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

+1085新增论文
+884其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 07:37 — 2026-11-19 07:37(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:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59库内论文最新更新时间:2026-11-18 08:00

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。

26,871 已收录论文22,375 AI 相关8,156 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 101 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v2arXiv:2609.34335

SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Enhancement

Yanwei Huang, Mingxuan Zhu, Shujie Li, Shiyuan Liu, Yuanxing Zhang, Arpit Narechania

原文摘要

Achieving high-quality cinematic text-to-video generation remains challenging for non-experts, whose prompts often lack professional narrative and creative design. Existing prompt enhancement (PE) methods and static cinematic skills offer limited capabilities for exploring diverse creative realizations. We propose SkillPE, a creativity-oriented PE framework that systematically evolves reusable cinematic skills through reference-guided exploration. Starting from expert-provided cinematic knowledge, SkillPE initializes and normalizes 20 structured seed skills. It then retrieves movie references categorized as resonators (good matches), dissonants (weak matches), and divergents (creatively inspiring near-misses). Resonators and dissonants refine skill applicability and execution, while divergents inspire alternative cinematic realizations through controlled mutations that preserve user intent. Candidate skills are assessed through generated videos along prompt fidelity, cinematic quality, narrative appeal, and creativity to construct the final skill libraries. Experiments on StoryEval and VBench demonstrate improvements of up to 1.10 points over seed skills and 1.02 points over the strongest external baseline on a 7-point four-dimensional evaluation scale. Overall, SkillPE offers a practical approach to balancing fidelity and creativity in cinematic text-to-video generation.

cs.CV · cs.AI

新论文 · v1arXiv:2611.22330

Multistage Contextual Optimization for Vehicle Repositioning

Jinyu Zhang, Di Huang, Zhiyuan Liu, Nikolas Geroliminis

原文摘要

Ride-hailing platforms reposition idle vehicles to improve spatial supply-demand balances. This problem is prediction-driven and multistage: at each stage, the platform forecasts future demand, executes current decisions, and uses the resulting state to initialize the next stage. We formulate a multistage linear program (LP) with a macroscopic fundamental diagram (MFD) linking accumulation to trip completion. We then develop a multistage contextual optimization approach that uses decision performance to train the prediction model. The learning problem combines multiple coupled stages, context that depends on earlier decisions, and predictions that affect the objective, the constraint matrix, and the right-hand side of the LP. We derive the exact gradient, which has three parts: parameters change forecasts and hence decisions; earlier decisions change the current decision through the inherited state; and this state also changes forecasts as context. An equivalent adjoint uses reverse vector-Jacobian products, avoiding full solution and state-parameter Jacobians. Finally, forward propagation solves many stage LPs one after another, which makes training slow. We propose a parallel block evaluation algorithm that solves blocks of consecutive stages in parallel and repeatedly feeds each block output to the next block. We prove that the algorithm recovers the serial trajectory within a finite number of passes and that its gradient error remains bounded when it stops early. On New York City ride-hailing data, multistage contextual optimization yields 7.7% to 9.1% more business benefit than the same predictor trained by mean squared error, outperforms all compared baselines from five paradigms, and even outperforms realized demand fed to the same policy. With eight workers, parallel block evaluation shortens training by a factor of 1.86 without loss of decision performance.

cs.AI · cs.LG

新论文 · v1arXiv:2611.22215

Communicate the Change: Efficient Expert Parallelism via Activation Compression

Fengyuan Liu, Jay Gala, Siva Reddy, Dzmitry Bahdanau

原文摘要

Scaling has driven the success of large language models (LLM), with sparse mixture-of-experts (MoE) architectures enabling greater parameter capacity without a proportional increase in computation. At large scales, MoE models rely on expert parallelism to distribute experts across devices. Each MoE layer requires two synchronous collective communication steps during inference: dispatching hidden states to the activated experts and combining the resulting expert outputs. As compute throughput has outpaced interconnect bandwidth, these synchronous collectives have become a major bottleneck to MoE scaling and efficiency. We address this challenge with EchoMoE, a lightweight architecture modification that retrofits existing MoE models, requiring approximately 8,500x fewer training tokens than full pretraining. Motivated by the observation that transformer blocks update the residual stream incrementally, we use a hidden state from an earlier layer as a reference and communicate only the compressed difference between it and the current state, rather than communicating each hidden state in full. EchoMoE periodically refreshes these reference states and transmits only the compressed differences synchronously, reducing the traffic on latency-critical paths without significant computational overhead. EchoMoE reduces inter-node communication volume by 58% and improves throughput by 22.6%, while preserving average performance within 3.8 percentage points across 18 benchmarks. EchoMoE further improves inference throughput by up to 2.38x over bandwidth-constrained Ethernet, paving the way for wide-area distributed inference. EchoMoE also tolerates quantization of the communicated representations without measurable quality loss. We release an efficient implementation for applying EchoMoE to pretrained MoE models, together with an inference integration for vLLM.

cs.LG · cs.AI · cs.DC

版本更新 · v2arXiv:2610.40749

Combinatorial Residual Network: a decay-chain-aware classifier without explicit jet assignment

John Alison, Patrick Bryant, Alejandro Gomez Espinosa, Christian Guinto-Brody, Aniket Khanal, Chuyuan Liu, Sindhu Murthy, Guanglei Zhao

原文摘要

Final states with several jets from the decays of heavy particles pose a combinatorial problem: the jets must be assigned, at least implicitly, to their parent particles. The Combinatorial Residual Network (CoReNet) is a classifier that encodes the assumed decay chain in its architecture, building the event representation level by level along the decay hierarchy and combining all jet assignment hypotheses, evaluated with shared weights, with learned weights. The exchange symmetries of the decay are built in, the network size does not depend on the number of hypotheses, and no generator-level jet assignments are used in training. Developed for the $b\bar{b}b\bar{b}$ final state and used in several CMS searches, CoReNet with 1508 parameters performs well above kinematic baselines on fast-simulated Higgs boson pair production against QCD multijet events and trains in minutes on a single GPU, and its hypothesis weights select the truth-matched jet pairing in most signal events in which it is defined. Since only the encoded decay chain is specific to the final state, we test the construction on $HH \to b\bar{b}W^+W^-$ against semileptonic $t\bar{t}$, where encoding the decay chain of the background as well improves the classification at a cost of about $10^{3}$ parameters. In both final states, CoReNet performs comparably to a state-of-the-art transformer-based network more than two orders of magnitude larger. The implementation is publicly available at https://github.com/cms-cmu/CoReNet.

