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

+1959新增论文
+1550其中 AI 相关
+212已有论文修订
+78新增 AI 导读

arXiv 最近完成扫描:2026-11-17 23:20 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 00:39 — 2026-11-18 00:39(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:2026-11-17 23:20最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 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。

25,786 已收录论文21,491 AI 相关7,725 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 32 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 23:19(北京时间)
版本更新 · v2arXiv:2601.02236

CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models

Yihao Liang, Ze Wang, Ximeng Sun, Jiang Liu, Jialian Wu, Hao Chen, Xiaodong Yu, Emad Barsoum 等 10 位作者

原文摘要

Diffusion language models (DLMs) accelerate generation by decoding multiple tokens in parallel, but pushing them to fast decoding often sacrifices accuracy. We attribute this to a static-to-dynamic mismatch: training optimizes local denoising under fixed schedules, while fast inference skips steps and encounters irregular mask patterns. Existing accelerators largely address only one side of this problem. Training-free inference methods speed up decoding without changing the model, leaving the mismatch unresolved; training-side distillation methods adapt the model, but often tie the student to a specific decoding trajectory, limiting composability and still suffering accuracy loss. We propose CD4LM, a composable framework for accurate DLM acceleration. Its core training component, Discrete-Space Consistency Distillation (DSCD) trains a trajectory-invariant student on diverse masked states, reducing the mismatch without fixing a decoding policy. We pair DSCD with a lightweight ConfidenceAdaptive Decoder, while keeping the trained student compatible with external inference-side accelerators. On GSM8K, CD4LM preserves accuracy while achieving a 5.18x speedup; stacking CD4LM with per-step cache accelerators further pushes speedup to 9.73x at teacher-level accuracy, suggesting a scalable path for combining training-side robustness with future decoding advances. Code is available at https://github.com/yihao-liang/CDLM.

cs.CL

版本更新 · v3arXiv:2511.21542

E0: Expressive Fine-Grained Discrete Action Prediction for Vision-Language-Action Models via Tweedie Discrete Diffusion

Zhihao Zhan, Jiaying Zhou, Likui Zhang, Qinhan Lyu, Hao Liu, Weizheng Li, Jusheng Zhang, Ziliang Chen 等 13 位作者

原文摘要

Vision-Language-Action (VLA) models offer a unified framework for robotic manipulation by integrating visual perception, language understanding, and control generation. However, existing VLA systems still struggle to generalize across diverse tasks, scenes, and camera viewpoints, and often produce coarse or unstable actions. We argue that these limitations are closely tied to the structural properties of actions in VLA settings, including the inherent multi-peaked nature of action distributions, the token-based symbolic reasoning of pretrained VLM/VLA backbones, and the effective finite resolution imposed by real-world robotic control. Motivated by these properties, we introduce E0, a tweedie discrete diffusion framework that formulates action generation as iterative denoising over quantized action tokens. By operating in a discrete action space with a principled diffusion process, E0 naturally aligns with token-based reasoning, supports fine-grained yet executable action control, and avoids the distributional mismatch of masking-based discrete diffusion. Experiments on LIBERO, VLABench, ManiSkill, and a real-world Franka arm demonstrate that E0 achieves state-of-the-art performance across diverse environments, outperforming strong baselines by 8.1% on average.

cs.RO · cs.AI · cs.CV · cs.LG

新论文 · v1arXiv:2611.13929

ReACT: Reflection-Consistent Modulation and Cross-Load Consistency for Humanoid Velocity Tracking Under Asymmetric Loads

Xianghui Wang, Aoran Fu, Liyou Luo, Shanze Wang, Xiaoyu Shen, Dan Zhang, Wei Zhang

原文摘要

In recent years, humanoid loco-manipulation has progressed to whole-body grasping, lifting, and transport. A basic requirement underlying these tasks is carrying the object to its destination, which depends on the locomotion controller accurately executing velocity commands from the navigation policy. However, carrying an object in one hand introduces a persistent asymmetric upper-body load that can degrade velocity tracking. Persistent tracking biases can accumulate into position and heading deviations, increasing the risk of collisions and navigation failure. To address this problem, we present ReACT, a framework for accurate velocity tracking under asymmetric upper-body loads. Reflection-consistent disturbance modulation uses the estimated wrench to modulate actor features for load compensation while preserving action correspondence under reflected observations. Cross-load tracking consistency training compares loaded and unloaded conditions under the same velocity commands to promote consistent velocity tracking across loading conditions. Simulation experiments on a Unitree G1 humanoid robot show improved velocity tracking and reduced directional bias under varying asymmetric loads. Real-world experiments demonstrate collision-free goal reaching in all 40 tested navigation trials under unilateral hand loads with a fixed mapless navigation policy.

cs.RO

版本更新 · v3arXiv:2609.12021

Fast Odd-Permutation Sums in Characteristic Two and Shortest Even Directed Cycles

Boxuan Chen, Bin Cui, Hanqing Li, Xupeng Miao, Haoze Wang

原文摘要

For an $n\times n$ matrix over a field of characteristic two, let $Φ$ denote the sum of the odd permutation monomials. We give a deterministic algorithm that evaluates $Φ$ and all its first partial derivatives using $O(n^ω)$ field operations, where $2<ω\le3$ is any fixed admissible exponent for square matrix multiplication. As an application, we obtain faster randomized algorithms for shortest even directed cycles. Given an $n$-vertex directed graph whose shortest even cycle has length $\ell$, with high probability we compute $\ell$ and the union of the arcs of all shortest even cycles in $\widetilde O(n^ω\ell)$ time, and find one such cycle in $\widetilde O(n^ω\ell+n^2\ell^2)$ time. The resulting general bounds are $\widetilde O(n^{ω+1})$ and $\widetilde O(n^4)$, respectively, improving on the $\widetilde O(n^{ω+3})$ and $\widetilde O(n^{ω+4})$ bounds of Björklund, Husfeldt, and Kaski [BHK24].

