part search, design reuse, and digitization, yet no public benchmark measures whether vision models can do it. We introduce Blueprint2CAD, a benchmark for drawing-to-render correspondence: given an orthographic line drawing and a shaded render, usually from another viewpoint, decide whether they show the same part. Its data layer, BlueCAD-30K, applies an open drafting pipeline to 29,925 Zero-to-CAD models, adding view-aligned renders, clean and dimensioned drawings from six viewpoints, and surface-type metadata. Frozen encoders retrieve the matching part from a 10,000-model gallery with up to 65% Recall@1 when viewpoints are known but 43% when they are not, and the four encoders we test lie within six points of each other: viewpoint, not backbone, is the bottleneck. Six zero-shot vision-language models reach only 0.52-0.67 verification accuracy, with model-specific Yes/No biases that chain-of-thought shifts but does not remove; a quick LoRA fine-tuning on in-domain pairs improves verification accuracy by a few points but sharpens these biases and leaves the viewpoint failure intact.

cs.CV

新论文 · v1arXiv:2611.14931

Hint-Informed Self-Distillation for Reasoning Segmentation

Kunze Jiang, Yuchen Wang, Kang Li, Qixing Zhang

原文摘要

Reasoning segmentation requires identifying the target referred to by a query among visually similar objects, yet trajectory-level rewards cannot directly indicate which tokens provide relevant visual evidence. We propose Hint-Informed Self-Distillation (HISD), which uses target-disambiguation evidence for token-level credit assignment. An external model generates Segment Hints offline from training images, queries, and ground-truth target annotations, organizing target identity, discriminative attributes, confusable objects, and anchoring paths. A hint-conditioned exponential moving average teacher scores the student's own trajectories, and HISD computes the teacher-to-student evidence ratio over a token support set to adjust only the magnitudes of positive group-relative advantages, leaving nonpositive advantages unchanged. This design encourages concise reasoning while retaining the information needed for target disambiguation, and the student requires neither hints nor a teacher at inference. Under a unified training protocol, HISD improves ReasonSeg test gIoU and cIoU over our reproduction of DPAD by 3.00 and 3.55 percentage points, respectively. Across the five evaluated splits of ReasonSeg and the RefCOCO family, HISD achieves higher segmentation metrics than this baseline and reduces the average token count of valid reasoning spans by 80.17 to 91.83 percent.

cs.CV · cs.AI

新论文 · v1arXiv:2611.14929

Speech Tokenizers are Vulnerable: Transferable Semantic Attack and Robust Tokenizer

Zhisheng Zhang, Yifan Mi, Yixuan Zhou, Haiyun Li, Shengbo Cai, Dongfu Song, Ziang Xu, Jie Hao 等 9 位作者

原文摘要

Speech tokenizers serve as speech front ends, encoding input speech signals into representations for downstream models, such as automatic speech recognition (ASR) systems and large audio-language models (LALMs). In this paper, we find that speech tokenizers are fragile at the semantic level: small perturbations can disrupt their semantic encoding process and consequently cause severe degradation in downstream ASR and LALM performance. To study this vulnerability, we propose T-SemAttack, a transferable semantic attack based on a semantic encoder ensemble. By jointly drifting the representation spaces of multiple semantic encoders, T-SemAttack effectively disrupts the semantic content of speech while preserving perceptual quality, thereby inducing error features. We further analyze layer-wise representation drift and cross-model gradient alignment. Our findings show that perturbations can induce substantial shifts in deep semantic representations and that the input gradients of different surrogate encoders exhibit directional alignment. These observations suggest that shared adversarially sensitive directions in the input space may be a key factor underlying cross-model attack transferability. Building on these, we introduce ROSETok, a robust speech tokenizer that combines noisy training with robust semantic distillation to improve reconstruction fidelity and downstream SpeechLLM robustness. Extensive experiments on multiple datasets, 9 open-source and black-box ASR systems, and 4 LALMs demonstrate that T-SemAttack achieves strong transferable attack performance, while the proposed Robust Speech Tokenizer exhibits robustness under high-fidelity reconstruction and downstream tasks. Our code and demo are available at https://wxzyd123.github.io/t-semattack.

eess.AS · cs.AI · cs.CR · cs.SD

新论文 · v1arXiv:2611.14928

Provably Optimal HBT Legalization in Seconds: Certified Optima Reveal Where the Headroom Really Lies

Kadhir Parani, Manjunath Bezawada, Divya M, Kesana Jathin, Kolli Sarath, Sm Zobaed