hep-ex · cs.LG · hep-ph · physics.data-an

新论文 · v1arXiv:2611.21339

MovieRoll: A Systematic Framework for Rolling Out Long-Form Videos

Yunyang Ge, Weijie Kong, Ryan Xu, Yue Wu, Qi Tian, Jiangfeng Xiong, Bin Lin, Mingzhe Zheng 等 12 位作者

原文摘要

Streaming video generation must sustain quality beyond the training horizon while handling self-generated history and growing cache costs. To address these challenges, we present MovieRoll, a base-to-distilled framework that connects streaming fine-tuning, long-rollout distillation, and long-horizon inference. We first establish a robust multi-step base through Window-wise Teacher Forcing (WinTF), which jointly denoises chunks at progressive noise levels with bidirectional attention within each window and causal access to preceding history. To retain historical context efficiently, hierarchical KV-cache compression (HieraKV) exploits layer-wise attention patterns, retaining full history in shallow layers and sink--recent history in deeper layers. This reduces cache memory by up to 78% while improving generation quality. Building on this base, cumulative long tuning with distribution matching distillation (CuLT-DMD) holds parameters fixed throughout each long self-rollout and averages local gradients before updating. Each update therefore combines supervision across temporal positions while retaining only one local computation graph, enabling efficient long-rollout training of a few-step generator. To extend generation beyond the training horizon, KV recomputation bounds context for both models, while guidance annealing (AnnealCFG) reduces guidance toward the clean endpoint to stabilize MovieRoll-Base. Complementing these modeling advances, FBCA attention and PS-VAE decoding support efficient training and streaming output. On HeliosBench, MovieRoll-Base remains competitive at 30s after training on videos of up to 15s, and MovieRoll-Distilled achieves the highest total scores among the compared methods across single- and multi-event evaluations up to 60s, combining sustained naturalness with active motion.

cs.CV

版本更新 · v2arXiv:2611.16269

FlowIR: Depth-driven Rectified Flow for Resolving Thermal Ambiguity in Infrared Super-Resolution

Xingyue Zhu, Qinyun Mei, Zhexi Min, Yang Zou, Xingyuan Li, Zhiying Jiang, Jinyuan Liu

原文摘要

Distinguishing different heat sources in low-resolution infrared (IR) images is inherently difficult, as multiple thermal emitters often collapse into ambiguous and overlapping responses. Existing super-resolution methods hallucinate structures from such ambiguous 2D evidence, leading to thermal drift, boundary merging, and unreliable restoration under infrared degradations. We propose FlowIR, a depth-driven rectified flow framework that resolves thermal ambiguity by injecting 3D geometric cues into the generation process. Pseudo-3D depth lifting and depth-guided 3D convolutions disentangle overlapping foreground objects, while cluster-wise inter-attention suppresses cross-source feature contamination. A Thermal-Geometry Consistency Loss further enforces geometric alignment during refinement. Built upon a lightweight rectified flow backbone, FlowIR restores IR images in only a few steps, producing sharply separated, degradation-robust, and geometrically faithful high-resolution results.

cs.CV

新论文 · v1arXiv:2611.19959

Sparse Rotatable Arrays (SRAs) for Cell-Free MIMO: Network-Wide Design of Antenna Activation and Panel Orientation

Ailing Zheng, Qingqing Wu, Xiyuan Liu, Wei Feng, Wen Chen, Guoying Zhang

原文摘要

This paper investigates a sparse rotatable array (SRA)-enabled cell-free multiuser multiple-input multiple-output (MIMO) system. Under a network-wide antenna activation budget, distributed access points (APs) select active antenna elements from their installed arrays and adjust panel orientations, enabling joint control of sparse array apertures and antenna directivity. To avoid frequent hardware reconfiguration in response to instantaneous channel variations, we formulate a two-timescale stochastic optimization problem to maximize the expected minimum-user rate. Long-term antenna activation and panel orientations are optimized based on user spatial distributions and statistical channel state information (CSI), while short-term precoders adapt to instantaneous CSI. Under line-of-sight (LoS) propagation, we derive the optimal single-user antenna allocation, characterize the two-user max-min signal-to-interference-plus-noise ratio (SINR) and establish conditions for discrete activation and panel rotation to attain the continuous-position benchmark, and obtain a closed-form multi-AP zero-forcing (ZF) allocation benchmark under a continuous antenna-count relaxation. For the general mixed-integer nonconvex stochastic problem, we develop an alternating algorithm based on sample-average approximation (SAA), integrating uplink-downlink (UL-DL) duality for short-term precoding, weighted minimum mean-square error (WMMSE) surrogates for panel-orientation optimization, and multi-start greedy search for antenna activation. Numerical results demonstrate that the proposed design outperforms the fixed-array benchmark, improves all-user service reliability with fewer active antennas, and adapts effectively to nonuniform user spatial distributions.

cs.IT

版本更新 · v3arXiv:2604.07338

Appear2Meaning: A Cross-Cultural Benchmark for Structured Cultural Metadata Inference from Images

Yuechen Jiang, Enze Zhang, Mohsinul Kabir, Chenying Lin, Ying Peng, Fengyuan Liu, Qianqian Xie, Stavroula Golfomitsou 等 10 位作者