cs.DS

版本更新 · v2arXiv:2610.07468

Partially Dynamic Single-Source Shortest Paths in Almost-Linear Time

Bin Cui, Hanqing Li, Xupeng Miao, Haoze Wang

原文摘要

We study $(1+ε)$-approximate single-source distances in directed graphs with positive integer edge weights in $[1,W]$. For every $0<ε\le1$, we give deterministic data structures for either edge insertions or edge deletions with total update time $m^{1+o(1)}ε^{-1}\log W$, where $m\ge n$ bounds the total number of initially present and inserted edges. Both structures explicitly maintain approximate distance estimates, answer distance queries in constant time, and identify unreachable vertices exactly. The incremental structure additionally reports a simple $(1+ε)$-approximate source path $P$ in $O(|P|)$ time. Our decremental structure gives the first almost-linear-time algorithm. It improves the previous best randomized expected bound of $\widetilde O(\min\{n^2,mn^{2/3}\})$ against an oblivious adversary [BPW20]. Our incremental bound improves the $ε^{-B}$ dependence of the $B$-level recursive algorithm of [Liu26] to an explicit $ε^{-1}$ factor while retaining almost-linear dependence on $m$. Our algorithms use modified interior point methods. For edge deletions, we extend the single-pair distance framework of [vBCKLMPSS24] to all targets simultaneously. A shared potential and one dynamic minimum-ratio cut instance support global updates to the distance labels. Our main insight is that constant relative cut balance certifies approximate distances at every target. For edge insertions, we develop an analogous circulation-based formulation implemented through the dynamic minimum-ratio cycle structure of [CKLMP24]. We also give a black-box reduction from distance estimates to path reporting in incremental graphs, with $m^{1+o(1)}ε^{-1}\log W$ additional maintenance time. This reduction may be of independent interest.

cs.DS

新论文 · v1arXiv:2611.09376

Can LLMs Debug Robots by Editing Their Weights?

Jusheng Zhang, Keze Wang, Liang Lin

原文摘要

A language model can repair a robot policy's lexical instruction grounding by editing just 65 token-embedding rows. We bring weight-space programming to robot foundation policies: GPT-6 Astra reads weights and uses a CPU workspace and budgeted simulator feedback, without gradient updates or new demonstrations. Three independent sessions on $π_{0.5}$ all improve success on 765 held-out paraphrases; the best raises success from 86.3\% to 92.0\% (48 repairs, four regressions; exact paired $p=1.31\times10^{-10}$). Among the 335 instructions containing edited tokens, success rises from 74.3\% to 87.5\%; the other 430 episodes have zero outcome changes. Matched random-direction edits do not help. Full replacement using the editor's own lexicon explains much of the gain but produces more regressions; its direct difference from the editor is not significant at 0.05. Across 13 further robot sessions, the editor declines 12 candidates; the sole retained edit does not show a significant held-out gain. Separately, benchmark metadata lowers FastWAM success from 70.0\% to 48.6\%, while the evaluated VLA's aggregate rate is unchanged. The evidence supports precise lexical repair, not general acquisition of missing robot capabilities.

cs.RO · cs.AI

新论文 · v1arXiv:2611.09013

KnowEvo: Knowledge Evolution for Protein Optimization

Zijie Xing, Xingyue Liu, Runze Wang, Luoming Hu, Yanming Shen

原文摘要

Large language models (LLMs) have shown promise in scientific discovery, yet systematically accumulating and refining reusable scientific knowledge remains challenging. Existing approaches primarily improve LLM-based problem solving through parameter optimization or feedback-driven refinement of prompts, programs, and solution trajectories, leaving acquired expertise either embedded in model weights or scattered across iterative problem-solving processes. As a result,knowledge is difficult to systematically inspect, evaluate, and refine. We propose KnowEvo, a framework that treats externalized knowledge itself as the optimization target. Our key insight is that scientific knowledge is inherently modular: multiple interacting mechanisms jointly determine the design outcomes. This makes knowledge evolution fundamentally challenging, as improvements cannot be attributed to individual components in isolation. To address this, KnowEvo represents knowledge as executable expertise blocks and organizes their refinements into strategy mutation trees, enabling structured exploration over a combinatorial knowledge space. The framework combines a Thompson-style forward allocation strategy that adaptively distributes evaluation budgets across strategy variants with a backward revision process, in which a code agent operates in an isolated sandbox to translate rollout evidence into localized program updates. This design enables persistent accumulation, evaluation, and refinement of mechanistic expertise across iterative experimentation. We evaluate KnowEvo on protein optimization tasks including stability and solubility. Results show that knowledge evolution consistently improves over initial strategy blocks and outperforms monolithic program evolution and prior LLM-guided evolution baselines across metrics such as pass@k, MRR, MAP,and NDCG@5. Code is available at https://github.com/recynie/KnowEvo.

cs.LG

版本更新 · v2arXiv:2607.06724

EvoPlan: Evolutionary Neuro-Symbolic Robot Planning with Spatio-Temporal Guarantees

Bhavya Sai Nukapotula, Samin Moosavi, Haoze Wang, Luke Duncan, Diya Shakkottai, Varun Murali, Srinivas Shakkottai

