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

+1680新增论文
+1333其中 AI 相关
+187已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 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 08:30 — 2026-11-18 08:30(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:2026-11-18 04:28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 22 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
新论文 · v1arXiv:2611.20986

Calpha: Toward Native Biomolecular Intelligence in a General-Purpose Language Model

Yong Liu, Zhanpeng Shi, Peicong Lin, Zhenyi Zhong, Yizhou Dang, Wendi Wu, Haoling Li, Shuangjia Zheng

原文摘要

Biomolecular foundation models predict the structures of proteins and their complexes accurately, and large language models (LLMs) reason in natural language, but the two remain separate: the abilities of the former are not part of a general-purpose LLM, and the reasoning of the latter does not enter a structure prediction. Calpha aims at one general model that folds proteins and complexes, understands protein sequence and structure, and lets its language reasoning influence the structures it predicts. This report covers the first step, in which an LLM outputs single-chain protein structures. Qwen3.5-9B reads a sequence enriched with ESM2 residue features. It can respond in text or emit a token that invokes a pretrained SimpleFold structure head, which receives information about the protein only through Qwen's residue states. Under a fixed folding request, the head achieves mean TM-scores of 0.808 on the FoldBench-334 development set, 0.635 on CASP16 domains and 0.900 on a CAMEO-style PDB set. We compare these predictions with a baseline in which ESM2-3B encodes the sequence and a fine-tuned SimpleFold-3B head predicts the coordinates. The two systems also differ in trainable weights, training duration and crop length. For chains of 100--299 residues, all three paired confidence intervals include zero. At 300--600 residues, the mean differences are -0.044, -0.160 and -0.025, respectively. In a separate test, four English request types triggered folding on every evaluated example. Protein training reduced accuracy on a 350-item MMLU-Pro subset from 77.4% to 70.3%. An LLM can therefore output single-chain structures from its own states, with lower long-chain scores in the current comparisons and reduced accuracy on the evaluated MMLU-Pro subset. Complex prediction, structure understanding and the effect of language reasoning on the predicted coordinates remain future work.

q-bio.QM · cs.AI

版本更新 · v4arXiv:2606.03159

NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation

Aarti Basant, Amlan Kar, Despoina Paschalidou, Fangyin Wei, Francesco Ferroni, Guillermo Garcia Cobo, Haithem Turki, Huan Ling 等 33 位作者

原文摘要

As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving policy model actively interacts with the environment, where its actions dynamically update the simulator state and directly influence the next set of generated sensor observations. While recent reconstruction-based neural simulators offer photorealism, they are fundamentally constrained by their initial captured data and struggle to generalize to highly dynamic or novel scenes. To overcome these limitations, we introduce OmniDreams, a foundation generative world model mid- and post-trained from the Cosmos diffusion model to autoregressively generate action-conditioned videos in real time. By leveraging the rich visual priors of Cosmos and mid- and post-training on 21k hours of driving scenarios, OmniDreams synthesizes complex, unobserved phenomena that are hard for traditional simulators to capture, such as extreme weather and unpredictable dynamic agent behaviors. Crucially, it autoregressively conditions its photorealistic sensor generation on past frames, the current simulator state, and immediate driving actions. Deployed in a closed-loop system with the Alpamayo 1 policy model and AlpaSim orchestrator, OmniDreams acts as a highly responsive, reactive environment, providing a scalable and comprehensive solution for training and evaluating next-generation autonomous driving policies. We additionally show preliminary results indicating that a world-action model (WAM) post-trained from OmniDreams achieves strong performance on the Physical AI Autonomous Vehicles NuRec dataset, surpassing the VLA-based Alpamayo 1.5 research policy model while using only 1/5 the total parameters. These results highlight the potential for a real-time world model like OmniDreams to also serve as a backbone for policy architectures.

cs.CV · cs.AI · cs.RO

版本更新 · v2arXiv:2608.07408

Addressable Memory for Video World Models

Xindi Wu, Sven Elflein, James Lucas, Olga Russakovsky, Laura Leal-Taixé, Despoina Paschalidou, Jonathan Lorraine, Aljoša Ošep