原文摘要

Museum records express how people understand heritage objects through cultural and historical relations. Recovering these human attributions from images is a technical challenge for vision-language models (VLMs). We introduce Appear2Meaning, a cross-cultural benchmark of 750 museum objects for image-only recovery of title, culture, period, origin, and creator. Its evaluation framework distinguishes field-level from complete-record compatibility and uses human validation for semantic judgement. Across nine VLMs, mean field accuracy is 36.16--49.82%; 7.20--17.02% of records have all four contextual fields compatible, and 2.13--7.87% have all five, including title. For the two tested models, image-only input yields 12.6--32.2 percentage points higher reference compatibility for culture, period, and origin than a museum-and-title-only control.

cs.CV · cs.CL · cs.MM

版本更新 · v2arXiv:2611.16265

Rectified Looped Transformer

Musheng Li, Jiawei Zhang, Ziyuan Liu, Yuantao Gu

原文摘要

Looped Transformers increase effective depth by repeatedly applying a shared block, offering a parameter-efficient approach to language modeling. However, most existing works directly reuse each loop's output as the next's input, which can lead to hidden-state scale growth and perturbation amplification as recurrence deepens. We propose Rectified Looped Transformer (RLT), which redesigns feedback between loops using an interpolation schedule inspired by flow-based modeling. At each loop, RLT forms the next input by linearly interpolating between the current state and its prediction. Such interpolation distributes state changes across loops, encouraging a smoother trajectory from the initial input to the final output. Theoretical analysis proves that, under appropriate assumptions, RLT keeps state magnitudes uniformly bounded across loops and reduces the worst-case perturbation amplification. We evaluate RLT on language modeling corpora and downstream benchmarks. At matched training and inference depths, RLT consistently achieves lower perplexity than a standard looped Transformer, while exhibiting greater robustness to input perturbations and variance in inference depth. Consistent with the theoretical results, latent trajectory analysis shows that RLT maintains more stable hidden-state norms across loops, which also facilitates extrapolation-based decoding strategies. Notably, RLT achieves these gains without requiring additional trainable parameters or extra recurrent block evaluations, thus providing a simple yet more stable feedback mechanism for looped Transformers.

cs.LG · cs.AI

新论文 · v1arXiv:2611.17955

WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents

Imene Kerboua, Fatemeh Pesaran Zadeh, Xing Han Lù, Weijian Qi, Alexander Miller, Junyi Song, Yunjia Tian, Dongjin Kang 等 22 位作者

原文摘要

Web agents powered by large language and vision-language models are increasingly applied to realistic browser work that spans heterogeneous applications, multimodal content, and stateful workflows. However, existing reproducible web-agent benchmarks cover only a small number of web applications drawn from a few software categories, and restrict modality to text and vision. Live benchmarks broaden site coverage but sacrifice reproducibility, since pages and data drift between runs. Moreover, existing benchmarks do not meaningfully evaluate whether agents can understand and use audio and video content embedded within web tasks. To address these gaps, we introduce WebArena-Pro, a benchmark comprising 300 tasks across 20 self-hosted web applications in six domain categories, spanning distinct interface conventions, workflows, and data models. Across the evaluated agents, the best performance is achieved by both Codex with GPT 6.1 Sol and Claude Code with Claude Opus 5.5 at 62.3%, followed by OpenCode with Kimi 3.1 Pro at 60.7%. The strongest GenericAgent configurations, Gemini 3.1 Pro omni and Gemma4 31B, both achieve 30.3%. Among reproducible, human-curated web agent benchmarks, WebArena-Pro provides the broadest application coverage and the most comprehensive multimodal support to date. The benchmark treats audio and video as core observations alongside text and vision, with dedicated actions for extracting information from each. WebArena-Pro runs each task in isolation and supports reproducible, parallel evaluation. Tasks are authored through a dedicated annotator interface, filtered by LLM-assisted triage, and finally validated by humans before release. Project page: https://webarena-pro.github.io

cs.AI · cs.CL · cs.LG

新论文 · v1arXiv:2611.17720

Ego2Flow: Benchmarking the Traffic-System Impact of Autonomous Driving on Maps Distilled from Real-World Roads

Yu Dong, Weiying Shen, Hangyu Li, Shu Han, Hong Li, Xiangbo Gao, Keshu Wu, Zhengzhong Tu 等 11 位作者

原文摘要

End-to-end autonomous driving is predominantly evaluated through ego-vehicle safety and task completion. Its deployment in urban traffic, however, creates sustained interactions among vehicles whose collective effects remain insufficiently evaluated. We introduce Ego2Flow, a closed-loop benchmark for assessing the traffic-system impact of autonomous driving on maps distilled from real-world cities. To construct realistic 3D urban environments for sustained closed-loop traffic simulation, we develop an agent-guided map distillation framework that integrates real-world maps and observations with complementary geographic information. Through an iterative feedback mechanism and a traffic information graph that jointly guide scene generation, the framework preserves lane topology, critical road geometry and decision-relevant visual conditions while simplifying nonessential details and completing unobserved regions. Using our proposed framework, we generate and publicly release six CARLA maps from the Argoverse 2 dataset, covering the corresponding real-world regions and enabling paired comparisons of driving behavior under real and simulated observations. On these maps, Ego2Flow evaluates how autonomous driving policies affect traffic efficiency, safety, stability and energy consumption across diverse road structures. Compared with existing construction methods, our framework achieves the lowest average displacement error between planning outputs from paired real and simulated observations. We further benchmark representative driving policies to characterize their system-level impact on urban traffic. Project Page: https://github.com/Fisher-007/Ego2Flow.

cs.RO · cs.CV

新论文 · v1arXiv:2611.16872

ACE-CaP-0:经验时代的真实世界代码即策略

ACE-CaP-0: Real-World Code-as-Policies in the Era of Experience

ACE-CaP Team, Changxu Wei, Yunpeng Qing, Guozheng Ma, Bowen Liu, Zexin He, Yilun Kong, Haoming Gu 等 28 位作者

