跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

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
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 05:06 · 全站最近入库：2026-11-07 17:43各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 05:56 — 2026-11-08 05:56（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：2026-11-08 05:06最近发现新增版本：2026-11-07 17:43库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 05:04（北京时间）
版本更新 · v3arXiv:2608.12035

How Far from Clinical Deployment? Evaluating the Complete Unsupervised Domain Adaptation Pipeline in Medical Imaging

Yiheng Xiong, Luisa Gallée, Daniel Santak Wolf, Heiko Hillenhagen, Michael Götz

原文摘要

Deploying unsupervised domain adaptation (UDA) in clinical practice requires choosing which algorithm to use and which of its trained models to ship. However, the deployment (target) domain is unlabeled, so models cannot be evaluated directly on it, leaving it unclear which to select. We address this by evaluating the complete UDA pipeline, considering both adaptation and label-free selection together. Our study covers eleven clinically relevant cross-domain scenarios from nine medical imaging datasets, with ten UDA algorithms and 13 label-free selection methods (validators), evaluating over 80,000 trained models in total. By this, we find that a capable adapted model usually exists, but identifying it without target labels is difficult: the validator-selected models leave a large and structural target performance gap to the best available one, with no evaluated validator consistently reliable. Towards closing it, we explore two strategies, ensembling and a small target-labeling budget; both narrow this gap but do not close it entirely. Overall, deployable UDA depends on the complete pipeline; addressing the less explored selection step could bring much of current UDA closer to clinical use. Our code is open sourced at \href{https://xiongyiheng.github.io/complete-uda-pipeline-site/}{Project Page}.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.10667

Constant-factor approximation of MinCostCSP with a conservative majority polymorphism

Marcin Kozik, Stanislav Živný

原文摘要

For a relational structure A, the Minimum Cost Constraint Satisfaction Problem is the following problem denoted by MinCostCSP(A): Given an instance of CSP(A) with rational costs on variable-value pairs, find a solution to the instance minimizing the sum of the chosen costs. For the exact minimization, a classification of MinCostCSP(A) in terms of A was established by Takhanov [STACS'10]. We focus on constant-factor approximations of MinCostCSP(A). DeHaan, Huang, and Lee recently showed that if A fails to admit a conservative near-unanimity polymorphism then MinCostCSP(A) is not constant-factor approximable [APPROX'25]. We provide a significant step towards a full classification, by proving a dichotomy for structures A admitting a conservative majority (also known as 3-near-unanimity) polymorphism. Our dichotomy criterion is not in terms of an algebraic condition on A but we show that this is unavoidable. We include a simple argument proving that no such condition exists.

cs.CC · cs.DM · cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.25522

PIMCQG: Co-Designing Billion-Scale Graph-Based Approximate Nearest Neighbor Search for Processing-in-Memory

Sitian Chen, Yusen Li, Yao Chen, Minwen Deng, Jintao Meng, Amelie Chi Zhou

原文摘要

Graph-based Approximate Nearest Neighbor Search (ANNS) has emerged as the dominant approach for large-scale AI applications, offering superior accuracy-efficiency trade-offs over alternative methods. However, graph-based ANNS is inherently memory-bound due to frequent and irregular graph traversal. This constrains CPU throughput due to limited memory bandwidth, while GPUs lack sufficient HBM capacity for billion-scale indexes. Processing-in-Memory (PIM) offers massive internal bandwidth by co-locating computation with data, making it a natural fit for irregular, memory-bound workloads. However, directly mapping graph-based ANNS onto PIM exposes severe algorithm-architecture mismatches: restricted per-PU local memory, costly inter-PU communication, heavy coordination overhead, and weak compute capability, forcing existing PIM-based ANNS to rely on cluster-based algorithms that plateau at low recall. We propose PIMCQG, an algorithm-hardware co-design framework through three optimizations: (1) a compact index reducing PIM-resident footprint by 14.5x; (2) an asynchronous pipelined scheduler fully utilizing host-PIM bandwidth; and (3) a multiplication-free distance kernel with less than 0.08% recall loss. Evaluations on three billion-scale datasets show up to 20x/17.1x throughput over CPU/GPU baselines, 129x over prior PIM accelerators at high recall, and scale well across multi-node and emerging PIM architectures.

cs.AR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04548

Predicting Void Points in Self-Occluding Forest Volumes

Benjamin Bachmayr, Mohamed Youssef, Oliver Bimber

原文摘要

Synthetic Aperture Imaging (SAI) enables drones to observe forest canopies by warping and averaging multiple displaced views at a common depth. However, occlusion is suppressed rather than eliminated, causing poorly observed regions to appear occupied and leading to systematic biomass overestimation. The Deep Forest project cannot distinguish reconstruction artifacts from real vegetation because its training data relies on measured reflectance points, excluding empty space and preventing the network from learning explicit occupancy boundaries. This thesis addresses the problem by modifying training labels rather than the imaging process. Each simulated scene is rendered twice: as a 9x9 grid of top-down captures for focal-stack generation and as 550 depth-clipped slabs derived from scene geometry to provide occupancy labels, explicitly representing void space as a negative class. A Gazebo pipeline generates procedural forest stands containing 80-200 trees across three species. A pretrained Pix2Pix model translates rendered RGB images into a synthetic near-infrared band, and Light Field Rendering produces aligned focal stacks of 550 planes across three channels. Four architectures were evaluated on a held-out scene. The plain 2D U-Net achieved an IoU of 0.6290, outperforming the volumetric 3D U-Net (0.5707). Established reconstruction methods performed substantially worse: COLMAP achieved 0.3446 and DepthAnything3 0.2959, both after their respective optimal dilation sweeps. An RGB-input variant of the volumetric architecture achieved the highest IoU of 0.6514 without dilation or per-scene calibration. These results highlight the limitations of conventional reconstruction methods, which recover visible surfaces but struggle to infer occupancy within closed canopies.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04546