原文摘要

Hybrid bonding terminal (HBT) legalization assigns every terminal of a face-to-face 3D IC to its own pitch-grid site with minimum total Manhattan displacement. Open3DBench reports that a reinforcement-learning (RL) legalizer reduces displacement by 19-22% relative to a sliding-window (SW) heuristic, but none of its legalizers is publicly released. We ask how much displacement any legalizer can still recover. We build an open benchmark of 21 design/pitch instances from Open3DBench placement data, with reconstructed greedy, SW (ViaLegal-style) and BTAssign-style baselines, and GEO-Exact, an exact solver that runs successive shortest augmenting paths over lazily generated spatial candidate edges. An independent dual certificate proves its assignment optimal on all 21 instances (relative primal-dual gap at most $8.2 \times 10^{-16}$). Against these optima, our SW reconstruction with ViaLegal's default configuration is on average 0.011% above optimal (worst 0.119%), while on the 16 contended instances BTAssign-style, a density-guided heuristic (DGHL) and greedy are 3.0%, 6.9% and 64.5% above. Headroom does appear outside this regime: with 2x2 windows SW reaches 34.1%, and above about 58% utilization, on three of six swept designs, it reaches 21.1% on bp, 27.5% on swerv and 8.9% on jpeg (217 further certified instances, and ten bp points checked against an independent exact solver). If the published 19-22% gain were measured on instances like ours, SW would have to be at least 24-28% above optimal on average, far more than any SW variant we tested at nominal pitch; the RL paper's own comparison with the Hungarian optimum puts its SW 3.05% above optimal on average. GEO-Exact is also about an order of magnitude faster than DGHL and SW in our harness (geometric means 8.1x and 40x; a compiled core against Python baselines on a shared server). Code, optimal values and certificates are released.

cs.AI

版本更新 · v2arXiv:2604.17861

GPUOS: A GPU Operating System Primitive for Transparent Operation Fusion

Yiwei Yang, Xiangyu Gao, Yuan Zhou, Yuhang Gan, Yusheng Zheng, Andi Quinn

原文摘要

Modern deep learning workloads often consist of many small tensor operations, especially in inference, attention, and micro-batched training. In these settings, kernel launch overhead can become a major bottleneck, sometimes exceeding the actual computation time. We present GPUOS, a GPU runtime JIT system that reduces launch overhead using a persistent kernel architecture with runtime operator injection. GPUOS runs a single long-lived GPU kernel that continuously processes tasks from a host-managed work queue, eliminating repeated kernel launches. To support diverse operations, GPUOS uses NVIDIA NVRTC to just-in-time compile operators at runtime and inject them into the running kernel through device function pointer tables. This design enables operator updates without restarting the kernel or recompiling the system. GPUOS introduces four key ideas: (1) a persistent worker kernel with atomic task queues, (2) a runtime operator injection mechanism based on NVRTC and relocatable device code, (3) a dual-slot aliasing scheme for safe concurrent operator updates, and (4) transparent PyTorch integration through TorchDispatch that batches micro-operations into unified submissions. The system supports arbitrary tensor shapes, strides, data types, and broadcasting through a generic tensor abstraction. Experiments show that GPUOS achieves up to 15.3x speedup over standard PyTorch on workloads dominated by small operations, including micro-batched inference and attention patterns. GPUOS improves utilization while remaining compatible with the PyTorch ecosystem.

cs.DC · cs.OS

版本更新 · v4arXiv:2507.11662

Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification

Moises Andrade, Joonhyuk Cha, Brandon Ho, Vriksha Srihari, Karmesh Yadav, Zsolt Kira

原文摘要

Verifiers--functions assigning rewards to agent behavior--have been key to AI progress in math, code, and games. However, extending gains to domains without clear-cut success criteria (e.g., computer use) remains a challenge: while humans can recognize desired outcomes, translating this intuition into scalable rules is nontrivial. Multimodal LLMs (MLLMs) offer a promising solution, given their world knowledge, human-preference alignment, and reasoning skills. We evaluate MLLM verifiers across web navigation, computer use, and robotics, spanning 13 models, 28 judge designs, diverse agent trajectories, and distinct downstream applications. We identify a critical limitation: a strong tendency for MLLMs to over-validate agent behavior, a phenomenon we term agreement bias. This bias is pervasive across models, is resilient to test-time scaling, and harms pipelines relying on MLLM judgments (e.g., self-improvement). We discuss principles for design and evaluation of verifiers, and introduce SGV, a method that improves verification by harnessing MLLMs' own capabilities via modulation of (un)conditional generation. First, an MLLM generates broad priors about desired behavior, independent of the data under evaluation. Then, conditioned on generated priors, it reasons over and judges a candidate trajectory. Our methods yield more human-aligned verifiers, with gains of up to 25pp in failure detection, 14pp in accuracy, and benefits extending to downstream applications. In self-improvement and online supervision, our verifiers boost task completion of a GUI specialist in OSWorld, a diffusion policy in robomimic, and a ReAct agent in VisualWebArena--surpassing the previous SOTA by 20pp. Finally, we release an updated version of VisualWebArena, featuring improved evaluators, high-fidelity environment parallelism with >10x speedups, and VWA-Lite, a 1/3-scale subset with comparable evaluation fidelity.

cs.AI · cs.CL · cs.LG · cs.MA · cs.RO

新论文 · v1arXiv:2611.14926

Understanding the Asymptotic Transience of Q-Learning via Distributional Expansion