AI 速读 基于摘要

作者提出 ACE-CaP-0 智能体配方,通过“按需演示”与“按需仿真”结合策略修订与经验获取,在八项真实机器人操作任务上以冻结程序实现 92.1% 成功率。

cs.RO

查看原文摘要

Recent advances in frontier models have pushed the boundaries of agentic robot control, enabling agents to perform complex robotic tasks through reasoning and interaction. However, repeated calls to these models during execution can substantially increase task completion time. Code as Policies (CaP) offers a route for coding agents to acquire physical skills through experience and retain them in executable programs, allowing the reasoning invested in development to be reused across runs. Developing reliable code policies while limiting the cost of physical experimentation remains a central challenge. We investigate human guidance as a source of priors for feasible actions and simulation as an auxiliary environment for exploring and testing candidate policies. Our findings favor robot demonstrations available on request and simulation used selectively during real-world policy refinement. These findings inform ACE-CaP-0, an agentic recipe that couples policy revision with experience acquisition through Demonstrations on Request and Simulation on Demand. Across eight real-world manipulation tasks spanning alignment, multi-object handling, and bimanual coordination, the resulting frozen programs achieve 92.1\% success (221/240 trials). Mean execution times across tasks range from 0.97 to 2.27 minutes. The programs execute with runtime perception and control, without a human or coding agent in the loop. These results highlight CaP's potential to turn experience into reliable, reusable physical skills.

版本更新 · v2arXiv:2609.04726

Bridging Modalities and Tasks: A Unified Hierarchical ViT for SAR-to-Optical Translation and Semantic Segmentation

Siyuan Liu, Xuze Zhang, Yongshun Wang, Licong Pan, Hang Liu, Huihui Li

原文摘要

Synthetic Aperture Radar (SAR) remains available through cloud and darkness, yet speckle and non-intuitive scattering make it hard to inspect and interpret. SAR-to-optical (S2O) translation renders radar observations as optical-like images for visual access, while semantic segmentation on SAR remains necessary since land-cover decisions cannot rely on synthesised pixels. We propose BMT, a hierarchical Vision Transformer coupling both tasks on a shared encoder via multi-scale one-hot conditioning, a gated LocalViTBlock, a colour-calibrating generation head, ControlNet-style zero-initialized injection, and uncertainty-based task weighting. The joint framework's value is not label-free training: it uses paired optical images and the same pixel annotations as a dedicated SAR segmentor, supervising the SAR decoder and teacher-forcing the generator with ground-truth one-hot maps. At test time, the model takes only SAR and returns an optical-like readout and a radar-decided land-cover map, with the translation objective supplying dense appearance supervision that speckle lacks. On WHU-OPT-SAR, the predicted-condition model achieves the best SSIM and PSNR among compared translators; its land-cover map surpasses the same backbone trained for labelling alone and is within about one point of DeepLabV3+.

cs.CV

版本更新 · v3arXiv:2605.10664

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions

Diancheng Kang, Zheyuan Liu, Ningshan Ma, Yue Huang, Zhaoxuan Tan, Meng Jiang

原文摘要

Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful dialogue. We identify KV-cache contamination as a key failure mode: steered token states are stored and repeatedly reused, turning a local perturbation into cumulative coherence degradation. To address this challenge, we propose Gated Cropped Attention-Delta steering (GCAD), which extracts steering signals from system-prompt contributions to self-attention and applies them with token-level gating. Across persona-steering experiments, GCAD preserves trait control while substantially improving long-horizon coherence. On the main multi-turn benchmark, GCAD improves average coherence drift from -18.6 to -1.9 and raises turn-10 trait expression from 78.0 to 93.1. These results suggest that activation steering becomes more reliable when interventions follow the prompt-mediated pathways that models already use for behavioral control.

cs.CL · cs.AI

新论文 · v1arXiv:2611.14508

真实连接组何时胜出?用未测量的生理参数检验连接组的结构-功能主张

When Does the Real Wiring Win? Testing connectome structure-function claims against unmeasured physiology

Yeyuan Liu

AI 速读 基于摘要

作者通过区分三种估计目标(P1/P2/P3),检验连接组约束模型中“真实布线优于打乱布线”的结论有多少来自调参偏差而非结构本身。

cs.LG · q-bio.NC

查看原文摘要

Connectome-constrained models are often used to argue that a measured wiring diagram outperforms shuffled or rewired wiring, and hence that structure shapes function. Such comparisons can confound wiring with how the models are tuned: a connectome fixes who connects to whom, not the excitability, gains or plasticity rates the model also needs, and modellers often tune these until the real-wiring model works. We separate three estimands: physiology tuned on the real wiring and transferred to nulls (P1), each wiring tuned on its own (P2), and P2 restricted to physiology consistent with independent data (P3). The biases involved are known in machine learning (under-tuned baselines, inherited weights, winner's curse); we measure what they do to biological conclusions, using synthetic ground truth, placebo nulls and three Drosophila circuit models. Some claims survive every protocol we test: segregated reward and punishment dopamine improves learning, and head-direction topography is required for a persistent bump. Others do not. In the mushroom body, the real Kenyon-cell output wiring beats a cross-subtype identity shuffle by 0.09 under P1 and P2 but loses to it by 0.09 under P3 (95% CIs exclude zero; held-out runs confirm). The verdict is set by the share of alpha'beta' cells among active Kenyon cells, which P1 selects low; at the share implied by imaging (about 44%) the real-wiring model fails to learn, exposing a model inadequacy rather than a deficit of the fly's wiring. In flyvis, P1 penalises a mirrored connectome, which has a constructed solution within 0.07 (median) of the real error, more than a spatially shuffled one in 50 of 50 members; the ranking survives ten-fold longer retraining but depends on the checkpoint at fifty-fold. A credible structural claim needs matched optimisation, data-constrained physiology and a model that still works there.