Are LLM Assistants Regulatory Ready? Answers from regenold's 2026 EU AI Act Q&A Challenge

Marco Virgolin, Thomas Haszprunar, Maximilian Regenold

原文摘要

Large language model (LLM) assistants are increasingly proposed for regulatory affairs, yet their reliability in regulatory tasks remains unclear. We introduce the EU AI Act Q&A Benchmark, an expert-curated benchmark of 110 open-ended questions about the EU AI Act (Regulation (EU) 2024/1689). Each question comes with an exemplary answer, question-specific correctness criteria, and expected references. Evaluation measures answer correctness, reference quality, conciseness, tone, and latency, with a multi-turn ``hard mode'' testing responses to simulated user pushback. We also present the results of the 2026 EU AI Act Q&A Challenge, based on the benchmark, where three off-the-shelf baselines and five purpose-built assistants (from four commercial developers and one academic entrant) were tested. Only two of the five submitted assistants consistently outperformed the baselines; one achieved high scores across all evaluated metrics. These results show that specialist development alone does not guarantee better performance and highlight the critical importance of LLM assistant evaluation in regulatory affairs. The benchmark code is openly available at https://github.com/regenold-GmbH/eu-ai-act-benchmark-2026/.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04545

Coercive at the equilibrium, monotone nowhere: exact convergence certificates for learning in first-price auctions

Benjamin Lubin

原文摘要

The Bayes-Nash equilibria of an auction are the solutions of a variational inequality, and for standard auctions its operator fails every monotonicity notion, so the theory of monotone operators is unavailable to learning in auctions. We show what replaces monotonicity for the first-price auction: a certificate that is strong but local. For uniform values the single-population operator has an exact closed form and an exact Minty identity at the equilibrium; for two bidders its Gateaux derivative there is $L^2$-coercive with best constant exactly one in every piecewise-linear bid space with $m$ pieces, while the Minty inequality holds only on a ball whose radius decays like $m^{-5/2}$. The decay is exact: $m^{5/2}$ times the radius converges to $1/(8 \cdot 3^{1/4})$, and the worst perturbations converge to an alternating geometric profile with ratio $-(2-\sqrt{3})$. Refinement shrinks the ball, not the constant; independent learners see the same constant. For a general prior and bidder count there are two certificates, at the true equilibrium and at the equilibrium of the finite-dimensional bid space a learning algorithm runs in. The first is an explicit weight $w_F$, positive for every log-concave prior, equal to the second exactly for the value distributions $F(v)=v^a$. Otherwise the learners' certificate differs by knot masses, because the discretized equilibrium's slopes oscillate with a law proved for two and three bidders, and for four under a computer-verified bottom layer. The limit of the learners' certificate is proved in closed form, a function of the prior alone, and characterizes positivity: positive uniformly in $m$ in the limit exactly when that minimum is positive, with a known rate; for one prior at every $m$ by interval arithmetic. For more bidders the limit is conjectured. The exact identities and leading-order inequalities are machine-checked in Lean.

cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04543

CANDO: Conservative Action-Noise Directional Optimization for Residual Reinforcement Learning

Zeyu Gao, Chengkai Hou, Chaoyue Li, Zhuangzhe Wu, Jiaming Liu, Yao Mu, Peng Jia, Li Zhang 等 9 位作者

原文摘要

Pretrained generative policies provide strong behavior priors for robot control, but adapting them efficiently with online reinforcement learning remains difficult. A central challenge is how to improve a frozen generative policy without destroying the structure learned from offline demonstrations. Noise-space residual methods address this by modifying the policy's input noise, but existing noise-space methods typically regulate adaptation through fixed latent feasible regions, which may exclude valuable noise edits. In contrast, action-space residual methods are more sample-efficient, but their efficiency can still be further improved. We propose Conservative Noise Directional Optimization (CNDO), a noise-space residual RL method that improves a frozen generative policy by learning state- and noise-conditioned directions around Gaussian latent samples. CNDO removes predefined latent feasible regions and instead regulates noise-space adaptation through the soft conservative constraint, which consists of conservative value estimation and gated execution. We further introduce Conservative Action-Noise Directional Optimization (CANDO), which adds an action-space residual, combining structured latent-space improvement with local action correction. Experiments show that, once CNDO narrows the gap between noise-space and action-space residual learning, CANDO further improves over single-space optimization, achieving 76.1 NAUC and a 91.4% final success rate, surpassing the best single-space results by 6.6 NAUC and 4.1% success rate. More demos and info are available on https://cando-rl.github.io/.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.05818