原文摘要

LLM-based robot planners are fluent but cannot guarantee that their plans are executable or safe. Classical PDDL planners can guarantee symbolic validity, but only once the problem is fully specified, and they make poor use of an LLM's ability to read context and repair plans. We present EvoPlan, a neuro-symbolic framework whose guarantees are symbolic validity and satisfaction of a constraint learned from data. The planner works with locally-hosted open-weight models, so it does not require a cloud service. EvoPlan has three parts. First, an offline procedure that mines a single global Signal Temporal Logic (STL) mobility constraint from demonstrations. Perturbed demonstrations supply the missing negatives without encoding any rule, and evolutionary search fits the constraint, which captures driving rules or social-navigation preferences within a modelled taxonomy of norms. We use the mined constraint to shield driving and navigation policies on Bench2Drive and HA-VLN-CE. Second, an evolutionary PDDL planner: an LLM proposes and repairs plans, programmatic validators decide which ones survive, and the validated portion of the plan grows over iterations. On open-world ALFWorld and NL-PDDL Blocksworld, it approaches classical planning when the goal vocabulary agrees with the action model, and it stays robust when the two disagree and classical planning fails. Third, a constrained execution loop: Nav2 uses the costmap to ground the plan into waypoints, which are checked against the mined constraint. Violations and execution failures update the PDDL problem for re-planning. We demonstrate the full pipeline in Gazebo and on a Clearpath Jackal robot. More details and videos are on the project page: https://nbhavyasai.github.io/evoplan/

cs.RO

新论文 · v1arXiv:2611.07481

Compact Motion Embeddings for Feed-forward Unified Human Animation

Seonwook Park, Hyunsoo Cha, Amrita Mazumdar, Shengze Wang, Tianye Li, Hanbyul Joo, Koki Nagano, Shalini De Mello

原文摘要

Animating a reference image with a driver's motion requires a motion representation that captures face, hand, and body articulation but excludes the driver's appearance. Most body animation methods take motion from external pose estimators and render it with many denoising steps; compact learned motion representations mostly cover the face. We present FUHA, a real-time-capable feed-forward transformer that learns a compact motion embedding of the whole human and uses it for face, upper-body, and full-body animation. A Q-Former compresses the driver's features from a frozen visual encoder into this embedding. To disentangle motion from appearance, a novel contrastive loss pulls it toward the motion embedding of the driver's rendered keypoint image and away from that of the same person in another pose. At inference time, FUHA needs no external pose estimators, keypoints, or parametric body models. As a retrieval key, the motion embedding matches body pose better than the learned global embeddings of ten vision encoders. Its same-person retrieval rate is 0.1%, against 9.5% for its own DINOv3 backbone. On our upper-body benchmark, FUHA outperforms all baselines on every self-reenactment metric and on cross-reenactment identity similarity. It is competitive on face and full-body and runs at up to 38.9 FPS at 512x512 on a single RTX 4090.

cs.CV

版本更新 · v3arXiv:2605.26647

More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations

Mingze Wang, Jinbo Wang, Yikuan Xia, Kai Shen, Shu Zhong

原文摘要

Feedforward network (FFN) layers account for a large fraction of parameters and nonlinear expressivity in Transformer-based large language models (LLMs). Despite the evolution from ReLU and GELU to gated variants such as SwiGLU, most FFN designs still use a single fixed activation function, applying the same nonlinear transformation to all tokens. In this work, we propose Mixture of Activations (MoA), a token-adaptive FFN design that mixes a dictionary of activation functions using lightweight input-dependent gates while sharing the same linear projections. As an input-independent counterpart, we also introduce learnable activations (LA), which form linear combinations of activation functions for both ReLU-type and SwiGLU-type FFNs. Theoretically, we establish strict finite-width expressive separations among fixed-activation FFNs, LA, and MoA: LA strictly contains fixed-activation FFNs, while MoA strictly contains LA, with the additional expressivity arising from input-dependent nonlinear hybridization. Empirically, we evaluate MoA through extensive pre-training experiments on dense and MoE language models ranging from 0.12B to 2B parameters under different token budgets, optimizers, and learning rate schedules. MoA consistently achieves lower terminal loss and exhibits more favorable scaling behavior than well-tuned baselines, with minimal parameter and computational overhead. These results suggest that token-adaptive activation mixing is a simple and effective mechanism for improving FFN expressivity in LLMs.

cs.LG · cs.AI · stat.ML

新论文 · v1arXiv:2611.06179

Chiron: Cache Management Empowered by LLM Intelligence for AI Workloads

Bohan Zhang, Renshu Ge, Tianze Wang, Chen Chen

原文摘要

AI clusters keep data in remote object stores and rely on local caches to stop GPUs from waiting for data. A cache performs well only when its prefetching and eviction policies match the access pattern, yet these patterns differ across AI workloads and change between phases of one workflow. Existing methods either need code changes, which compromises user transparency, or use low-end heuristics, which cannot follow such changes. Large language models (LLMs) can infer access behavior without user hints, but direct LLM control of cache actions suffers from long reasoning delay, high token cost, and poor decision quality. We present Chiron, a cache system based on advisory switching control. An LLM asynchronously diagnoses the access pattern and recommends a policy. A deterministic harness gates this advice, executes expert-designed policies locally, and returns cache feedback for review. We implement Chiron atop JuiceFS and evaluate it on nine AI workloads. It reduces job completion time by 14.3-41.2% over the best baseline on popular AI workloads.

cs.DC · cs.LG

版本更新 · v2arXiv:2510.10035

Failure-Driven Workflow Refinement

Jusheng Zhang, Kaitong Cai, Qinglin Zeng, Ningyuan Liu, Stephen Fan, Ziliang Chen, Keze Wang