新论文 · v1arXiv:2611.14285

LM-SimBench:面向大语言模型训练仿真的统一框架、数据集与基准

LM-SimBench: A Unified Framework, Dataset, and Benchmark for Large Language Model Training Simulation

Yu Dong, Hong Li, Qiang Sun, Xu Zhou, Jinbiao Huo, Qixiu Cheng, Zhiyuan Liu

AI 速读 基于摘要

提出统一框架、性能剖析数据集与基准 LM-SimBench,用于在可控条件下比较和评估大语言模型训练仿真器。

cs.AI

查看原文摘要

Evaluating candidate parallelization strategies through distributed training runs makes strategy selection prohibitively expensive at scale. Performance simulation offers a lower cost alternative, yet controlled comparisons among existing simulators remain difficult because they differ in the training stages they model and the workloads on which they are evaluated. We introduce LM-SimBench, a unified framework, profiling dataset, and benchmark for evaluating LLM training simulators. The framework decomposes simulation into functional stages from model compilation to schedule level aggregation, connecting execution representations and cost estimators to measurable evaluation targets. Following this framework, we profile 23 model settings from 10 dense and Mixture-of-Experts (MoE) LLM families on an Ascend Neural Processing Unit (NPU) cluster. The resulting dataset contains 348 feasible configurations that jointly vary five parallelism dimensions and activation recomputation, with six views spanning configuration, rank, operator, event, and kernel granularity. Evaluations of representative training simulators demonstrate how LM-SimBench supports comparisons of prediction accuracy, assessment of configuration selection, and diagnosis of prediction errors. Matched GPU-NPU experiments validate the cross-platform applicability of the collection and evaluation protocol and demonstrate NPU-guided GPU configuration selection.

新论文 · v1arXiv:2611.14033

Few-Step Streaming Video Generation via Condition Shifting

Deyuan Liu, Jungang Li, Kaiwen Zheng, Kai Jiang, Jintao Chen, Yaole Wang, Ming Lin, Tao Lin 等 11 位作者

原文摘要

Few-step sampling reduces the cost of streaming video generation. Distribution Matching Distillation (DMD) supervises few-step generators with a separate fake-score network, which adds training memory and computation and must track the evolving generator. We extend APEX to streaming video by using condition shifting to estimate the velocity field of the generated distribution within the generator. The original text condition selects generation, while a shifted condition selects fake estimation using the same parameters. This removes the independent fake network while retaining S2-Avatar's frozen reference teacher, Self-Replay Forcing, and perceptual regularization. We evaluate APEX on 180-second videos using three backbone evaluations per block and a one-step spatial Refiner, with a 70-case human study and a 320-case StreamAV-Bench comparison. Compared with S2-Avatar, APEX achieves higher video instruction fulfillment on the Progressive track (3.856 versus 3.831) and higher visual aesthetics across both tracks (0.641898 versus 0.632606). Human raters favor APEX most strongly on instruction following, with +30.0% net preference, followed by consistency and video quality at +4.3% each. Motion quality favors S2-Avatar, audiovisual synchronization is predominantly tied, and usability is unchanged. Separate measurements under matched training settings show 4.4% lower peak allocated GPU memory per GPU and 9.2% shorter mean iteration time than DMD.

cs.CV · cs.AI

版本更新 · v3arXiv:2602.22838

How Many Votes is a Lie Worth? Measuring Strategyproofness through Resource Augmentation

Ratip Emin Berker, Vincent Conitzer, Eden Hartman, Jiayuan Liu, Caspar Oesterheld

原文摘要

It is well known, by the Gibbard-Satterthwaite Theorem, that when there are more than two candidates, any non-dictatorial voting rule can be manipulated by untruthful voters. But how much stronger is an untruthful voter than a truthful one under different voting rules? We suggest measuring the potential comparative advantage of a strategic voter by asking how many copies of their (truthful) vote must be added to the election in order to achieve an outcome as good as their best manipulation. Intuitively, this definition quantifies what a voter can gain by manipulating in comparison to what they would have gained by finding like-minded voters to join the election (equivalently, by increasing their voter weight). Our measure is prior-free and requires no assumptions on the voters' cardinal utilities. Using this framework, we obtain a principled method to compare the manipulation leverage for different voting rules. We show that while the manipulation leverage of many rules grows linearly with the number of voters, Borda Count's is m-2, where m is the number of candidates. We prove that the positional scoring rule with the smallest manipulation leverage is always Borda Count (if voters outnumber candidates) or Plurality (otherwise). Further, any rule satisfying a weak form of majority consistency (and thus any Condorcet extension) cannot outperform Plurality, while any majoritarian rule will perform significantly worse. Consequently, Borda Count has much lower manipulation leverage than these wide classes of rules under large electorates. Finally, we establish a quantitative extension of the Gibbard--Satterthwaite theorem, proving no anonymous and onto voting rule can have manipulation leverage that is lower than m-2 across all electorate sizes. As a result, Borda Count is indeed optimal among all such rules.

cs.GT

新论文 · v1arXiv:2611.13572

Market-Conditioned JEPA: Learning from Unpredictable Market Shocks

Yuqi Wang, Fengyuan Liu, Mukai Li, Haochen Luo, Lei Li, Qi Liu

原文摘要

Much of the variation in financial time series is driven by market-wide shocks that cannot be predicted from an asset's own history. Per-asset self-supervised learning treats this variation as irreducible noise. Under a latent factor model, we show that conditioning prediction on the realized market factor makes the asset's market exposure necessary for optimal prediction, while reducing the noise against which the asset-specific component is learned. Building on this insight, we introduce Market-Conditioned JEPA (MC-JEPA), a joint-embedding predictive architecture for financial time series. During training, we construct a leave-one-out market condition for each asset from the future target embeddings of other assets and incorporate it through factor loadings derived from the asset's own representation. On 11 years of minute-level Chinese A-share data, MC-JEPA improves over per-asset JEPA across nine targets spanning returns, market exposure, risk, and liquidity, with the strongest and most statistically significant gains in exposure, risk, and liquidity. It achieves the best RankIC on all liquidity targets and on return horizons from two hours to five days, outperforming time-series foundation models and self-supervised baselines, and delivers the best portfolio performance in a historical backtest. Ablations show that the return and exposure gains require the condition to be aligned with the realized market movement. After restoring the volatility scale removed by normalization, the predictor's factor loadings rank stocks by market beta nearly as well as a supervised probe, without labels. A synthetic factor-model study with known parameters shows that conditioning improves the recovery of both market exposure and the asset-specific component.