What the Guard Misses, the Robot Executes: Implied Harm in VLA Instructions

Sripad Karne, Arjun Balaji

原文摘要

Vision-language-action models (VLAs) act on instructions without being able to refuse, so screening harmful requests falls to monitors. We test whether these monitors catch ordinary robot tasks requested for harmful reasons, holding the task fixed while varying only how explicitly the intent is stated. $π_{0.5}$ completes the task at every level of explicitness, as often as for harmless controls. Text guards flag nearly every blunt request but few implied ones: up to 95% of implied-harm runs end with the task done and no flag raised, and most still leak after recalibrating on robot instructions at low false-positive rates. Monitoring the model's activations does not close this gap. Linear probes separate harmful from harmless instructions almost perfectly in the base language and vision-language models, but this separation weakens after robot training in two model families, most for implied harm.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.37161HF 社区推荐

WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training

Ziyang Zeng, Tingyang Chen, Jia Deng, Qiyao Wang, Shuo Tang, Yike Yang, Tao Ren, Wayne Xin Zhao 等 13 位作者

原文摘要

Scaling supervised fine-tuning for working agents requires not only broad coverage of professional tasks, but also expert demonstrations that faithfully carry out professional workflows to completion. However, missing or inconsistent task information can disrupt expert demonstrations, weakening the resulting supervision. We introduce WorkFactory, a scalable task-construction framework that turns professional intents into executable task environments through hybrid intent sourcing, semantic workflow planning, and execution-based repair. Starting from these intents, WorkFactory constructs a Semantic Workflow Graph that explicitly represents information requirements, dependencies, and locations within the task environment. The graph guides the instantiation of task environments, while an adversarial execution-refinement loop exposes missing or inconsistent information and steers targeted repairs that preserve the original intent. Using WorkFactory, we construct 112,686 tasks spanning 612 occupations and train the WorkPilot family at 4B, 27B, and 35B-A3B scales on the resulting teacher trajectories. All three models improve over their respective base models across four professional-work benchmarks, with WorkPilot-35B-A3B rising from 879 to 1565 Elo on GDPval-AA v2.1. Scaling experiments with up to 110k tasks further show that larger models benefit more from additional task data but exhibit diminishing returns at smaller data scales, while WorkPilot's long-horizon execution evolves from verbose trajectories toward more efficient task completion. Controlled component studies quantify the negative effects of task-environment defects on downstream performance and show how semantic workflow planning and execution-based repair yield downstream gains through improved task-environment quality. The subset of data are available at https://github.com/IQuestLab/WorkFactory.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04537

BtsPruner: Role-Aware Visual Token Pruning for Large Vision-Language Models

Zihao Qi, Zhibo Zhang, Miaoxin Zhang, Jincheng Cai, Zengqiang Yan

原文摘要

Large Vision-Language Models (LVLMs) often process hundreds or thousands of visual tokens, resulting in substantial computational and memory overhead during inference. Existing training-free pruning methods typically estimate token importance using language-model attention, visual attention, or feature similarity. However, these methods treat visual tokens with uniform criteria and overlook that tokens may serve different roles during visual encoding. In this work, we investigate the evolution of visual token roles in LVLMs and observe that tokens progressively transition from local detail carriers to globally referenced representatives as encoding proceeds. Based on this observation, we propose BtsPruner, a training-free role-aware visual token pruning framework that preserves complementary token roles under a fixed budget. Specifically, BtsPruner first identifies the token-role transition point based on the evolution of attention concentration. It then discovers globally referenced representatives from later encoding stages and recursively retrieves local detail tokens from earlier stages to recover complementary fine-grained evidence. Extensive experiments across LLaVA-1.5, LLaVA-NeXT, Qwen-VL, InternVL, and CogVLM demonstrate that BtsPruner achieves superior performance retention under aggressive token reduction. On LLaVA-1.5-7B, BtsPruner preserves 91.6% of the dense model's performance using only 32 of 576 visual tokens (5.6%). In the high-resolution LLaVA-NeXT-7B setting, it achieves up to a 5.95x CUDA-latency speedup.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.19623

Near-Logarithmic Inapproximability of Parameterized Set Cover

Bingkai Lin, Xin Zheng

原文摘要

In the $γ$-gap $k$-SetCover problem, we are given a family $\mathcal{S}$ over a universe $U$, and the goal is to distinguish between the case where $\mathcal{S}$ contains $k$ sets covering $U$, and the case where at least $γk$ sets in $\mathcal{S}$ are needed to cover $U$. We show that, for every $k^{Ω(k^2)}\leρ\le n^{O(1)}$, it is W[1]-hard to approximate $k$-SetCover within ratio $Ω\big(\frac{\logρ}{k^2\log\logρ}\big)$ on instances with $n$ sets and universe size at most $ρ\log n$. We also show that under the randomized $k$-OV Hypothesis, there is no bounded-error randomized $f(k)n^{o(k)}$-time $o\big(\frac{\log N}{\log\log N}\big)$-approximation algorithm for $k$-SetCover. These results improve on the previous $(\log n)^{1/O(k)}$-inapproximability. For fixed $k$, this matches the polynomial-time $(\lnρ+O(1))$-approximation up to a $\log\logρ$ factor. We further establish a connection between small universes and large approximation gaps. We show that for every $1\leγ\le\min\big\{\frac{\log u}{\log\log N},\frac{\log u}{k^2\log\log u}\big\}$, exact $k$-SetCover with universe size $u^{Θ(1/γ)}$ is equivalent to $γ$-gap $k$-SetCover with universe size $u$ under randomized Turing reductions. This suggests a barrier to proving superconstant-gap W[2]-hardness: such a result would also make exact $k$-SetCover with universe size $n^{o(1)}$ W[2]-hard under randomized FPT Turing reductions. Finally, we analyze the VC dimensions of the set systems produced by our reduction. Write $d$ and $d^*$ for the primal and dual VC dimensions respectively. We show that for $γ=o(\frac{\log N}{\log\log N})$, $γ$-gap $k$-SetCover is W[1]-hard even when $d=O(k^{2}γ\log(kγ))$ and $d^*=O(kγ)$. The bound for $d^*$ matches the $O(d^*\log k)$-approximation algorithm up to a $k\log k$ factor.

cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04534

A Universal Raw-IQ Radar Encoder for Cross-Sensor Human Sensing

Jonas Leo Mueller, Dario Zanca, Sebastian Hoefler, Jan Petermann, Thomas Altstidl, Naga Venkata Sai Jitin Jami, Emmanuelle Salin, Bjoern M. Eskofier

原文摘要

Radar-based human sensing typically relies on end-to-end task-specific models trained on hand-chosen signal projections, which generalize poorly across unseen users, tasks, and hardware. We argue that the dominant signal processing choice, the micro-Doppler spectrogram, is a poor starting point for transfer because it keeps the Doppler axis, which carrier frequency rescales, and discards the angular axis, which carrier frequency leaves unchanged. We instead pretrain a convolutional beta-VAE without labels on clutter-removed raw radar measurements from four platforms spanning 60 and 77 GHz and 4 to 12 virtual antennas, aligned by a unified spectral interpolation grid. For every downstream benchmark the encoder stays frozen, and only a small supervised temporal classifier is trained on its embeddings. We compare against supervised models trained end to end on each benchmark and a pretrained radar foundation model across ten settings covering activity, gesture, sign-language, and gait recognition. When the test users and the radar are seen during training, our encoder is best on all five benchmarks. For users never seen in training, it leads on three of four benchmarks, by 4.8 to 23.2 points. On subject-disjoint gait recognition, it is best for each of the four held-out subjects and 8.3 points above the strongest baseline on average, even though its pretraining excluded every recording of this radar. Excluding the test radar from pretraining costs at most 5.3 points on any benchmark. Code is available at https://github.com/jonasmueler/UniversalRadarEncoder_WACV.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04532

The Price of List Replicability: Tight Bounds for Bias Estimation

Michael Chen, Atieh Bastan, A. Pavan, N. V. Vinodchandran

原文摘要

We study the sample complexity of list replicable algorithms for estimating the biases of $d$ coins. An algorithm is $(k,\varepsilon,δ)$-list replicable if for every bias vector $\mathbf{p}\in[0,1]^d$, there is a set of outputs $L_{\mathbf{p}}\subseteq \mathbb{R}^d$ of at most $k$ elements such that every $\mathbf{y}\in L_{\mathbf{p}}$ satisfies $\lVert\mathbf{y}-\mathbf{p}\rVert_\infty\leq\varepsilon$, and the algorithm output is in $L_{\mathbf{p}}$ with probability at least $1-δ$. Prior work gave a $(d+1,\varepsilon,δ)$-list replicable algorithm with sample complexity $\widetilde{O}\left(\frac{d^3}{\varepsilon^2}\right)$, but no nontrivial sample complexity lower bound was known. We establish the first non-trivial sample complexity lower bound for this problem and give an improved algorithm that matches it up to polylogarithmic factors. Together, these results determine the optimal sample complexity for list size $d+1$ to be $\widetildeΘ\left(\frac{d^2}{\varepsilon^2}\right)$, showing that the quadratic dependence on dimension is inherent up to polylogarithmic factors. More generally, for every $k\in[d+1,2^d]$, we establish matching upper and lower bounds of $\widetildeΘ\left(\frac{d^2}{\varepsilon^2\log k}\right)$ on the total sample complexity.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02671

TME-ContextNet: Class-Conditioned Spatial Supervision and Grouped Decoding for Joint Nuclei Instance Segmentation and Classification

Rukang Ma, Bingxue Wang, Liwen Zou, Yingying Cao, Zhenghua Cai, Yu Li, Dong Wang, Huiyu Zhou 等 9 位作者

原文摘要

Joint nuclei instance segmentation and classification requires precise boundaries and neighborhood information that helps distinguish morphologically similar cell types. We present TME-ContextNet, a multi-task framework that learns class-conditioned spatial context from existing nuclear annotations and organizes decoding into geometry-related and semantic task groups. Class-conditioned spatial supervision extends nuclear labels into a dense target using Euclidean distance transforms, requiring no additional tissue-region annotation. We derive its nearest-region interpretation and characterize its stability to small annotation perturbations. A local--global context module combines dilated convolution and self-attention, while a grouped task decoder reduces redundant computation. The spatial head supplies training supervision and is omitted during inference. Experiments on PanMix, CoNSeP, and PanNuke yield Dice scores of 80.23%, 65.32%, and 79.13%, and mean multi-class panoptic quality (mPQ+) scores of 58.67%, 35.50%, and 43.74%, respectively. PanNuke results are averaged across three test folds. Target and decoder controls support the combination of distance-based supervision and grouped decoding while identifying their dependence on task configuration. The framework uses 36.40 million parameters, compared with 54.74 million for HoVer-Net. These findings support a compact, context-aware formulation for joint nuclei analysis in computational pathology.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04529

Learning to Falsify: Hierarchical Multiple Instance Learning for High Resolution AI-Generated Image Detection

Haoran Chen, Daiqi Gao, Xinyuan Li, Yongwei Wang, Lei Zhu, Rui Cai, Jianfeng Dong