原文摘要

Optimizing LLM-based workflows is typically formulated as a global search, where candidate workflows are evaluated based on a scalar metric. This paradigm, however, suffers from a critical flaw: information collapse. By reducing rich, multi-step execution traces to simple success/failure signals, existing methods are rendered blind to the underlying structure of failures, fundamentally preventing them from modeling the workflow's failure distribution. We reconceptualize this challenge as a distributional problem. We propose a new paradigm where the optimization goal is not to maximize a scalar score, but to directly minimize a workflow's Expected Failure Mass, i.e., the integral of its failure probability density function defined over a high-dimensional Failure Signature Space (FSS). This distributional lens allows us to move from inefficient, zero-order optimization to a principled, gradient-like descent on the failure landscape itself. We introduce CE-Graph, a framework that operationalizes this paradigm through a novel, failure-driven refinement process. CE-Graph approximates the failure distribution from a pool of counterexamples, identifies its densest regions as recurring failure modes, and applies targeted, operator-constrained graph edits via a Propose-and-Verify mechanism to greedily reduce the failure mass. On math, code, and QA benchmarks, our CE-Graph achieves higher robustness at a significantly lower cost than strong baselines. This suggests that a system's reliability emerges not from avoiding failures, but from systematically learning and reshaping the geometric structure of its failure distributions.

cs.AI

新论文 · v1arXiv:2611.03626

Isekai3D SDG: A Platform for Diverse Synthetic Gameplay Visual Data

Rafal Karp, Gene Liu, Shih-Hsin Li, Eric Courtemanche, Shengze Wang, Josef Spjut, David Pankratz, Mischa Kolbe 等 13 位作者

原文摘要

We present Isekai3D Synthetic Data Generation (SDG), a platform for simulating and capturing synthetic 3D gameplay for research in vision and world models, neural graphics, gameplay agents, and other applications. The platform combines reusable environment and character assets with Unreal Engine plugins in a two-stage workflow. First, world simulation generates gameplay while recording the world state, character movements, actions, and camera tracks needed for replay. Second, the recorded simulation is replayed to capture selected outputs, such as rendered video, images, and depth maps, at a specified resolution and frame rate under selected rendering and camera configurations. Separating simulation from capture allows the same recorded gameplay to produce multiple output variants without repeating the original simulation. Visual outputs are accompanied by frame-aligned camera, character, and action metadata. The platform uploads generated data directly in a training-friendly format, reducing intermediate storage, preparation time, and manual processing. This report describes the design of our overall system, including the platform's assets, plugins, and their functionality, explaining how they work together to generate diverse synthetic gameplay data.

cs.CV

新论文 · v1arXiv:2611.03404

VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing

Yexin Liu, Yunlong Lin, Zehan Wang, Guangxin He, Xinli Xu, Jiajun Zha, Yaofu Liu, Yueze Wang 等 14 位作者

原文摘要

Video dubbing aims to synthesize lip movements that match target speech while preserving the speaker identity, head pose, and background of a source video. Existing editors are predominantly trained via self-reconstruction under original paired audio, even though the source mouth becomes a conflicting target when driving speech is replaced. We introduce replacement-aware cross-audio supervision: paired-audio samples use full-frame reconstruction, whereas unpaired replacement-audio samples mask out source-mouth reconstruction losses and supervise the mouth solely through audio-visual synchronization while preserving unmasked facial regions and background. Because offline dubbing provides the complete source video and target speech beforehand, we present VidDub, a full-context diffusion editor distilled into two denoising steps (2 NFE). Our replacement-aware teacher first learns accurate lip synchronization without regressing toward conflicting source mouth movements. Matched trajectory regression then transfers the teacher's CFG-guided trajectories to a two-step student, and distribution matching distillation recovers visual quality after step compression. We will release the curated training dataset, VidDub-Bench, fixed paired- and cross-audio evaluation manifests, preprocessing outputs, and unified evaluation code. Across three training seeds, masking out conflicting source-mouth reconstruction improves cross-audio Sync-C by 0.833; the final two-step model combines strong lip synchronization with superior visual quality, identity preservation, and visual speech recognition across four benchmarks.

cs.CV

新论文 · v1arXiv:2610.39714

MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery

Yikun Zhang, Xiwei Cheng, Mingze Yuan, Yu Zhang, Brian Shim, Aarti Krishnan, Daniel Rosen, Kunyang Sun 等 18 位作者

原文摘要

Molecular discovery requires navigating vast combinatorial search spaces while balancing competing biological objectives. AI agents can automate expert-defined molecular design protocols, but automation alone does not address how to optimize workflows for new tasks or improve their development through experience. Here we introduce MoLRSI, an AI agent that combines systematic optimization of workflows and model architectures with persistent cross-task memory to recursively improve its search policy for molecular discovery. Workflow performance, refinement outcomes, and execution feedback guide subsequent searches, allowing the agent to improve both its workflows and its strategy for developing them. We evaluate MoLRSI in two challenging molecular discovery settings that require balancing competing properties. In antibiotic discovery, MoLRSI developed a screening workflow balancing antibacterial activity, cytotoxicity and structural novelty, achieving an experimental hit rate of 15.9%, compared with 8.7% for a previous expert-led workflow using the same training data and screening library. In de novo peptide-MHC binder design, MoLRSI developed workflows that jointly consider target binding and specificity, producing eight experimentally validated hits against MART-1 and SARS-CoV-1 pMHCs with preferential binding over tested off-targets while Claude Science completely failed. These findings demonstrate how experience-guided workflow optimization can address competing discovery objectives while improving the search strategies used in subsequent campaigns.