cs.LG · cs.AI · cs.CE

新论文 · v1arXiv:2611.12872

HiVe-Mem:面向多模态智能体的横向记忆扩展与纵向证据组合交织框架

HiVe-Mem: Interleaving Horizontal Memory Expansion and Vertical Evidence Composition for Multimodal Agents

Haozhen Zhang, Bohan Liu, Jianzhu Bao, Qingyuan Liu, Haodong Yue, Xiao Li, Zi Pong Lim, Wenya Wang

AI 速读 基于摘要

HiVe-Mem 通过关系图扩展记忆覆盖范围,并为每条检索记忆按查询自适应组合多模态证据,以提升多模态智能体的长期交互表现。

cs.CL · cs.AI · cs.LG

查看原文摘要

As multimodal agents accumulate increasingly long interaction histories, effectively retrieving and utilizing past information becomes critical for long-term interaction. Existing memory systems typically rely on semantic retrieval over compressed memories and expose predefined representations, which may miss relevant memories and overlook heterogeneous evidence needs across queries. We introduce \textbf{\hivemem}, a multimodal memory framework that interleaves \textbf{\textsc{H}}or\textbf{\textsc{i}}zontal Memory Expansion with \textbf{\textsc{Ve}}rtical Evidence Composition. For horizontal memory expansion, \hivemem organizes memory episodes into a relational graph using textual and visual anchors, expanding semantically retrieved seeds with related neighbors to recover complementary information. For vertical evidence composition, each retrieved memory retains multiple evidence forms, including compact summaries, captions, grounded visual views, raw images, and interaction history. A lightweight trainable selector independently composes an evidence subset for each retrieved memory, enabling query-adaptive utilization of heterogeneous multimodal information. This two-dimensional design jointly broadens memory coverage and adapts the evidence contributed by individual memories. Experiments across three multimodal memory benchmarks show that \hivemem consistently improves task performance across base models while reducing token consumption by about 90\% compared with the most efficient competing multimodal baselines.

新论文 · v1arXiv:2611.12452

V3DSAM: Semantic-Geometric Loop Verification and Geometry-Anchored Persistent Instance Mapping for Feed-Forward Dense SLAM

Maolin Ye, Dongqing Zhao, Linyang Li, Shuai Xue, Yuan Liu, Yiyuan Wang, Wen Li

原文摘要

To address unreliable cross-view association in long-sequence feed-forward dense SLAM, this letter presents V3DSAM, an open-vocabulary semantic dense SLAM system that establishes physical correspondences at both the scene and object levels. The system combines feed-forward geometric estimates from VGGT-SLAM 2.0 with open-vocabulary semantic observations from SAM3. We introduce semantic-geometric dual-scale loop verification, which identifies false loop closures using pixel-level bidirectional reprojection and object-level 3D spatial correspondences, without accessing backbone-internal features. We further propose geometry-anchored persistent instance mapping, which defines physical instances through class-constrained 3D connectivity in an optimized global coordinate system and assigns global IDs without inter-frame identity propagation. The proposed verifier rejects all four false loop candidates in our TUM RGB-D evaluation, while long-sequence ScanNet experiments show improved instance identity consistency. Thus, V3DSAM reduces dependence on internal backbone features and temporal ID propagation for robust long-term cross-view association.

cs.RO · cs.CV

新论文 · v1arXiv:2611.12288

ForgeSystem: An Architecture for Demand-Specific Artefact Production with AI Agents

Qingfeng He, Zhui Zhu, Yaojian Chen, Shangzhan Li, Leshan Li, Tingjian Zhang, Qian Xie, Yuxuan Li 等 10 位作者

原文摘要

General-purpose software serves many different demands, but this flexibility costs performance and efficiency on any specific demand. Software tailored to a specific demand avoids these losses, yet developing it requires substantial time and effort from human experts. AI agents offer an alternative: they can design, implement and test artefacts tailored to individual demands. We call this production paradigm Forge. Forging for a demand is economically justified when the cumulative benefit of specialisation exceeds the total cost of construction, verification and maintenance. To make Forge a repeatable production process, we propose ForgeSystem, which consists of a control layer, a forge loop and a recursive self-improvement (RSI) loop. The control layer selects which artefact serves each demand and decides which demands to forge, when to forge them and from which starting point; the forge loop iterates between production and verification until a candidate artefact passes verification; and the RSI loop draws on accumulated production records to supply starting points, refine the harness and train models. We implement ForgeSystem for training frameworks, decoding megakernels and individual computational kernels. Forged training engines reach 1.047-1.332x the model-FLOPs utilisation of their reference frameworks, forged megakernels achieve a geometric-mean decoding speedup of 1.21x over SGLang across thirteen configurations, and forged kernels match or exceed expert libraries in eighteen of twenty-two configurations, while satisfying task-specific quality requirements. Controlled comparisons show that explicit quality requirements steer agents towards optimisations that preserve training quality. We also discuss a gradual transition to Forge through service routing, and how demand-specific production may shift value accumulation and trust towards production systems.

cs.SE

版本更新 · v2arXiv:2609.19911

CitySTAR: Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding

Shuai Zhang, Hongye Hou, Qinghe Liu, Zhuoxiao Li, Dongli Wu, Jing Ou, Yuan Liu, Wufan Zhao