原文摘要

Recent advances in generative models have made synthetic images increasingly photorealistic, posing growing challenges to reliable and generalizable detection of AI-generated images. Existing methods typically rely on holistic image-level classification, which may overlook local artifacts, especially in high-resolution images. To address this limitation, we formulate this task as a falsification-driven multiple instance learning problem, where a single fake patch can falsify the whole image, while a real image requires all patches to be authentic. Based on this formulation, we propose \textit{Learning to Falsify (LTF)}, a hierarchical multiple instance learning framework that models an image as multiple bags of instances across different spatial levels and aggregates their predictions under the falsification-inspired principle. We further introduce Cross-Shuffle during training to encourage the model to learn local artifact evidence rather than image-level shortcuts. Furthermore, we propose the \textit{Falsification-driven Test-time Aggregation Strategy (FATAS)}, a plug-and-play module that extends the same falsification-inspired principle to existing detectors by aggregating patch-level predictions. Extensive experiments demonstrate that LTF achieves strong generalization and robustness across multiple benchmarks, while FATAS substantially improves representative detectors in high-resolution scenarios without retraining. Code is available at https://github.com/HuiGuanLab/LTF.git

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.05861

LLMCodec: Adapting Video Codecs for Efficient Weight Compression of Large Language Models

Rui Wang, Yan Zhao, Li Song, Zhengxue Cheng

原文摘要

The rapid development of large language models(LLMs) has led to remarkable advances in natural language processing. However, the increasing scale of these models introduces substantial challenges in terms of storage, transmission, and deployment. Though great efforts have been devoted to model compression and quantization, existing methods often rely on fine-tuning or calibration data, which exhibit limited generalization across different tensor types. In this paper, we argue that video codecs offer a promising solution for LLM compression, due to their inherent compatibility with matrix structured data, configurable compression strategies, and the availability of highly optimized, off-the-shelf implementations. Therefore, we present LLMCodec, a video codec-based LLM compression method that integrates affine quantization with the recent VVC/H.266 video codec. Beyond VVC, we further compare a range of video codecs and encoding profiles to evaluate their impact on compression performance. Experiments on different models demonstrate the robustness and generality of LLMCodec. Notably, on LLaMA-3-8B at 2-bit precision, LLMCodec reduces perplexity by over 1.5x and improves downstream task accuracy by 21% compared with the existing method.

cs.MM · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.00891

CacheBridge: Efficient Cross-Model KV Transfer for Multi-Model LLM Serving

Xingyu Qu, Siyuan Lu, Zhiyu Chen, Sheng Wang, Tao Lin

原文摘要

Multi-model LLM serving uses routers, cascades and agent workflows to move requests across models with different costs and capabilities. Existing serving systems reuse KV caches only within one model, so every switch forces the target to re-prefill history the source already processed, adding time to first token (TTFT) that grows with history length and target size. Cross-model KV transfer can replace this prefill, yet prior methods are slower than re-prefill end to end. We present CacheBridge, the first serving system to accelerate heterogeneous multi-model workloads through cross-model KV transfer. It co-designs a compact, attention-calibrated KV mapper with systematic optimization for online multi-model serving, which makes model switch efficient on latency and memory cost. In Qwen3 14B$\rightarrow$32B agent serving on $τ$-bench, it reduces mean TTFT by $30$ to $98\%$ versus re-prefill at $1$ to $24$ QPS with comparable task success. Across five model pairs from three families, it uses $8$ to $12\times$ less mapper memory than Closed-Form Mapper and retains on average $97.94\%$ and $102.94\%$ of re-prefill task quality on chat/reasoning and RAG workloads, respectively. The promising results have opened new opportunities for efficient multi-model LLM serving through cross-model KV reuse.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.23288

Spatio-Temporal Similarity Volume Aggregation for Open-Vocabulary Action Recognition

Yerim So, Jiyeong Kim, Jiwon Yoon, Dongbo Min

原文摘要

Recent Open-Vocabulary Action Recognition (OVAR) methods typically aggregate visual features into a global representation before computing text alignment, a process that obscures local patch information and fine-grained spatio-temporal cues. We propose Similarity Volume Aggregation (SimVA), a framework that constructs a dense 4D spatio-temporal similarity volume from patch-level visual-text similarities. SimVA constructs a spatio-temporal similarity volume over local video tokens and action classes, and employs class sampling to ensure similarity aggregation scalable to large vocabularies. The similarity volume is refined by spatial aggregation, which contextualizes local similarity patterns to improve intra-frame consistency. Motion-aware modulation further injects inter-frame variation cues, highlighting dynamically changing regions. Mamba-based temporal aggregation then models the evolution of class-conditioned similarity patterns across frames. By maintaining dense visual-text correspondence, SimVA effectively transfers CLIP to video action recognition, achieving competitive performance across zero-shot, few-shot, and base-to-novel benchmarks.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.09579

You Only Flow Once: Calibrated and Real-Time Radar Pose Estimation with Multi-Hypothesis Normalizing Flows

Jonas Leo Mueller, Sebastian Hoefler, Dario Zanca, Naga Venkata Sai Jitin Jami, Thomas Altstidl, Bjoern M. Eskofier