原文摘要

We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames. However, we find that models can no longer reliably address stored content once rollouts extend beyond the training horizon, because temporal Rotary Positional Embedding (RoPE) offsets can exceed the training range and the model struggles to retrieve the relevant visual information through attention. Moreover, naively compressing the cache in the RoPE-rotated space degrades memory by averaging keys with incompatible positional phases. To address this, we propose WorldTrace, a training-free memory framework for long-horizon visual persistence. WorldTrace keeps compressed memory addressable by assigning each summary slot a distinct, in-distribution virtual position. Within this cache, WorldTrace uses the model's own attention to decide which observations to retain verbatim and which redundant ones to merge into compressed summaries, all within one bounded addressable memory bank. We evaluate this ability with LoopBench, a benchmark that tests whether a compressed cache can reconstruct a previously visited scene after a long detour. On LoopBench, WorldTrace improves average DINOv2 recall similarity by 32.6% over a sliding window at the same cache budget, extending visually persistent generation without retraining.

cs.CV · cs.LG

新论文 · v1arXiv:2611.13685

Ego Guidance: Enhancing Robot Policy Learning with Action-Free Human Egocentric Videos

Lin Long, Tianren Ma, Zhong Chu, Di Wu, Maosong Cao, Qixiang Ye, Junbo Zhao, Shanghang Zhang

原文摘要

In this paper, we investigate how human egocentric videos can benefit robot policy learning without action supervision. Building on a pretrained VLM, we propose Shared Prediction on Action and Representation (SPAR), an MoT architecture in which future visual state prediction can provide independent and complementary learning signals alongside action prediction. We find that representations learned from egocentric videos improve downstream performance on out-of-distribution robot tasks, with further gains as video data scales. We also study the effects of objective choices and data curation, providing insights into how to leverage action-free videos for scalable robot learning.

cs.RO · cs.AI · cs.CV

版本更新 · v3arXiv:2605.21489

Variance Reduction for Gradients from Diffusion Teachers

Jesse Bettencourt, Xindi Wu, Matan Atzmon, James Lucas, Jonathan Lorraine

原文摘要

Pretrained diffusion models serve as frozen teachers for pipelines such as text-to-3D, single-step distillation, and data attribution. The teacher gradients these pipelines consume are expectations over noise levels and Gaussian noise, estimated by Monte Carlo (MC). Each MC draw requires expensive upstream work (rendering, simulation, encoding), so estimator variance dominates compute cost. We introduce CARV, a compute-aware variance-accounting framework that casts these gradients as a classical two-stage sampling problem with asymmetric per-level costs. This motivates a hierarchical MC estimator that amortizes each expensive upstream computation by reusing it across cheap diffusion draws, with within-unit variance further reduced by timestep importance sampling (IS) and stratified inverse-CDF sampling. CARV delivers 2 to 3x effective compute multipliers on text-to-3D and data attribution without changing the objective. In text-to-3D, reuse provides most of the gain and IS with stratification adds about 25%. In single-step distillation, the same techniques cut gradient variance by an order of magnitude but do not improve downstream FID, marking the regime where MC variance is no longer the bottleneck.

cs.LG · cs.AI · cs.CV · stat.CO · stat.ML

新论文 · v1arXiv:2611.12139

BioMARS 2.0: a robotic biologist for formulating and adapting biological experiments

Yibo Qiu, Zan Huang, Yilin Qiao, Ziyang Ling, Yi Wang, Zhengyang Lu, Hangke Peng, Haoliang Ye 等 22 位作者

原文摘要

Biological experimentation is not reducible to a single optimization problem, but requires decisions at multiple levels of abstraction: translating scientific knowledge into experimental procedures, adapting culture conditions to measured phenotypes and selecting interventions that test biological hypotheses. Automating experimental execution does not, by itself, determine which experiments should be performed next or how they should change in response to biological feedback. Here we introduce BioMARS, a human-in-the-loop multi-agent robotic system that connects knowledge-guided experimental decision-making with robotic execution and biological feedback. At the procedural level, BioMARS generated literature-grounded protocols and traceable action plans, improving expert-reviewed protocol quality scores across four model backends. At the parametric level, BioMARS used image-derived phenotypes from robotic retinal organoid culture to select subsequent experimental conditions, with higher reported scores in later rounds of the three-round experiment. At the intervention level, BioMARS nominated drug-repurposing candidates from biomedical evidence and advanced six candidates to wet-lab testing by researchers. Together, these studies demonstrate feedback-driven robotic biological experimentation within a framework that supports decisions about experimental procedures, culture conditions and biological interventions.