Shengbo Wang

原文摘要

Q-learning has been empirically observed to exhibit substantial transient error. This transient remains uncaptured by the leading Gaussian limit because the central-limit normalization removes the smaller-scale displacement generated by the initial nonlinear evolution. On the other hand, worst-case finite-sample guarantees, while accounting for transient effects, can obscure the mechanisms responsible for the error on a particular problem instance. We develop a finer asymptotic analysis that gives an asymptotically exact characterization of this transient for a fixed instance. Specifically, for synchronous Q-learning in finite discounted Markov decision processes, we separate the last-iterate error into an optimal-policy temporal-difference (TD) component and a nonnegative displacement caused by maximization. The centered TD component has Gaussian fluctuations at scale $n^{-1/2}$, whereas the maximization transient is of order $n^{-1}$ and converges almost surely, after rescaling by $n$, to a random limit. This limit represents the propagated effect of maximization errors generated before the greedy policy stabilizes. We combine this characterization with an Edgeworth expansion of the TD component to identify the corrections to its Gaussian approximation, separating the effects of initialization, non-Gaussian TD fluctuations, and maximization. The results reveal how transient errors arise for individual Q-learning instances and how their effects persist below the central-limit scale.

math.OC · cs.LG · stat.ML

新论文 · v1arXiv:2611.14925

ToolTurns: Benchmarking LLM Agents in Multi-Turn Dialogue

Milad Gholami, Brendan King, Jeffrey Flanigan

原文摘要

Tool-using language models are increasingly deployed in conversational settings, yet most large-scale tool-use benchmarks focus on isolated requests. We introduce ToolTurns, a benchmark of 2,620 problems spanning 1,827 tools and 11,004 API endpoints across 47 categories. Each dialogue begins with an intentionally underspecified request and continues through two context-dependent follow-ups, testing clarification, tool use, and retention of conversational context. We also introduce an open-source user simulator that reveals withheld context through dialogue and generates follow-up requests, with a checker--fixer pipeline for improving its turns. Across nine language models, the best agent resolves 69.6% of individual requests but completes only 39.8% of full dialogues. Under this evaluation protocol, every evaluated model receives lower success scores on follow-up requests than on the initial request, and dialogue-quality rubric scores and task success can rank models very differently. Paired turn-level evaluation shows that the checker--fixer reduces detected dialogue defects, and blind human evaluation favors the revised turns. ToolTurns provides a testbed for evaluating whether agents sustain task success across multi-turn dialogue with tools.

cs.CL

新论文 · v1arXiv:2611.14924

Edge-Native Multimodal RAG: Hardware-Aware Quantization and Architectural Optimization for Consumer GPUs

Zahraa Selim, Menna Hamed, Wesam Ahmed, Sohyla Said, Sara Basheer, Rami Zewail

原文摘要

Deployment of retrieval-augmented generation (RAG) for Edge-AI is constrained by memory and bandwidth limitations. A standard 7B parameter model consumes 14 GB Video Random Access Memory (VRAM) in half-precision (FP16), precluding co-location of vector indices and Key-Value (KV) caches. This paper presents an engineering integration and empirical evaluation of a multimodal RAG framework optimized for consumer-grade Turing hardware (e.g., NVIDIA Tesla T4). Our system-level analysis identifies a critical trade-off: while generative pre-trained transformer quantization (GPTQ) offers superior throughput (51.6 tok/s), it exhibits significant context instability at 2048+ tokens on Turing architectures. Conversely, NormalFloat 4-bit (NF4) maintains robust long-context performance with viable latency (81 ms/tok). By coupling NF4 with a decoupled Florence-2 vision integration, we achieve visual reasoning with only 430 MB VRAM overhead. Furthermore, empirical observations of prompt-induced search space pruning show that structured prompting reduces latency by 47% without altering computational intensity (1.88 GFLOPs/token). The integrated architecture maintains an 8.37 GB footprint, establishing a viable RAG pipeline for 12-16 GB GPUs. Finally, structured few-shot prompting effectively compensates for quantization-induced reasoning loss, restoring mathematical accuracy from 35.0% to 92.0% across 200 trials.

cs.AI

新论文 · v1arXiv:2611.14922

A Transferable Pretrained 3D Model for Impedance Inversion with Sparse-Well Prior Conditioning

Gen Li, Zhaoyun Zong, Diqiong Jiang, Man Tang

原文摘要

Deep-learning-based seismic impedance inversion commonly requires retraining for each target survey, which may generalize poorly beyond the conditioning locations when well control is extremely sparse. We propose a transferable three-dimensional inversion framework that separates offline learning from target-survey deployment. A masked autoencoder first learns seismic structural representations from unlabeled multi-survey data, after which the frozen encoder is incorporated into an inversion network trained on synthetic geological models with sparse-well-derived low-frequency priors. During deployment, the complete inversion network remains fixed; the available conditioning well is used only to construct the low-frequency prior and align the global impedance range. Experiments on the Overthrust model show that the proposed method achieves the lowest full-volume NRMSE and reduces the P95 trace-wise NRMSE from 0.1310 to 0.1074 relative to the best target-trained baseline, indicating fewer localized large errors under different well locations. In a field survey with one conditioning well and three blind wells, it reduces the mean blind-well NRMSE by 20.95% relative to the target-trained U-Net while maintaining the highest correlation. These results demonstrate that the proposed framework transfers useful impedance information beyond the conditioning location with low deployment cost and without retraining the inversion network.