原文摘要

Sparse and noisy millimeter-wave radar point cloud observations often correspond to multiple plausible human poses, making deterministic pose estimation fundamentally ill-posed. Yet existing radar methods remain deterministic, collapsing this ambiguity into a single estimate. Diffusion-based alternatives can model multi-hypothesis distributions but require costly sequential denoising for each sample and lack calibrated uncertainty. We propose Multi-Hypothesis Normalizing Flow Pose Generator (MH-NFPG), which models pose distributions from radar point clouds using a conditional normalizing flow. Specifically, we combine a spatiotemporal transformer backbone with a normalizing flow that transforms a Laplace base distribution into an expressive posterior, generated in parallel through a single forward pass. Leveraging this efficiency, we outperform diffusion-based alternatives in calibration across three radar benchmarks (MM-Fi, mmRadPose, mRI) at comparable pose accuracy, while achieving up to 22x faster inference and reducing calibration error by up to 84%. We find that calibration degrades substantially for diffusion models, whereas our flow-based approach maintains reliable coverage, also across environments. These results demonstrate normalizing flows as a practical alternative to diffusion models for real-time, uncertainty-aware radar pose estimation. Our code is available at https://github.com/jonasmueler/YouOnlyFlowOnce_WACV.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04524

E2I-Flow: EEG-to-Image Reconstruction via Wavelet-Temporal Cross-Attention and Conditional Flow Matching

Haowei Pan, Hwa Hui Tew, Junn Yong Loo, Fuad Noman, Hernando Ombao, Chee-Ming Ting

原文摘要

Electroencephalography (EEG)-based visual decoding and reconstruction aims to recover visual information from non-invasive brain signals. But there are challenges due to the complex temporal-frequency characteristics of EEG signals and the difficulty of discrete denoising framework in mapping neural activity to meaningful visual representations. Here, we propose E2I-Flow, an EEG-to-image decoding and reconstruction framework that combines a novel EEG encoder for time-frequency representation learning from EEG features, and conditional flow matching for visual decoding. A stationary-wavelet frequency branch and a temporal-mixing branch are integrated through bidirectional cross-attention and adaptive fusion, with the resulting EEG representations aligned to ground-truth image embeddings using contrastive and mean-squared-error loss supervisions. The aligned EEG representation is then used as a condition for a Transformer-based flow-matching model to predict the corresponding visual embedding for image synthesis. Experimental results show strong zero-shot EEG-to-image retrieval and improved visual reconstruction performance, outperforming several state-of-the-art baselines.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.01940

ReWY: Faster Backpropagation for Delta-Rule Attention - From 7 to 3 Matrix Multiplications

Yi Zhang, Zhixin Zhao, Weiwei Sun, Yitao Hu, Sheng Chen, Keqiu Li

原文摘要

Delta-rule linear attention underlies language models such as Kimi Linear and Qwen3-Next. Chunkwise implementations expose matrix parallelism, but their backward passes compute unnecessary auxiliary adjoints. We present ReWY, an algebraic reformulation that reduces this work before optimizing accelerator execution. Differentiating the chunk correction as one triangular residual system eliminates the inverse adjoint and reduces seven local WY matrix products to three. Two complementary transformations expose further reuse: centered matrix contractions replace pairwise vector-gate processing, and scalar-gate reductions reuse key-gradient products instead of forming a key Gram matrix. These identities simplify backward computation for DeltaNet, GDN, KDA, and GDN2 while preserving the recurrence and gradients in exact arithmetic, without changing the architecture or training objective. We implement the reduced graph on GPUs and Ascend NPUs. Under matched recomputation and full-saving policies, precision-qualified six-shape comparisons with frozen FLA references yield 1.15-1.81$\times$ geometric-mean complete low-level backward speedups on NVIDIA GPUs. All four operators achieve 1.18-1.70$\times$ on H100 and H200 while retaining original FP32 working matrices. A separate public-autograd evaluation on Ascend 950DT, including gradient conversions, yields 1.09-2.89$\times$ under available matched policies. Paired ablations establish further ReWY gains after optimizing the complementary contractions. Complete-gradient checks validate the recorded operator cases; supplementary full-model backward measurements assess integration into community FLA models and a GDN2 layer port. Code and reproduction materials: https://github.com/flashserve/ReWY.

cs.LG · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.27114

Quadratic Complexity of Voronoi Diagrams in $\mathbb{R}^3$ for Lines in a Single Ruling of a Regulus

Eunku Park, Kangjin Han

原文摘要

We study nearest and farthest Voronoi diagrams of lines in three-dimensional Euclidean space, which partition space according to the closest and farthest input lines, respectively. For arbitrary lines, a gap remains between the known quadratic lower bound and near-cubic upper bounds for the complexity of the nearest diagram. We consider input lines chosen from one of two continuous families of straight lines on a smooth surface defined by a quadratic equation, with one line from each family passing through every point of the surface. Under the geometric assumptions stated in the paper, we prove quadratic upper bounds on the total number of vertices, edges, faces, and connected three-dimensional regions in both diagrams. We also construct quadratically many nearest vertices using lines from a single family on one fixed surface, establishing a tight quadratic worst-case bound. The farthest diagram has quadratic total complexity for every input satisfying our assumptions. Our proof uses a parametrization that arranges the input lines in a cyclic order and expresses tangency to a sphere by a polynomial equation of degree four. At a Voronoi vertex, the four tangent input lines give four distinct roots. The sign changes between these roots, together with the nearest or farthest condition, force two intervening parameter intervals to contain no other input parameters. Thus, only quadratically many choices of four lines can define a vertex, and each choice yields at most eight isolated candidate centers.