cs.RO · q-bio.QM

新论文 · v1arXiv:2611.13020

ChipOmni: A General-Purpose AI Agent for Electronic Design Automation

Pengkun Wang, Rui Mao, Zhe Zhao, Dongting Xie, Haibin Wen, Song Xu, Di Wu, Xu Wang 等 12 位作者

原文摘要

Electronic design automation (EDA) workflows remain highly fragmented, requiring engineers to coordinate heterogeneous representations, specialised software tools, and iterative verification across multiple design stages. Although large language models have brought more general reasoning and code-generation capabilities to EDA, many existing approaches remain focused on isolated tasks and struggle to plan, verify, and repair designs autonomously within executable engineering environments. Here we introduce ChipOmni, a knowledge-enhanced, context-evolving AI agent framework for EDA. ChipOmni integrates multimodal understanding, dynamic planning, multi-agent collaboration, and verification-driven tool interaction into a unified autonomous system. By continually incorporating feedback from external engineering tools, the framework maintains an evolving task context, integrates domain knowledge, and iteratively refines intermediate designs. Across benchmarks for analog circuit, RTL, testbench, and formal-assertion generation, ChipOmni improves multiple task-specific measures over the evaluated baselines and solves all 30 AnalogCoder-Pro tasks. In a long-horizon case study, ChipOmni advances a natural-language RISC-V specification through three design levels to a micro-SoC GDSII layout that passes physical sign-off, without human intervention after initialization. Together, these results show that ChipOmni can coordinate verification-driven design across heterogeneous tasks and sustain long-horizon engineering workflows, advancing a shift from fragmented, tool-centred processes towards agent-centred, closed-loop systems.

cs.AI

版本更新 · v2arXiv:2610.23908

ContraSafe-VL: A Contrastive Safety Preference Dataset for Vision-Language Models

Di Wu, Yanyan Zhao, Xin Lu, Hao Yang, Taotao Zhang, Yunzhen Zhao

原文摘要

Vision-Language Models (VLMs) are increasingly deployed as general-purpose multimodal assistants, making multimodal safety alignment an important challenge. Safety depends on the interplay between textual and visual content, with visual context often playing a critical role. However, VLMs may fail to use visual information appropriately, either overlooking safety-relevant visual content or over-interpreting sensitive visual content, leading to unsafe responses or over-refusal. Existing multimodal safety alignment datasets largely follow the response-preference paradigm, which teaches models how to respond but provides limited supervision on how visual context should inform the safety judgment, making it difficult to balance safety and over-refusal. To address this limitation, we introduce \textbf{ContraSafe-VL}, a \textbf{Contra}stive \textbf{Safe}ty preference dataset for \textbf{V}ision-\textbf{L}anguage Models. For each fixed textual query, ContraSafe-VL constructs paired visual contexts that result in multimodal queries with different safety labels, providing direct supervision for how visual context should inform multimodal safety judgments. It further provides response preference pairs based on harmlessness and helpfulness to encourage models to generate responses that are both safe and helpful. Experiments across three VLM architectures and multiple benchmarks demonstrate that training with ContraSafe-VL improves cross-modal safety recognition and achieves a better safety--over-refusal trade-off while preserving general multimodal capabilities. The dataset is available at https://github.com/pikepokenew/ContraSafe-VL

cs.CV

新论文 · v1arXiv:2611.07238

How Do AI Agents Waste Your Money?