cs.LG · physics.geo-ph

新论文 · v1arXiv:2611.14920

Janus: One Agent, Two Roles for Digital Twin Construction and Network Orchestration

Peijun Hou, Yue Zhang, Yi Wei, Nan Cen

原文摘要

Next-generation wireless networks are increasingly large-scale, heterogeneous, and dynamic, posing significant challenges to network modeling and control. Digital twins offer a promising solution, but existing approaches typically rely on static models and decouple twin construction from network orchestration, limiting adaptability. Meanwhile, large language models (LLMs) provide strong reasoning capabilities but struggle with graph-structured data and are highly sensitive to prompt design, making inference unreliable. In this paper, we propose Janus, an agentic LLM-based framework that unifies digital twin construction and network orchestration within a closed-loop system. At the core of Janus is a novel NetTwin agent, which introduces a new one-agent, two-role paradigm, enabling a single agent to simultaneously construct the digital twin from partial observations while performing task-driven network decision-making. To realize this, we design a modular architecture with three functional roles, including planner, modeler, and coder, along with a newly designed unified prompt module that further enhances graph reasoning robustness. Extensive evaluations on wireless networks with up to 200 nodes and two representative tasks, including user association and SAGIN routing, show that Janus achieves over 90% digital twin accuracy and near-optimal performance with gaps within 10.53%, while maintaining moderate computational overhead. These results demonstrate the effectiveness, scalability, and generalizability of Janus, paving the way for AI-native autonomous wireless network orchestration.

cs.NI

新论文 · v1arXiv:2611.14918

DIVAL: Diffeomorphic Vector-Field Alignment for Nonholonomic Motion Planning

Yike Qiao, Xiaodong He, An Zhuo, Zhiyong Sun, Weimin Bao, Zhongkui Li

原文摘要

Conventional vector-field-based motion planners for nonholonomic robots consist of two steps: first designing a nominal vector field and then controlling the robot to follow it to approach the target. However, a nonholonomic robot cannot follow the vector field instantaneously and may collide with obstacles, due to the inevitable mismatch between the robot's initial heading and the vector field's direction. This paper proposes a diffeomorphic vector-field alignment (DIVAL) method, which aligns the vector field's direction with the robot's initial heading so the robot can follow the vector field from the start. Specifically, the nominal vector field is locally reshaped by applying a diffeomorphic deformation to the workspace, such that the reshaped vector field has the same direction as the robot's heading at the initial position and coincides with the nominal vector field outside the deformed region. Since DIVAL eliminates the initial heading mismatch, the nonholonomic robot can maintain heading alignment with the reshaped vector field throughout the motion. This heading alignment further ensures that the robot preserves the nominal vector field's properties, including obstacle avoidance, convergence to the target, and smooth control signals. Numerical simulations provide vector-field-tracking baselines where the nominal vector fields are reshaped with DIVAL. Compared to the original baselines, the proposed method achieves collision-free convergence in all trials and avoids control discontinuities. Hardware experiments on a ground vehicle further demonstrate collision-free convergence across different targets and initial conditions under real-world disturbances.

cs.RO · eess.SY

版本更新 · v2arXiv:2611.10375

CHARM: Certified Homology-Aware Reverse-scale Mapping via Diffusion-Guided Quotient Towers

Zhe Li

原文摘要

Conventional dimensionality-reduction methods optimize geometric fidelity but do not return auditable homology certificates or identify the input observations associated with nontrivial classes. Direct high-dimensional persistent-homology computation is costly, and its representatives are rarely linked to a shared planar view. We introduce Certified Homology-Aware Reverse-scale Mapping (CHARM), which augments two-dimensional coordinates with algebraically certified, sample-traceable structural records. Diffusion-guided cover proposals and homotopy-safe contractions compress the input neighborhood flag complex. A Cover Quotient Tower supports cross-scale representative tracking and exact $H_k$ certification when algebraic tests complete. Reverse-scale layout connects quotient-chain preimages to the same coordinates used for geometric exploration. Contraction preserves the input neighborhood flag-complex homotopy type; the quotient tower inherits a multiplicative 3-interleaving with coarse-hop Rips, and conditional distortion bounds connect it to original Euclidean Rips. In a fixed-seed benchmark of 22 datasets (41,637 samples), CHARM achieves the highest share of first- or second-place scores across 15 metrics. On nonsynthetic data, it ranks first or second on every metric and first on all four $H_0/H_1$ persistence-diagram metrics. CHARM couples strong nonsynthetic geometric performance with an auditable structural layer.

cs.LG

版本更新 · v3arXiv:2610.14671

SPARE: Shared Perception and Adaptive Retrieval of Evidence for Streaming Video Understanding