cs.CG · math.AG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04522

Action Intent as a Bridge: Transferring Manipulation Knowledge from Human-Centric Videos to Robots

Zhiqian Xia, Lianyang Ma, Haifeng Xia, Siyu Xia, Wei Wang, Xiaochun Cao

原文摘要

Vision-Language-Action (VLA) models have achieved promising performance for generalized robotic manipulation, yet their reliance on expensive real-robot data remains a fundamental bottleneck. A scalable alternative is to transfer knowledge from off-the-shelf human-centric videos. However, existing methods extract latent action representations that are entangled with scene-specific noise, diluting the transferred knowledge. Motivated by this limitation, we propose Action-Intent Transfer (AIT), a two-stage method that transfers knowledge through a clean action representation shared across humans and robots. In the first stage, AIT extracts explicit action intents and disentangles the implicit action intent from manipulation videos. In the second stage, AIT aligns the human and robot domains within this shared intent space and decodes the intent into executable robot actions. Extensive experiments in both simulation and real-world environments demonstrate that AIT transfers human knowledge more effectively and consistently outperforms prior baselines.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2508.12969

Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation

Qirui Li, Guangcong Zheng, Qi Zhao, Jie Li, Bin Dong, Yiwu Yao, Xuewei Li, Zequn Qin 等 9 位作者

原文摘要

The quadratic computational complexity of self-attention mechanisms imposes a critical constraint on transformer-based video generation, particularly for synthesizing ultra-long and high-definition sequences. While most sparse attention techniques employ fixed or heuristic patterns, they often struggle to accommodate the heterogeneous and layer-specific redundancies inherent in video diffusion transformers (VDiTs). We find that different attention heads consistently concentrate most of their attention mass in different coarse query-key regions, a behavior we call functional specialization. Although individual attention values vary with the generated content, these regions remain similar across prompts and random seeds. Leveraging these insights, we introduce Compact Attention, a hardware-aware sparse attention framework for efficient long-video synthesis. We quantify this stability and use it to construct searchable, reusable, head-specific masks. Based on the observation, we propose a deformable dual-window sparse pattern mechanism that flexibly approximates local and axial attention regions within one tile-aligned mask family. To avoid manually choosing a mask for each head, we develop a recall-driven offline auto-search algorithm that identifies high-quality sparse masks while leveraging temporal stability for mask reuse. Extensive evaluations on Wan2.1 (14B) and Hunyuan-Video demonstrate that Compact Attention achieves 2.25x/3.03x attention speedups over FlashAttention-2 and 1.20x/1.74x over FlashAttention-3, respectively, while maintaining visual quality and temporal consistency comparable to full-attention baselines. Project Page: https://yo-ava.github.io/Compact-Attention.github.io/

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04521

Estimating the generator of matrix exponential time-series

Jonáš Fuksa, Jens Eisert, Ingo Roth

原文摘要

The achievable precision in estimating the spectrum of a time-series signal that is promised to be sparse in Fourier space deteriorates rapidly as the spectral peaks get closer together, as soon as we introduce noise. Here, we study the related task of generator estimation: estimating the generator of a matrix exponential time-series and its eigenvalues. We obtain rigorous non-asymptotic precision guarantees on genESPRIT, a practical algorithm solving generator estimation, and show that this task can be solved with precision independent of the spectral spacing. The guarantees are complemented by a Cramér--Rao analysis of a relaxation of the problem. In particular, in the case of unitary data with bounded additive noise with effective entrywise variance $σ^2$, we show that genESPRIT estimates the associated propagator matrix in Frobenius norm with precision scaling as $\tilde{\mathcal{O}}(σNL^{-\frac12})$ in the length of the time-series $L$ and matrix dimension $N$, matching the corresponding spectrum-independent Cramér--Rao standard deviation scaling up to logarithmic factors. We prove that the matching distance error in the spectrum estimated by genESPRIT scales as $\tilde{\mathcal{O}} (σ^2 N^3 L^{-1} + σN^{\frac32} L^{-\frac32} )$, which we compare to the lower bound on the corresponding Cramér--Rao bound with the asymptotic standard deviation scaling $\mathcal{O}(σL^{-\frac32})$. These guarantees provide the first rigorous bounds on solving the generator estimation problem. As the matrix exponential time-series can be obtained from linearly independent vector time-series by concatenation, this work opens up a new direction in spectral estimation, which circumvents the problem of crowded spectra, under the additional assumption of linear independence.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.14542

A Deep State-Space Model Compression Method using Upper Bound on Output Error

Hiroki Sakamoto, Kazuhiro Sato

原文摘要

We study deep state-space models (Deep SSMs) that contain linear quadratic-output (LQO) systems as internal blocks and present a compression method with a provable output error guarantee. We first derive an upper bound on the output error between two Deep SSMs and show that the bound can be expressed in terms of the $h^2$-error norms between the layerwise LQO systems. In particular, we show that reducing the $h^2$ approximation errors of the LQO systems placed in shallow layers is effective in reducing the derived upper bound on the output error. Next, we formulate an optimization problem for the derived upper bound and develop a gradient-based MOR method. In the numerical experiments, using the IMDb task from the LRA benchmark, we demonstrate the effectiveness of the proposed upper-bound-based compression method. In particular, we show that the number of trainable parameters can be reduced by approximately 60\% without retraining while maintaining the performance of the original model.

eess.SY · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04519

Order-Dependent Complexity of Enumeration and Direct Access for Conjunctive Queries on Dynamic Data