Huimin Zeng, Yuxuan Lu, Jesse Cai, Eric Hanchen Jiang, Di Wu, Po-Nien Kung, Wenbo Hu, Ziyi Wang 等 11 位作者

原文摘要

AI agents may consume massive tokens across a wide range of tasks, but how many of those tokens are really necessary? Although prior work has shown that agents can incur unexpectedly high token costs, we still lack a systematic way to identify and measure token waste. In this work, we introduce a unified framework for measuring token waste across heterogeneous agent systems. Our framework records and normalizes complete agent trajectories, identifies removable spans using an LLM-as-a-Judge (LLMaJ), and maps the identified text spans back to the original trajectory for token-level measurement. We validate the identified waste through direct interventions by removing marked spans, resuming agent execution, and measuring changes in task outcomes and subsequent actions. In online pruning experiments, we remove 41-46% of the model's reasoning while largely preserving task performance across two distinct agent benchmarks. Using this framework, we analyze agents across multiple settings. Our analysis shows that token waste has a system-level structure that aggregate token usage alone cannot reveal. First, waste varies more across tasks and agent settings than across models. Second, reasoning and visible execution can exhibit different waste patterns. Third, different harnesses can introduce distinct sources of inefficiency even under the same model and task. Overall, our framework transforms token waste into an actionable optimization signal, enabling researchers and practitioners to train more efficient models, design better reasoning strategies, and optimize agent harnesses toward reducing unnecessary computation rather than merely reducing token usage.

cs.CL

版本更新 · v2arXiv:2608.07163

Rate-Fidelity Control for Wide-Area Quantum Links

Connor Clayton, Cory Nunn, Quinn Carmack, Wayne McKenzie, Anne Marie Richards, Xiaodi Wu, Bobby Bhattacharjee

原文摘要

Quantum network links must distribute entanglement at high rates while satisfying application-specified fidelity demands. However, wide-area deployed fiber links suffer from polarization drift which destabilizes end-to-end fidelity and forces periodic compensation. Current deployments often use active stabilization with fixed control policies, and improvements generally stem from advances in quantum hardware. Meanwhile, software control remains relatively underexplored. Here, we formulate quantum link operation as a joint control problem over tunable rate-fidelity tradeoffs and uncontrollable link drift. From this framework, we construct a link control protocol that dynamically adapts source pump power and polarization compensation to maximize entanglement distribution rate subject to a minimum fidelity constraint. We evaluate the protocol through trace-driven simulations driven by data from a 64 km deployed optical fiber. Compared with optimized static policies, our adaptive controller improves mean entanglement distribution rate by 14% over a 24 hour trace, without requiring any offline policy optimization. Our results show that software-based physical layer control can provide a practical mechanism for improving near-term quantum link performance without requiring additional quantum hardware.

quant-ph · cs.NI

版本更新 · v3arXiv:2610.23479

HexaShell: A Universal Harness for Robot Coding Agents in Simulation and the Real World

Hongcheng Gao, Jianshu Zeng, Alex Zhou, Shijia Ge, Xuan Shangguan, Yazhe Wang, Yexing Wan, Zelin Zheng 等 16 位作者

原文摘要

Agents built on vision language models (VLMs) now control robots by writing code, but the strongest of them refine task-specific code over many rounds of trial and revision. Such code tends to overfit the benchmark on which it was tuned, can exploit the benchmark's shortcuts, and is costly to carry over to a new benchmark or robot. We present HexaShell, a thin, task-agnostic harness designed to test how far general tools can go instead. We design a simple and complete set of 14 basic tools, 4 for motion, 5 for perception and 5 for state, which the agent calls in one Python cell per turn. Perception pairs SAM 3, which segments an object from a few words or a click, with NumPy and OpenCV geometry that turns its outlines in several cameras, or a depth image, into its position, size and grasp angle. The API, agent loop and sandbox are shared across all tasks; a new simulator or robot needs only an adapter of 350 to 1,450 lines and a prompt describing its world, and the only task-specific input is an optional skill of about a page of guidance. The same code runs on four simulated benchmarks, built on three simulators with two kinds of arm, and on real robots. With GPT-6-Astra and no task-specific input, HexaShell reaches success rates of 69.9% on RoboDojo, 59.3% on RoboCasa365, 78.3% on LIBERO-PRO and 82.2% on RoboTwin 2.0. With task skills, it reaches 85.0% (score 88.8), 85.6%, 96.7% and 96.8%, respectively, above the best published result we are aware of on each benchmark. The RoboCasa365 result is listed first on its leaderboard. On real dual-arm robots, HexaShell succeeds in 76 of 90 episodes across nine tasks.