Senbin Xu, Zijun Zhang, Xinhua Wu, Li He, Jubo Feng, Li Qiao, Zhen Gao, Yan Zhang 等 10 位作者

原文摘要

Streaming video understanding requires answering questions from the observed video, with evidence drawn from recent observations or earlier events. Historical context can improve recall but may interfere with judgments based on recent frames. Its usefulness depends on both when it is introduced and which clips are selected, while relevance alone does not guarantee sufficient evidence for an answer. We propose SPARE, a framework that combines adaptive historical retrieval with visual encoder sharing. A lightweight gate predicts whether recent observations provide sufficient evidence to answer the question. When additional evidence is predicted to be necessary, a multimodal embedding model retrieves relevant historical clips to supplement the current context. LoRA instruction tuning trains the understanding model to use recent observations and retrieved history jointly and abstain when the evidence remains insufficient. To reduce redundant visual parameters, the understanding and retrieval branches share a visual encoder while retaining separate language backbones. Four linear adapters align the shared features with the retrieval model through distillation at the visual token and final retrieval embedding levels. With visual-only inputs, SPARE achieves 77.78% on the evaluated Real-time and Backward task groups of OVO-Bench and 73.31% on StreamingBench. Compared with Qwen3-VL-8B-Instruct evaluated at 2 fps, SPARE improves accuracy by 20.68 percentage points on OVO-Bench and 14.15 percentage points on StreamingBench.

cs.CV

版本更新 · v3arXiv:2608.13233

Fabrication of Complex Soft Robotics: Challenges, Solutions, and Optimization

Mohammed Abboodi

原文摘要

Manufacturing complex soft pneumatic actuators remains challenging because geometric fidelity, compliance, structural integrity, and airtightness must be achieved simultaneously. This study presents a manufacturing-focused evaluation of several fabrication routes for complex pneumatic structures, including heat-shrink forming, silicone casting, powder- and liquid-based additive manufacturing, and fused deposition modeling (FDM). The processes were assessed through process screening, baseline fabrication, failure analysis, and process improvement to distinguish inherent process limitations from correctable manufacturing defects. Heat-shrink forming was limited by geometric conformity, casting by mold accessibility and bonded interfaces, powder-based methods by residual material trapped within enclosed passages, and digital light processing by the material properties and post-processing requirements of the investigated system. FDM provided the most adaptable route because its dominant defects could be progressively reduced through process optimization. The results further showed that airtightness depends not only on nominal wall thickness but also on extrusion-path architecture, while support-free geometry is important when access for internal post-processing is limited. These findings establish a practical design-for-manufacturing approach in which process selection is guided by the compatibility between actuator architecture and manufacturing constraints. The proposed approach provides practical guidance for developing complex, flexible, and airtight soft pneumatic actuators for soft robotic applications

cs.RO

新论文 · v1arXiv:2611.14916

CuEVM: Scaling Smart Contract Execution on GPUs

Nhut-Minh Ho, Tien Tuan Anh Dinh, Quang Trung Ta, Fredrik Svantes, Xiaokui Xiao, Beng Chin Ooi

原文摘要

Smart contracts on Ethereum blockchain process transactions worth billions of US dollars daily. They run on top of Ethereum Virtual Machine (EVM) which executes transactions sequentially. This execution model creates a performance bottleneck, especially for new blockchain workloads with large numbers of transactions, such as security testing. We present CuEVM, a GPU-native and semantically complete EVM execution engine that treats transaction execution as a massively parallel data processing problem. It employs novel data structures and GPU-aware scheduling to accelerate execution. Unlike prior works that transpile the contract and rely on a host CPU for many operations, CuEVM supports complete EVM semantics natively on the GPU. It passes 100% of the Ethereum VMTests and 96.2% of the full execution-test suite. On a single commodity GPU, CuEVM executes over 8 million ERC-20 transfers per second, outperforming existing baselines by up to two orders of magnitude. We build a smart contract fuzzer, called CuEVM-fuzz, on top of CuEVM. The fuzzer achieves over a million end-to-end executions per second, up to 23x and 4.8x higher than the state-of-the-art CPU-based and GPU-based baselines, respectively.

cs.DC · cs.CR · cs.DB

版本更新 · v3arXiv:2610.09505

Bias-Aware Adjoint Calibration and Optimal Control of Stochastic Multiscale Bioprocess Digital Twins

Keilung Choy, Wei Xie

原文摘要

We develop a bias-aware digital-twin calibration and control framework for multiscale bioprocess models within a biological systems-of-systems (Bio-SoS) paradigm. The digital twin is represented by a stochastic differential equation (SDE) model and calibrated from sparse observations using quasi-likelihood estimation and adjoint sensitivity analysis. SDE generator-based moment expansions characterize truncation-induced parameter bias, while forward-backward adjoints quantify how calibration uncertainty propagates to value functions and policy performance. The resulting parameter-error distribution supports both policy-directed data acquisition and uncertainty-aware policy optimization through a second-order Gaussian-averaged objective. We characterize the asymptotic behavior of the resulting exploration criterion and derive a physical-system performance under the optimized policy. To implement these ideas, we develop an Actor-Simulator algorithm that jointly updates model parameters, selects informative experiments, and optimizes control policies. Numerical studies demonstrate improved calibration accuracy, sample efficiency, and control performance relative to state-of-the-art baselines.