Antoine Amarilli, Nofar Carmeli, Clémence Dumoulin

原文摘要

This note studies the fine-grained complexity of ranked enumeration and ranked direct access of conjunctive query answers over a dynamic database. We focus on lexicographically sorted answers, defined by an ordering on the query's free variables. From the literature, when no particular order is required, we know that when the query is self-join-free and q-hierarchical, we can build a data structure for enumeration (resp. direct access) with linear (resp. linearithmic) preprocessing and constant (resp. logarithmic) update time in the size of the database. For enumeration (resp. direct access), this data structure yields an algorithm that enumerates all query answers (resp. that returns the $k$-th query answer) with constant delay (resp. logarithmic access time). Our goal is to extend these results to ranked enumeration and ranked direct access, with the ranking function defined by a lexicographic order. We define a property on the order over the variables of $Q$, which we call being hierarchy-consistent. Given a user-specified query and hierarchy-consistent order, we first propose, for ranked enumeration under updates, an algorithm with linear preprocessing and logarithmic update time that enumerates all the query answers according to the user-specified order with constant delay. Moreover, for ranked direct access under updates, we propose an algorithm with linear preprocessing and logarithmic update time that returns the $k$-th tuple according to the user-specified order with logarithmic access time. In contrast, given a user-specified query and non-hierarchy-consistent order, we show a lower bound for ranked direct access under updates.

cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04518

LLM-Assisted Planning with Distributed Onboard Behaviour Tree Execution for Multi-AUV Missions

Ehsan Khorrambakht, Cristiano Caissutti, Andrea Munafo, Andrea Caiti

原文摘要

Coordinating autonomous underwater vehicles requires translating operator intent into feasible assignments while preserving autonomous execution when communication is limited. We present a hierarchical framework that couples Large Language Model (LLM) interpretation of natural-language mission instructions with Mixed-Integer Linear Programming (MILP) and distributed Behaviour Tree (BT) execution. The LLM extracts assignment and ordering constraints, which the MILP optimizer combines with vehicle capabilities and temporal requirements. A BT-LLM Bridge distributes the resulting allocations to onboard BT Mission Managers. Per-vehicle Robotic Agents assess local faults and request selective replanning, allowing unaffected vehicles to continue their assigned tasks. Evaluation in a ROS-based AUV simulator compares Qwen-3-8B and Llama-3.1-8B on constraint extraction and tests recovery from sensor degradation and critical vehicle faults. Qwen-3-8B provides more accurate constraint extraction, and all tasks are completed in the tested failure scenarios. These simulation results support the feasibility of combining language-based mission specification with structured allocation and distributed execution.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04515

Learnings and Pitfalls from AI-Assisted A/B Experimentation at Scale

Brett Daley, Ilya Gorbachev, Anubhav Natani, Nicholas Brown, Athena Dai, Rachel Song, Marcin Pekalski, Josip Domazet 等 10 位作者

原文摘要

A/B testing underpins product decisions by providing trustworthy, reproducible quantification of proposed changes' effects. Growing large language model (LLM) capabilities have motivated efforts to automate experimentation workflows. Yet LLMs are nondeterministic and prone to hallucination, properties that conflict with the trust experimentation systems must provide. Experiments are also operationally messy: diagnosing anomalies, debugging configurations, and conducting bespoke follow-up analyses require flexible reasoning and manual effort. These tasks let agents accelerate experimentation without replacing its deterministic statistical foundations. We report lessons from building and operating such an agent. Our central finding is that this tension is resolved not by making the model deterministic, but by bounding where its nondeterminism can reach; the model selects and sequences procedures, while deterministic code computes every quantity it reports. Three consequences surprised us: withholding information from the model improved its answers, demand concentrated on mundane retrieval rather than the autonomous decisions we anticipated, and the agent's eagerness to help threatened statistical validity.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.26337

CIS-Transolver: A Cross-layer Incremental-State Neural Operator for Fine-Scale Automotive Aerodynamic Flow Prediction

Jianglong Liu, Zhicheng Zhu, Jia Hao, Liangyue Jia, Wenxuan He

原文摘要

Neural operators offer an efficient data-driven approach to predicting complex automotive aerodynamic flows. However, spectral bias limits their ability to reconstruct fine-scale flow variations around geometric features such as side mirrors and wheel arches. Reliable assessment of local geometric changes therefore requires models that capture fine spatial detail together with global flow interactions. Inspired by iterative refinement and state evolution, we propose CIS-Transolver, a cross-layer incremental-state neural operator that integrates local multiscale information into global flow modeling. The method extracts local feature variations and encodes them as zeroth- to second-order geometric moments. These encodings are combined with information from earlier layers to form a cross-layer memory. Memory-derived corrections enter the value branch of Physics-Attention, allowing local details to inform global physical-state interactions throughout the network. We systematically evaluate CIS-Transolver on three public automotive aerodynamics benchmarks, ShapeNet-Car, AhmedML, and DrivAerNet++, covering surface pressure fields and volumetric pressure and velocity fields. CIS-Transolver achieves the lowest mean relative L2 error among the evaluated methods for all five prediction metrics across the three benchmarks. Relative error reductions average 8.72% compared with the best baseline for each metric. Also achieves the lowest high-frequency spectral errors across all five metrics, with an average relative reduction of 16.06% compared with the best baseline. These results support cross-layer reuse of local information for fine-scale automotive flow prediction.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