cs.AI

版本更新 · v2arXiv:2610.14807

ASIWorld: Benchmarking Autonomous Agents in a Persistent Survival Sandbox

Jianfeng Lin, Runze Wang, Haorong Hong, Yuxuan Xie, Zeno Zeng, Zhongyuan Liu

原文摘要

Evaluating autonomous agents requires examining whether they can translate goals into coherent action across extended interactions. In persistent environments, this requires coordinating interdependent actions under incomplete observations, accounting for delayed effects, and adapting as earlier decisions shape subsequent opportunities. We introduce ASIWorld, a survival sandbox that combines persistent world and character state with character-scoped observations and a programmable asynchronous interface to study sustained goal execution. Agents pursue interdependent production and exploration tasks through direct actions or agent-authored programs that continue running between model calls. The evaluation assesses task success, the attainment of development achievements, and survival costs, complemented by an analysis of execution behavior. In an exploratory study of nine agent configurations using a common harness, eight complete the production task and six complete both tasks. Analyses of execution trajectories and performance across difficulty levels reveal different preparation, combat, and recovery behaviors among configurations with similar task outcomes. Incomplete preparation is associated with stalled progression, while configurations that complete the tasks differ in survival costs and the fulfillment of additional achievement criteria. These findings illustrate the value of assessing sustained goal execution through both task outcomes and the behaviors and costs associated with achieving them.

cs.AI

版本更新 · v3arXiv:2602.18907

DeepInterestGR: Mining Deep Multi-Interest Using Multi-Modal LLMs for Generative Recommendation

Yangchen Zeng, Guangyuan Dong, Zhenyu Yu, Zhiyuan Hu, Jinze Wang, Rongfeng Guo

原文摘要

We introduce DeepInterestGR, a novel framework that integrates deep interest mining into the generative recommendation pipeline. This addresses the "Shallow Interest" problem: existing generative methods rely on surface-level textual features and fail to capture latent user motivations, limiting personalization depth and recommendation interpretability. Our approach leverages Multi-LLM Interest Mining (MLIM) via structured reasoning prompting, Reward-Labeled Deep Interest (RLDI) for quality control, and Interest-Enhanced Item Discretization (IEID) via RQ-VAE, combined with a two-stage SFT-GRPO training pipeline guided by an Interest-Aware Reward. We validate DeepInterestGR on three Amazon Review benchmarks (Beauty, Sports, Instruments), comparing against 14 state-of-the-art baselines including SASRec, BERT4Rec, TIGER, LC-Rec, and S-DPO. Our method achieves 12.4%-15.4% relative improvements on HR@10 and 15.5%-17.9% on NDCG@10, with cross-domain generalization gains of +24.8%. To our knowledge, this is the first work to demonstrate such significant gains by incorporating deep semantic interests into generative recommendation.

cs.LG · cs.CV · cs.CY

新论文 · v1arXiv:2610.38126

Answer-Only Disclosure: Private-Context LLM Assistance over Web APIs with a Leakage Ledger

Liang Yuan, Xiaohu Du, Ruikun Luo, Jinze Wang, Mashud Rana, Kaibin Wang, Jiangwen Zhou, Bo Li 等 9 位作者

原文摘要

Web assistants increasingly answer questions about a user's private documents by pairing a small on-device model with a cloud LLM behind a Web API. In collaborative decoding, the document stays on the client, and the cloud receives only a public view that the user approves, such as the question alone, but the two models exchange messages while the answer is generated. We show that the message transcript can disclose private content that neither the public view nor the answer contains. In a planted-secret audit, speculative decoding with private drafts did not include the secret code in its answers, yet sent the code to the cloud in rejected drafts. We present ADLER, a decoding protocol for streaming LLM APIs in which every message to the cloud depends only on the public view and the answer the user sees, regardless of how the client combines the two models or how the cloud behaves. A client-side leakage ledger then bounds how much the answer itself reveals relative to a public reference process built from the cloud's replies. In the audit, no ADLER configuration exposed the secret beyond the answer. On GSM8K math problems with numerical values masked in the cloud's input, ADLER with an unlimited leakage budget raises the exact-match accuracy of a 0.5B client from 0.41 to 0.83 and of a 1.5B client from 0.67 to 0.85 under lenient answer parsing, close to the 0.92 achieved by uploading the full problem. It also exceeds a zero-leakage program baseline (0.69) by 0.14 and 0.16, respectively. In this baseline, the cloud writes a program that the client runs offline using the private numbers. The ledger records the disclosure charge associated with this gain; budgets of 16 nats or less leave accuracy near the cloud-only baseline on GSM8K.

cs.CR · cs.AI

新论文 · v1arXiv:2610.37403

AuRaSim: A Ray-Tracing Based Automotive FMCW Radar Simulator for Dynamic Scenarios

Zhaoze Wang, Changxu Zhang, Tai Fei, Christopher Grimm, Yi Jin, Claas Tebruegge, Markus Gardill