stat.ML · cs.LG

新论文 · v1arXiv:2611.14912

Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data

Yunlong Hou, Fengzhuo Zhang, Yuan Cheng, Jiachun Pan, Xingyao Li, Zhuoran Yang

原文摘要

Large language models trained with Reinforcement Learning (RL) with verifiable rewards exhibit strong reasoning ability and broad generalization, whereas models trained with Supervised Fine-Tuning (SFT) are often viewed as more prone to memorization and limited transfer. This paper rethinks this distinction through the lens of SFT training data on widely used Qwen2.5 and Qwen3 series models. First, we study the role of data source and show that it is critical: a carefully mixed SFT dataset substantially outperforms data generated solely by a larger model. Second, we study the role of data scale and show that matching the number of correct rollouts between SFT and RL greatly improves SFT generalization, while matching the total rollout budget enables SFT to generalize as well as RL. Combining these two factors further enables SFT to generalize even better than RL. Third, by using LLM annotations to characterize the solution methods in training rollouts, we show that larger datasets cover more tail methods and that these tail methods provide generalizable reasoning signals. Finally, we support these empirical findings theoretically by analyzing the training dynamics of shallow transformers under both RL and SFT.

cs.LG · cs.AI

版本更新 · v3arXiv:2605.02350

A Near-optimal SQ Lower Bound for Smoothed Agnostic Learning of Boolean Halfspaces

Tim Sinen

原文摘要

We study the complexity of smoothed agnostic learning of halfspaces on $\{\pm 1\}^n$ under uniform marginals in the model of~\cite{KM25}, where each input coordinate is independently flipped with probability $σ\in (0, {1}/{2})$. We show that $L^1$ polynomial regression achieves runtime and sample complexity $\tilde{O}(n^{O(\log(1/\varepsilon)/σ)})$, and prove a nearly matching Statistical Query complexity lower bound of $n^{Ω(\log(1+σ/\varepsilon^2)/σ)}$. This complements the recent work of~\cite{DK26}, which established analogous bounds in the continuous setting under Gaussian marginals.

cs.LG

新论文 · v1arXiv:2611.14910

MuEdit: An efficient multi-task editing method towards inter-domain knowledge conflicts

Songshi Liang, Ting-En Lin, Zixuan Huang, Yuchuan Wu, Yongbin Li, Zihe Wang, Rui Yan

原文摘要

Large language models (LLMs) require frequent knowledge updates across heterogeneous domains, but existing editing methods fail when applied sequentially to multi-task settings. We trace this collapse to inter-domain null-space misalignment: heterogeneous tasks induce distinct Jacobian geometries, causing their common null space to shrink dramatically and leaving insufficient admissible directions for conflict-free updates. We propose the Conflict Index to quantify this geometric interference, and introduce Mu-Edit, which mitigates multi-task conflicts via (1) conflict-aware ordering to minimize cumulative interference, and (2) dynamic low-rank approximation to expand the null space when ordering alone is insufficient. Experiments across five functional domains and three backbones show that Mu-Edit significantly outperforms existing baselines in multi-task editing performance while preserving general capabilities, and remains effective under incremental task arrival.

cs.AI · cs.CL

新论文 · v1arXiv:2611.14909

Explicit Subspace Evasive Sets via Subspace Designs

Joshua Brakensiek, Yeyuan Chen, Mahdi Cheraghchi, Rohan Goyal, Venkatesan Guruswami, Aaron Putterman, Zihan Zhang

原文摘要

Given a finite field $\mathbb F_q$, we say that a set $A\subseteq \mathbb F^n_q$ is an $(r,c)$ subspace evasive set if and only if for any affine subspace $U\subseteq \mathbb F^n_q$ with bounded dimension $\dim(U)\leq r$, the intersection size $|A\cap U|$ is at most $c$. The probabilistic method shows the existence of $(r,c)$ subspace evasive sets with $|A| = q^{(1-ε) n}$ with $c = O(r/ε)$. However, the best explicit constructions by Dvir--Lovett (STOC 2012) and Ben-Aroya--Shinkar (CJTCS 2013) have $c$ growing as an exponential function of $r$. Here, we give an explicit construction of such subspace evasive set that achieves the intersection bound $c=O(\min(r\log(r/ε)/ε, r^2/ε))$ when both $r$ and $1/ε$ are constants. Our approach is simple and the key idea is to compose subspace design codes (Guruswami-Xing, STOC 2013) with a suitably chosen ``local'' subspace evasive set. As a corollary, we give the first construction of an explicit (strongly) capacity-achieving list-recoverable code with nearly optimal list size, circumventing all previously-known barriers to construction.

cs.DM · cs.IT · math.CO

版本更新 · v15arXiv:2203.05022

A proof of P != NP (New symmetric encryption algorithm against any linear attacks and differential attacks)