原文摘要

3D grounding aims to localize target entities in complex scenes from natural language and plays a fundamental role in embodied perception and spatial reasoning. However, existing approaches mostly rely on feature similarity or direct matching, making it difficult to connect natural-language intent with the implicit semantic and geometric structures hidden in billion-scale urban point clouds. We reformulate city-scale 3D grounding as structured constraint reasoning, where description semantics are organized into computable cross-modal constraints over open-vocabulary 3D entities, attributes, and spatial relations. We present CitySTAR, a training-free framework for reasoning-driven urban 3D grounding. CitySTAR lifts raw billion-scale urban point clouds into a query-ready scene graph of open-vocabulary 3D instances, with CodeLLM-driven tools supplying multimodal evidence for node attributes and 3D spatial relations. It then models target-context topology with paired hypergraphs and performs bidirectional topology verification for structural disambiguation. Finally, a Reflective Cross-modal Grounding module integrates topology consistency and candidate-centered 2D visual evidence to make decisions over a metric-aware 3D context graph. To further support this setting, we introduce CitySTAR-3D, an enhanced benchmark that improves semantic coverage, instance completeness, bounding-box fidelity, and spatial-relation complexity in city-scale 3D grounding. Extensive experiments show that CitySTAR consistently improves open-world urban 3D grounding while maintaining strong interpretability and generalization.

cs.CV

新论文 · v1arXiv:2611.11875

Beyond Head Importance: Collective Computation in Video Transformers

Yi Yang, Siyuan Liu, Bingbing Nie

原文摘要

Attention heads in video Transformers vary greatly in functional importance. Understanding their contributions requires examining not only which heads are important, but also how they participate in collective computation within the network. We study this collective computation from two perspectives: the downstream use of head outputs and the composition of interactions across layers. Ablation analyses of four video Transformers show that high-importance heads identified on a single task also support other video understanding tasks and help preserve the representational structure that distinguishes different videos. Representational responses to head ablation correlate weakly with head importance after the attention module, but more strongly after the MLP in the same block. Adapting this downstream processing through MLP-only fine-tuning further improves the use of lower-importance head outputs. Meanwhile, through composition across layers, sets of heads with shorter spatiotemporal attention distances support stronger perturbation responses at distant tokens than sets with longer distances. Their joint ablation causes even greater performance loss than ablating equally sized sets of high-importance heads, revealing collective contributions not fully captured by individual importance rankings. These findings highlight collective computation as a key perspective for understanding attention head function: functional contributions depend on both how head outputs are used downstream and how local interactions compose across layers.

cs.CV

版本更新 · v3arXiv:2606.09777

AetheRock: An Arm-Worn Robot Teaching System for Force-Guided Vision-Tactile Learning

Hong Li, Yue Xu, Yihan Tang, Yankang Dong, Chenyuan Liu, Chenyang Yu, Xuyang Li, Siyuan Huang 等 11 位作者

原文摘要

Force and tactile sensing are essential for contact-rich manipulation, but their integration into handheld or wearable devices is constrained by cost, size, and mechanical compatibility. Tactile signals are also sensitive to manufacturing variations and wear during use, posing further challenges to policy learning. To address these hardware and learning challenges, we introduce AetheRock, an arm-worn device for collecting gripper-force, visual, and tactile data. AetheRock incorporates GelSlim-Mini, our improved version of GelSlim 4.0 designed for low-cost, easy manufacturing, at the gripper fingertip, together with a resistive pressure sensor at the human finger contact area. To learn robust representations from the collected data, we propose ForceVT, a framework that aligns multimodal representations and uses force and vision to guide tactile learning, mitigating the effects of manufacturing variations and sensor degradation. Real-world experiments demonstrate efficient data collection with AetheRock. ForceVT improves average performance by 13% over the vision-tactile baseline and maintains an average task progress of 55.0% under reduced tactile fidelity, compared with 58.0% at full fidelity. Project page: https://lihongcs.github.io/aetherock.

cs.RO

版本更新 · v2arXiv:2605.08354

Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria

Juanxi Tian, Fengyuan Liu, Jiaming Han, Yilei Jiang, Yongliang Wu, Yesheng Liu, Haodong Li, Furong Xu 等 9 位作者

原文摘要

Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scalar or pairwise labels, collapsing nuanced preferences into opaque parametric proxies and exposing vulnerabilities to reward hacking. While recent Rubrics-as-Reward (RaR) methods attempt to recover this structure through explicit criteria, generating rubrics that are simultaneously reliable, scalable, and data-efficient remains an open problem. We introduce Auto-Rubric as Reward (ARR), a framework that reframes reward modeling from implicit weight optimization to explicit, criteria-based decomposition. Before any pairwise comparison, ARR externalizes a VLM's internalized preference knowledge as prompt-specific rubrics, translating holistic intent into independently verifiable quality dimensions. This conversion of implicit preference structure into inspectable, interpretable constraints substantially suppresses evaluation biases including positional bias, enabling both zero-shot deployment and few-shot conditioning on minimal supervision. To extend these gains into generative training, we propose Rubric Policy Optimization (RPO), which distills ARR's structured multi-dimensional evaluation into a robust binary reward, replacing opaque scalar regression with rubric-conditioned preference decisions that stabilize policy gradients. On text-to-image generation and image editing benchmarks, ARR-RPO outperforms pairwise reward models and VLM judges, demonstrating that explicitly externalizing implicit preference knowledge into structured rubrics achieves more reliable, data-efficient multimodal alignment, revealing that the bottleneck is the absence of a factorized interface, not a deficit of knowledge.

cs.AI

新论文 · v1arXiv:2611.10562

ZARA: Zero-shot Animatable and Relightable 3D Avatar reconstruction from a single image

Yixiao Chen, Dongdong Weng, Chengfeng Zhao, Tao Gong, Zhihe Zhao, Zhe Zhu, Yue Liu, Yuan Liu