原文摘要

Modern simulators can generate synthetic camera and LiDAR data with accurate annotations for downstream tasks. In contrast, automotive radar simulation remains less mature because it requires not only a 3D engine to model dynamic objects in the scenes but also electromagnetic material properties, antenna configurations, wave propagation mechanisms, and coherent signal synthesis. Existing frameworks are either proprietary or overly simplified, limiting the scalability of radar raw measurements. This paper presents AuRaSim, a ray-tracing-based automotive frequency-modulated continuous wave (FMCW) radar simulation framework for dynamic scenarios. Rather than implementing all components from scratch, AuRaSim builds on Blender for efficient dynamic-scene construction and Sionna RT for graphics processing unit (GPU) accelerated electromagnetic ray tracing, while introducing radar-specific adaptations for path-resolved propagation with complex coefficients, motion-aware Doppler modeling, and subsequently coherent multi-channel analog-to-digital converter (ADC) cube synthesis based on waveform configurations. Quantitative comparison between simulated and measured range-Doppler maps in digital-twin scenarios achieves a root-mean-square error (RMSE) of 0.147 and a peak signal-to-noise ratio (PSNR) of 16.93 dB, demonstrating the accuracy and fidelity of the synthetic signal. AuRaSim therefore provides a complete and extensible platform for reproducible automotive radar simulation and research. Project homepage: https://wangzhaoze.github.io/aurasim.

cs.RO · eess.SP

版本更新 · v2arXiv:2602.14107

ML-ECS: Heterogeneity-Aware Collaborative Multimodal Learning for Edge-Cloud Synergies

Yuze Liu, Shibo Chu, Tiehua Zhang, Hao Zhou, Zhishu Shen, Jinze Wang, Jianzhong Qi, Feng Xia

原文摘要

Edge-cloud synergies provide a promising paradigm for privacy-preserving deployment of foundation models in heterogeneous web environments, enabling lightweight edge models to support domain-specific multimodal we b services while cloud-hosted models facilitate collaborative knowledge sharing. However, in practical edge-cloud web environments, collaborative multimodal learning is challenged by modality heterogeneity (different modality combinations across domains) and model-structure heterogeneity (different modality-specific encoders/fusion modules). To address these issues, we propose ML-ECS, a collaborative multimodal learning framework that enables joint training between a server-based model and heterogeneous edge models. This framework consists of four components: (1) cross-modal contrastive learning (CCL) to align modality representations in a shared latent space, (2) adaptive multimodal tuning (AMT) to preserve domain-specific knowledge from local datasets, (3) modality-aware aggregation (MAA) to robustly aggregate while mitigating noise caused by missing modalities, and (4) SLM-enhanced CCL (SE-CCL) to facilitate bidirectional knowledge transfer between cloud and edge. Experimental results on various multimodal tasks show that ML-ECS consistently outperform state-of-the-art baselines under varying modality availability, achieving improvements of 1.55% to 16.75% in Rouge-LSum and improving both client- and server-side performance. In addition, by communicating only low-rank LoRA parameters and fused representations, ML-ECS achieves high communication efficiency, requiring only 0.71% of the total parameter volume.

cs.DC

版本更新 · v2arXiv:2605.09410

RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models

Weijia Liufu, Xiaoyu Guo, Ruiyi Chen, Jingzhi Liu, Kaidong Zhang, Xiwen Liang, Jianqi Lin, Dawei Sun 等 19 位作者

原文摘要

Vision-Language-Action (VLA) models remain brittle in long-horizon, contact-rich manipulation because success-only imitation provides little supervision for execution drift, while failed rollouts are often discarded. We introduce RePO-VLA, a recovery-driven policy optimization framework that assigns distinct roles to success, recovery, and failure trajectories. RePO-VLA first applies Recovery-Aware Initialization (RAI), slicing each corrective suffix into a new episode so corrective actions depend on the current adverse state rather than the preceding failure. It then learns a Progress-Aware Semantic Value Function (PAS-VF), aligning spatiotemporal trajectory features with instructions and successful references. The resulting labels salvage useful failure prefixes via reliability decay, while low-value labels mark drift and terminal breakdowns, teaching differences among nominal, failed, and corrective actions. The data engine turns adverse states into planner-generated or human-collected corrective rollouts, teaching recovery to the success manifold. Value-Conditioned Refinement (VCR) trains the policy to prefer high-progress actions. At deployment, a fixed high-value token biases actions toward the learned success manifold without online failure detectors or heuristic retries. We introduce the Failure-Recovery Benchmark (FRBench), with standardized error injection and recovery-focused evaluation. Across simulated and real-world bimanual tasks, RePO-VLA improves robustness, raising adversarial success from 20% to 75% on average and up to 80% in scaled real-world trials. Code and video results are available at https://1018weijia.github.io/RePO-VLA-Web/.

cs.RO · cs.AI

版本更新 · v2arXiv:2607.14486

Full-data accuracy with fewer labels for training and fine-tuning machine-learning force fields

Sheng Bi, Yi-Ze Wang, Jun Cheng

原文摘要

Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottleneck for both train-from-scratch and foundation fine-tuning workflows. Active learning can reduce this cost, but standard model-committee uncertainty is impractical for foundation MLFFs because each committee member requires a separate fine-tuning run. We present an active-learning workflow based on last-layer-projection regression (LLPR), a forward-pass-cheap per-configuration uncertainty estimator. Across molecular, condensed-phase, and electrolyte systems, LLPR identifies compact, high-value training sets that recover full-data accuracy using only a small fraction of electronic-structure labels. In foundation-model fine-tuning, LLPR-selected configurations approach the practical fine-tuning ceiling with substantially fewer labels than random selection. In iterative electrolyte fine-tuning, LLPR detects unphysical local coordination before new labelling, calibrates uncertainty in force-error units, and supports retrospective convergence monitoring. The resulting models reproduce reference density and Li--O coordination structure, providing a scalable uncertainty-quantification strategy across MLFF training regimes.