Gao Ming

原文摘要

P vs NP problem is the most important unresolved problem in the field of computational complexity. Its impact has penetrated into all aspects of algorithm design, especially in the field of cryptography. The security of cryptographic algorithms based on short keys depends on whether P is equal to NP. In fact, the security requirements for cryptographic keys are much stricter than those for P$\neq$NP, the security of the key must ensure not only a sufficiently high computational complexity to crack it, but also consider the security of each bit of the key, while fully avoiding the effectiveness of various attack methods. In this paper, we innovatively propose a new encoding mechanism and develop a novel block symmetric encryption algorithm, whose encryption and decryption can be completed in linear time. The key consists of 12 variables, for the attacker, in the case when only the plaintext-ciphertext correspondence is known, the problem of cracking the key is equivalent to solving a system of equations about 12 unknown variables $(w_{1}, w_{2}, ..., w_{11}, w_{12})$ together with some implicit variables which are generated by the encryption process. In this paper, we will prove that there is no universal algorithm without brute-force searching at least one variable during the process of verifying five variables $(w_{1}$, $w_{2}$, $w_{3}$, $w_{4}$, $w_{9})$ whose computational complexity is not greater than solving the 12 variables......

cs.CC · cs.IT

新论文 · v1arXiv:2611.14908

Hy ASR 3.0 Technical Report

Aoxiong Yin, Auden Li, Chao Huang, Chuanyang Hu, Eitan Wang, Ethan Zou, Fangming Feng, Guangyu Chen 等 63 位作者

原文摘要

We present Hy ASR 3.0, a large language model (LLM)-based automatic speech recognition (ASR) system that delivers strong recognition accuracy, supports flexible contextual conditioning, and maintains robust recognition performance across diverse speech conditions. Hy ASR 3.0 supports Mandarin Chinese, English and 13 Chinese dialect groups, including Cantonese. Among the evaluated systems, it achieves the lowest aggregate error rates on public Mandarin Chinese, English, and Cantonese benchmarks and the lowest error rates on the corresponding internal test sets, alongside first-tier dialect recognition performance. Beyond audio-only transcription, Hy ASR 3.0 supports multiple forms of external context, including hotword lists, question--answer dialogues, and summaries, enabling the use of task-relevant information during recognition. The model also leverages intra-utterance context to disambiguate homophonic and phonetically similar keywords using information from other parts of the same utterance, without requiring a separate contextual input. Evaluations demonstrate strong contextual recognition in both external-context and intra-utterance settings, as well as robust recognition of long-form speech, children's and older adults' speech, low-volume speech, and speech in noisy environments. This report describes the model architecture and training methodology and presents evaluations across recognition accuracy, context utilization, and robustness.

cs.CL · eess.AS

版本更新 · v2arXiv:2509.25705

How Diffusion Models Memorize

Juyeop Kim, Songkuk Kim, Jong-Seok Lee

原文摘要

Despite their success in image generation, diffusion models can unintentionally memorize and reproduce training data, raising serious privacy and copyright concerns. Although prior work has studied memorization from different perspectives, a unified account of how this reproduction occurs during generation remains incomplete. In this paper, we develop a mathematical account of this process in text-to-image latent diffusion models with classifier-free guidance. We trace reproduction across denoising steps through predictions of the final denoised latent made with and without the prompt. Assuming these predictions are Bayes-optimal and uniformly bounded, we show that sufficiently low loss on a training prompt--image pair enables the prediction made with the prompt to reproduce the paired training latent with high probability, even at the first denoising step. At this first step, we bound the difference between the prediction made without the prompt and the empirical mean of the training latents, showing how guidance amplifies the reproduced training latent's deviation from that mean. We then quantify how the latent passed between denoising steps carries prompt influence to subsequent predictions made without the prompt. When both predictions are sufficiently close to the paired training latent at the final step, their guided combination also reproduces it in the final generated latent. We also analyze how their difference evolves, showing that closer agreement alone does not establish reproduction. Finally, our account provides a unified explanation of existing detection and mitigation strategies.

cs.CV

新论文 · v1arXiv:2611.14907

Lines Are Ideas: Visual Creativity Assessment in Hyperbolic Space

Baoliang Chen, Zihao Lin, Hao Liu, Xiangjie Sui

原文摘要

Assessing human creativity from drawings provides a scalable way to evaluate human creative ability. However, existing approaches either rely on costly expert annotation or treat creativity as a single regression target, overlooking its underlying structure. Psychological theories have long emphasized that creativity emerges from balancing novelty and appropriateness. Motivated by this principle, we recast creativity as structured semantic deviation between paired drawings, where novelty measures the extent of departure from the original base sketch, and appropriateness determines whether such departures remain meaningful. This formulation naturally leads to a hyperbolic representation, in which novelty is quantified by geodesic distance and appropriateness is evaluated conditionally via a learned decision boundary, further regulated by an abstraction-conditioned adaptive constraint. Experiments on AuDrA-Drawings demonstrate state-of-the-art alignment with expert judgments and strong robustness under rater and task shifts. Beyond performance gains, our framework reveals an interpretable radial organization of creative variation, offering a principled geometric foundation for automatic creativity assessment.