原文摘要

Recent large human reconstruction models create remarkable animatable 3D avatars from a single image, but their appearance remains entangled with the illumination and cannot be relighted. In contrast, existing 3D relightable-avatar reconstruction methods typically require person-specific optimization. We present ZARA, a zero-shot feed-forward framework that reconstructs an animatable 3D Gaussian avatar together with its intrinsic attributes from a single image. ZARA couples a pretrained large-scale human reconstruction model with a Material Transformer to inherit geometry priors while learning material-aware Gaussian representations. To preserve localized details, we introduce Gaussian-aligned material feature fusion strategy, which injects multi-scale material features onto individual Gaussians and combines them with geometry tokens. As most human-avatar datasets lack ground-truth material maps, we use pseudo-material labels as conditioning inputs and supervision targets during training. We further introduce MatFace regularization to preserve facial structure and color in albedo prediction under unreliable facial pseudo-material supervision. Extensive experiments demonstrate that ZARA reconstructs animatable and relightable humans within tens of seconds without person-specific optimization or post-processing, outperforming existing baselines in both relighting quality and materials generalization ability. As the ability of recovering the physically-based-rendering attributes of the human, ZARA also enables direct material editing of the avatar's appearance.

cs.CV

版本更新 · v2arXiv:2607.07625

Embedded Blockchain Infrastructure Management (eBIM): A RISC-V-Empowered Hardware--Software Co-Design Framework Towards Trustworthy Blockchain

Qinglin Yang, Yuan Liu, Yaoyao Zhang, Boya Wang, Zongjian You, Chunming Rong, Zhihong Tian

原文摘要

Blockchain systems are shifting from decentralized ledgers for digital assets to general-purpose trust infrastructures for verifiable computation, decentralized physical resources, and automated infrastructure management. However, deploying these systems through third-party Blockchain-as-a-Service (BaaS) offerings may introduce dependencies involving operational control, confidentiality, and infrastructure governance. Meanwhile, blockchain execution and verification impose demanding requirements on cryptographic processing, isolation, and reproducibility. RISC-V offers an open, extensible instruction set architecture that enables co-design of software execution environments and domain-specific security hardware. Inspired by the embedded identity and provisioning model of an embedded subscriber identity module (eSIM), this survey proposes embedded Blockchain infrastructure management (eBIM) as a conceptual hardware-software co-design framework that organizes existing RISC-V-enabled technologies into a hardware-anchored blockchain infrastructure stack. We systematically review RISC-V-based smart-contract execution, trusted execution environments, zero-knowledge virtual machines, and cryptographic acceleration, and analyze their relationship to blockchain requirements, including deterministic execution, verifiability, extensibility, and secure key management. Based on this evidence, we distinguish currently demonstrated capabilities from the proposed eBIM integration vision and identify major open challenges, including system-level benchmarking, blockchain-oriented cryptographic extensions, TEE security, post-quantum migration, and deployable hardware-software co-design. The survey provides an architectural reference for researchers and designers investigating open and verifiable blockchain infrastructure.

cs.CR · cs.AR

版本更新 · v2arXiv:2604.17139

The Consensus Trap: Collaborative Interleaved Generation to Defend against a Corrupted Majority

Jiayuan Liu, Shiyi Du, Weihua Du, Xinhao Cheng, Mingyu Guo, Vincent Conitzer

原文摘要

Majority voting offers a simple way to combine answers from multiple large language model (LLM) agents. When a majority follows instructions favoring the same incorrect answer, however, agreement reinforces the error. We call this failure the "consensus trap": a minority may identify the error, yet its reasoning cannot change a vote over completed answers. We introduce chunk-interleaved Round-Robin (RR) collaboration, in which agents take turns extending one unfinished reasoning trajectory. A minority of agents with correct reasoning can insert corrections that subsequent speakers read before the answer is complete. RRMaj combines several such trajectories by a final vote. We characterize a majority barrier for outcome-level voting over final answer labels and derive a local sufficient condition for expected progress when the minority's cumulative corrections outweigh opposing corrupted updates. Across model families and verifiable reasoning benchmarks, RRMaj substantially improves accuracy under majority corruption while retaining comparable average performance under minority corruption in the main advisory-instruction setting. RR also strengthens full-response debate. Scoring the shared reasoning between turns shows that, on average, continuations from uncorrupted agents increase support for the correct answer over the incorrect target. Parallel local serving adds modest latency in the measured deployment. These findings show how language shared during reasoning, and the timing of that exchange, can help a minority correct a group's answer.

cs.CL · cs.AI · cs.MA

新论文 · v1arXiv:2611.09041

DobotTrack: Target-Grounded Vision-Language-Action Learning for Embodied Person Tracking

Shengjun Deng, Yinghan Zhang, Chengrui Wei, Liu Liang, Songyuan Liu, Pengkun Zheng, Yajun Zheng, Ying Zhang 等 11 位作者

原文摘要

Language-guided embodied person tracking requires a mobile agent to identify a target from a referring description and consistently follow the target under egocentric observations. We present DobotTrack, a target-grounded vision-language-action (VLA) framework that integrates auxiliary grounding supervision with efficient temporal modeling. We systematically investigate five auxiliary tasks---person segmentation, bounding-box grounding, visual-spatial classification (VSC), future DINO feature prediction, and future-frame prediction---and adopt complementary mask and bounding-box supervision to enhance target delineation and localization. We introduce Q-identity, a target-conditioned historical visual compression module that leverages target-grounding predictions to selectively preserve identity-discriminative appearance features and spatial cues in compact historical tokens. On EVT-Bench, our 0.8B-parameter model achieves an average success rate of 77.9%, exceeding OmTrackVLA by 16.9 percentage points across the three tasks. We further construct a real-world person-tracking dataset collected using a quadruped robot, comprising 126 episodes and 596,323 mask-annotated frames. The target masks enable automatic derivation of bounding boxes and visual-spatial labels encoding horizontal position and apparent image scale, providing additional grounding supervision without separate manual annotation of these labels. Together, our framework and annotation pipeline support learning target-grounded tracking policies from simulated and real-world data. Code is available at https://github.com/Dobot-Team/dobot_track.

cs.RO · cs.CV