cs.LG

新论文 · v1arXiv:2610.35090

Test-Time Prompt-Agnostic Decomposition

Junze Wang, Lei Fan, Dezheng Zhang, Donglin Di, Yang Song, Sidong Liu, Cong Cong

原文摘要

Test-Time Prompt Tuning (TPT) adapts large pretrained models to unseen target distribution shifts by updating only lightweight prompt tokens. Existing TPT methods are effective, but they mainly optimize each prompt update locally. Across test-time steps, prompts updated at the current step are reused for the corresponding predictions and updates, so noisy or biased unlabeled objectives can accumulate and destabilize the prompt-update trajectory. We identify two failure modes: magnitude expansion, where updates move the prompt too far, and directional drift, where consecutive updates point in inconsistent directions. To analyze and control these failures, we propose Test-Time Prompt-Agnostic Decomposition ($\mathtt{TPD}$), which characterizes observed prompt-update trajectories from a dynamical-systems view and decomposes base prompt updates into magnitude and direction. $\mathtt{TPD}$ computes a spectral radius to measure update expansion and decomposes update directions into persistent, oscillatory, and residual components. Building on this decomposition, Adaptive Koopman Control ($\mathtt{AKC}$) regulates update magnitude by shrinking updates under expansive recent dynamics, while Hankel Update Router ($\mathtt{HUR}$) refines update direction by preserving persistent components and suppressing oscillatory and residual components. Together, $\mathtt{AKC}$ and $\mathtt{HUR}$ produce a stabilized prompt update. As a prompt-agnostic framework, $\mathtt{TPD}$ can be plugged into visual and text TPT methods without modifying the backbone, prompt architecture, or adaptation loss. Experiments on 15 datasets show that $\mathtt{TPD}$ consistently improves 10 baselines, with accuracy gains of $3$--$8\%$ for visual prompts and over $2\%$ for text prompts.

cs.CV

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1011ACL Anthology · ACL 2026

MAGIC: Deep Geometric Evolution with Structural Consensus for Temporal Knowledge Graph Reasoning

Chengao Liu University of the Chinese Academy of Sciences, Yuan Li, Yingze Wang, Jianbin Jiao University of the Chinese Academy of Sciences

原文摘要

Temporal Knowledge Graph (TKG) reasoning remains challenging to characterize with conventional flat representations due to its intrinsic heterogeneous structure. Existing multi-geometry approaches face two key bottlenecks: 1) the Riemannian depth barrier driven by numerical instability, which restricts models to shallow architectures; and 2) gate collapse, where adaptive fusion mechanisms suffer from gradient starvation and degenerate into single-geometry solutions. To this end, we propose MAGIC (Multi-geometry Annealing Graph Interaction with Consensus). Our framework introduces a Tangent-Residual Engine in multi-geometric spaces, which enables the first stable 8-layer geometric evolution and reveals a phenomenon termed Geometric Annealing, where manifold curvature spontaneously evolves from semantic flatness in shallow layers to structural complexity in deeper layers. We further design an explicit reasoning module with structural consensus, leveraging geometric invariants and structural priors to regulate gradient flow, prevent collapse, and ensure robust synergy across Hyperbolic, Spherical, and Euclidean spaces. Experiments show that MAGIC achieves state-of-the-art performance in TKG reasoning, improving MRR by up to 2.9 points.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1248ACL Anthology · ACL 2026

Enabling Agents to Communicate Entirely in Latent Space

Zhuoyun Du, Runze Wang alibaba, Huiyu Bai, Zouying Cao, Xiaoyong Zhu Alibaba Group and Microsoft, Yu Cheng Alibaba Group, Bo Zheng Alibaba Group, Wei Chen Zhejiang University 等 9 位作者

原文摘要

While natural language is the de facto communication medium for LLM-based agents, it presents a fundamental constraint. The process of downsampling rich, internal latent states into discrete tokens inherently limits the depth and nuance of information that can be transmitted, thereby hindering collaborative problem-solving. Inspired by telepathy, which bypasses symbolic language in communication, we propose Interlat (Inter-agent Latent Space Communication), a paradigm that leverages the continuous last hidden states of an LLM as a representation of its thought for direct communication (termed “latent communication”). An additional learned compression process further compresses latent communication via latent space reasoning. Experiments demonstrate that Interlat outperforms both fine-tuned chain-of-thought (CoT) prompting and single-agent baselines, even across heterogeneous models, promoting more exploratory behavior and enabling genuine utilization of latent information. Further compression not only substantially accelerates inference by up to 24× but also maintains competitive performance through an efficient information-preserving mechanism. We position this work as a feasibility study of entirely latent space inter-agent communication, and our results highlight its potential, offering valuable insights for future research.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.190ACL Anthology · ACL 2026

Stable Language Guidance for Vision–Language–Action Models

Zhihao Zhan, Yuhao Chen SUN YAT-SEN UNIVERSITY, Jiaying Zhou SUN YAT-SEN UNIVERSITY, Qinhan Lyu, Hao Liu SUN YAT-SEN UNIVERSITY, Keze Wang SUN YAT-SEN UNIVERSITY, Liang Lin SUN YAT-SEN UNIVERSITY, Guangrun Wang SUN YAT-SEN UNIVERSITY

原文摘要

Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously brittle to linguistic perturbations. We identify a critical "modality collapse” phenomenon where strong visual priors overwhelm sparse linguistic signals, causing agents to overfit to specific instruction phrasings while ignoring the underlying semantic intent. To address this, we propose Residual Semantic Steering (RSS), a probabilistic framework that disentangles physical affordance from semantic execution. RSS introduces two theoretical innovations: (1) Monte Carlo Syntactic Integration, which approximates the true semantic posterior via dense, LLM-driven distributional expansion, and (2) Residual Affordance Steering, a dual-stream decoding mechanism that explicitly isolates the causal influence of language by subtracting the visual affordance prior. Theoretical analysis suggests that RSS effectively maximizes the mutual information between action and intent while suppressing visual distractors. Empirical results across diverse manipulation benchmarks demonstrate that RSS achieves state-of-the-art robustness, maintaining performance even under adversarial linguistic perturbations.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.2131ACL Anthology · ACL 2026