cs.CV

新论文 · v1arXiv:2611.14904

SubGPU Pipelining: Intra-GPU Fine-Grained Spatial Parallelism for LLM Inference

Muralidhar Andoorveedu, Marius Juston, Tingkai Liu, Sanjay Patel

原文摘要

Large language model (LLM) decode is dominated by short, predominantly memory-bound kernels that make bursty use of on-chip execution resources and memory bandwidth. This paper introduces SubGPU Pipelining, a fine-grained, intra-GPU spatial execution model that cuts an operator graph into ordered contiguous segments, binds those segments to spatial stages backed by disjoint streaming-multiprocessor (SM) pools, and streams microbatches through the resulting schedule. Selecting the graph cuts, segment-to-stage binding, per-stage SM allocation, and microbatch size is a coupled optimization problem: each choice changes the overlap pattern, shared-resource contention, cache state, and execution times of the others. We evaluate SubGPU Pipelining through both simulation and silicon experiment using the GPT-OSS 120B workload with 32-GPU B200 deployment settings. The analytical shared-resource simulator searches across SubGPU pipeline structures and batch sizes to map the per-user/per-GPU throughput Pareto frontier. At matched per-GPU throughput, the modeled SubGPU frontier provides up to 2.2x higher per-user throughput than temporal execution, and at matched per-user throughput it provides up to 1.9x higher per-GPU throughput. To test physical feasibility and further validate the simulation results, silicon experiments are performed, using one B200 GPU to emulate a 32-GPU B200 deployment. The experiment evaluates one selected two-stage pipeline configuration at global batch 2,048 using CUDA Green Contexts and TensorRT-LLM kernels. Results show that SubGPU Pipelining improves mean DRAM read-plus-write throughput from 71.8% to 83.6% of peak, and reduces the 36-layer decoder iteration time by 10.33%.

cs.DC

版本更新 · v4arXiv:2610.33857

TrackTok: Semantically Persistent Tokens for Latent Video Generation

Nhi Pham, Christopher Wewer, Bernt Schiele, Jonas Fischer, Jan Eric Lenssen

原文摘要

We introduce TrackTok, an efficient video tokenization framework that produces object-aligned tokens, i.e., tokens that consistently encode the same semantic object across time, even as it moves, deforms, or undergoes partial occlusion. Conventional patch-based or existing holistic tokenizers produce token identities often tied to fixed image locations. In contrast, our approach learns temporally persistent object-aligned representations that bind visual features across frames into stable semantic units. This enables substantially more compact, continuous latent video representations, reducing the number of tokens required for downstream generative modeling with state-of-the-art flow models, while preserving the semantic structure needed for high-quality synthesis. Our tokenizer offers a favorable quality-efficiency trade-off. TrackTok achieves comparable class-conditional generative FVD on UCF-101 dataset at 8 times fewer latent tokens and better latency, and outperforms existing 1D tokenization baselines on frame prediction task on Kinetics-600 across low token budgets. These results suggest that object-aligned and temporally persistent tokenization is a promising direction for scalable video generation, where reducing latent token counts is critical for efficient modeling. Our code for this work is available at github.com/phamleyennhi/tracktok.

cs.CV

新论文 · v1arXiv:2611.14903

Epigraph Form Reinforcement Learning-based Safe Trajectory Tracking Control for Connected and Autonomous Vehicles

Xiaoke Yang, Jin Chen, Yafei Wang, Qi Zhang, Ming Li, Haiwen Wu, Chengliang Yin, Yong Zhang

原文摘要

Safe trajectory tracking (STT) aims to enable autonomous vehicles to follow a reference trajectory accurately while avoiding collisions. This problem is particularly challenging for Connected and Autonomous Vehicles (CAVs) in highly dynamic environments. Existing non-learning-based STT methods often use simplified vehicle and interaction models to meet real-time requirements, which may result in suboptimal tracking accuracy. Although Deep Reinforcement Learning (DRL) can help address this limitation, widely used Lagrangian DRL methods often suffer from unstable training because increasing Lagrange multipliers amplify policy-gradient magnitudes. To address these issues, we propose a novel reinforcement learning framework for STT, called STT Control Epigraph Form RL (STTC-EFRL). In this framework, the STT problem is formulated as an epigraph-form min-max optimization problem. Based on this formulation, we develop a learning mechanism that uses a decreasing scalar related to the epigraph to adjust the policy gradient descent direction without increasing the gradient magnitude, thereby improving training stability. We also develop a computationally efficient ray-casting method to compute a polyhedron scaling factor for safety quantification. Experimental results, including Vehicle-in-the-Loop tests, show that STTC-EFRL achieves higher tracking accuracy than the considered non-learning-based baseline and more stable training than widely used Lagrangian DRL methods, while satisfying safety requirements in connected environments.

cs.LG