Reinforcement Learning for Diffusion LLMs via Energy-Based Gibbs Alignment

Yijia Fan Nanyang Technological University, Microsoft Research Asia and SUN YAT-SEN UNIVERSITY, Jing Yang, Mingyu Liu, Kaitong Cai, Jian Wang Snap Inc., Keze Wang SUN YAT-SEN UNIVERSITY, Jusheng Zhang

原文摘要

Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm for text generation, offering parallel decoding and bidirectional context modeling. However, aligning dLLMs with reinforcement learning (RL) remains a significant challenge, as the marginal likelihood of sequences in masked diffusion is typically intractable, rendering standard policy gradient methods unstable or computationally prohibitive. In this work, we propose Diffusion-Gibbs Alignment (DGA), a novel variational framework that reformulates RL for dLLMs as a distribution matching problem. DGA bypasses the explicit computation of log-probabilities by leveraging a learned energy function to model the relative quality of samples. The optimization is decoupled into two stable steps: (1) contrastive energy ranking to capture global reward structures, and (2) weighted diffusion alignment to update the policy via importance sampling. Empirically, DGA establishes a new state-of-the-art across logical reasoning (Sudoku, Countdown), mathematical reasoning (GSM8K, Math500), and code generation (HumanEval, MBPP) benchmarks. DGA offers a novel variational perspective for dLLM alignment, achieving better performance while simultaneously enhancing training speed and memory efficiency.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.528ACL Anthology · ACL 2026

Provably Safe Offline-to-Online RL: Decoupling Learning from Data-Driven Safety Enforcement

Kaitong Cai, Jusheng Zhang, Keze Wang SUN YAT-SEN UNIVERSITY

原文摘要

Hybrid offline–online reinforcement learning (O2O RL) promises both sample efficiency and robust exploration, but suffers from instability due to distribution shift between offline and online data. We introduce RLPD-GX, a framework that decouples policy optimization from safety enforcement: a reward-seeking learner explores freely, while a projection-based guardian guarantees rule-consistent execution and safe value backups. This design preserves the exploratory value of online interactions without collapsing to conservative policies. To further stabilize training, we propose dynamic curricula that gradually extend temporal horizons and anneal offline–online data mixing. We prove convergence via a contraction property of the guarded Bellman operator, and empirically show state-of-the-art performance on Atari-100k, achieving a normalized mean score of 3.02 (+45% over prior hybrid methods) with stronger safety and stability. Beyond Atari, ablations demonstrate consistent gains across safety-critical and long-horizon tasks, underscoring the generality of our design. Extensive and comprehensive results highlight decoupled safety enforcement as a simple yet principled route to robust O2O RL, suggesting a broader paradigm for reconciling exploration and safety in reinforcement learning.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.558ACL Anthology · ACL 2026

RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents

Jize Wang, Han Wu, Zhiyuan You, Yiming Song Shanghai Jiaotong University, Yijun Wang, Zifei Shan WeChat, Tencent, Yining Li Shanghai AI Laboratory, Songyang Zhang Shanghai Artificial Intelligence Laboratory 等 12 位作者

原文摘要

Mixture-of-Agents (MoA) improves LLM performance through layered collaboration, but its dense topology raises costs and latency. Existing methods employ LLM judges to filter responses, yet still require all models to perform inference before judging, failing to cut costs effectively. They also lack model selection criteria and struggle with large model pools, where full inference is costly and can exceed context limits. To address this, we propose RouteMoA, an efficient mixture-of-agents framework with dynamic routing. It employs a lightweight scorer to perform initial screening by predicting coarse-grained performance from the query, narrowing candidates to a high-potential subset without inference. A mixture of judges then refines these scores through lightweight self- and cross-assessment based on existing model outputs, providing posterior correction without additional inference. Finally, a model ranking mechanism selects models by balancing performance, cost, and latency. RouteMoA outperforms MoA across varying tasks and model pool sizes, reducing cost by 89.8% and latency by 63.6% in the large-scale model pool. Code is available at https://github.com/Jize-W/RouteMoA.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.922ACL Anthology · ACL 2026

League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models

Qianhong Guo, Wei Xie, Xiaofang Cai, Enze Wang, Shuoyoucheng Ma, Xiaobing Sun A*STAR, Tian Xia, Kai Chen 等 10 位作者

原文摘要

Although large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, reliable evaluation remains a critical challenge due to data contamination, opaque operation, and subjective preferences. To address these issues, we propose League of LLMs (LOL), a novel benchmark-free evaluation paradigm that organizes multiple LLMs into a self-governed league for multi-round mutual evaluation. LOL integrates four core criteria (dynamic, transparent, objective, and professional) to mitigate key limitations of existing paradigms. Experiments on eight mainstream LLMs in mathematics and programming demonstrate that LOL can effectively distinguish LLM capabilities while maintaining high internal ranking stability (Top-k consistency = 70.7\%). Beyond ranking, LOL reveals empirical findings that are difficult for traditional paradigms to capture. For instance, “memorization-based answering” behaviors are observed in some models, and higher in-family scores are found in the OpenAI model family (\Delta = 9, p < 0.05). Finally, we make our framework and code publicly available as a valuable complement to the current LLM evaluation ecosystem.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表