cs.RO

版本更新 · v5arXiv:2403.15191

Your Trust, Your Terms: A General Paradigm for Near-Instant Cross-Chain Transfer

Di Wu, Jingyu Liu, Xuechao Wang, Jian Liu, Yingjie Xue, Kui Ren, Chun Chen

原文摘要

Cross-chain transactions today remain slow, costly, and fragmented. Existing custodial exchanges expose users to counterparty and centralization risks, while non-custodial liquidity bridges suffer from capital inefficiency and slow settlement; critically, neither approach guarantees users a unilateral path to recover assets if the infrastructure fails. We introduce the Delegated Ownership Transfer (DOT) paradigm, which decouples key ownership from value ownership to enable secure, high-performance cross-chain payments. In DOT, a user deposits funds into a sandboxed on-chain Temporary Account (TA) (value ownership) while delegating its private key (key ownership) to an abstract Trusted Entity (TE). Payments and swaps are thus reframed as near-instant, off-chain ownership handoffs. Security follows from dual guarantees: the TE's exclusive control prevents double-spending, while a pre-signed, unilateral recovery transaction ensures users retain ultimate authority over their assets. Building on this foundation, we design a novel off-chain atomic swap that executes optimistically in near real time and remains fair even if the TE fails. We formalize the security of DOT in the Universal Composability framework and present two concrete instantiations: a high-performance design based on Trusted Execution Environments (TEEs) and a cryptographically robust variant leveraging threshold cryptography. Our geo-distributed prototype shows that cross-chain payments complete in under 16.70 ms and atomic swaps in under 33.09 ms, with costs fully decoupled from Layer-1 gas fees. These results provide a practical blueprint for building secure, efficient, and interoperable cross-chain payment systems.

cs.CR · cs.DC

新论文 · v1arXiv:2611.04772

TactiNavi: Serving and Revising an LLM Game Coach with Explicit Strategy Conditions

Qi Liu, Xiaoyang Yuan, Zhuomeng Zhang, Yubin Ruan, Xinyi Mou, Wenjin Wang, Hanying Jiao, Di Wu 等 12 位作者

原文摘要

A deployed LLM coaching agent answers requests whose correct response depends on player state and game version, so advice that is right for one player can be wrong for the next. We describe TactiNavi, the serving system behind the LLM coach of a commercial open-world game, which makes strategy applicability an explicit artifact shared by offline compilation, online execution, failure diagnosis, and release. An offline compiler turns versioned game evidence and expert guidance into strategy packages with explicit prerequisites, the serving plane evaluates those prerequisites as three-valued conditions over structured player state and records decision traces, and a control plane uses the resulting condition-rule dependencies to validate revisions on held-out traffic before release. In a retrospective evaluation of 1,122 logged coaching turns from three deployment periods, condition-bearing packages raise correctness from 57.9% to 82.0% over atomic facts and reduce strategy misapplication under changed player state from 18.1% to 10.4%, while trace-based claim verification reaches 86.4% precision at a median reply latency of 2.07 s. The deployment also showed that most apparent fixes are generation noise, because an unchanged-system rerun recovers 38.4% of failing turns and only one of 15 shipped revision units passes the release checks retrospectively. We distill these results into lessons on treating applicability as a first-class serving object, sizing traces for later diagnosis, and building the null model into the release path.

cs.AI

新论文 · v1arXiv:2610.40560

FARMS:面向自动化计算科学的可验证基础

FARMS: A Verifiable Foundation for Automated Computational Science

Di Wu, Ling Liang, Haizhao Yang

AI 速读 基于摘要

作者提出 FARMS,将计算数学知识转化为可供 AI 解释与复用、并带有显式保证的“计算知识”基础。

cs.AI · cs.LO

查看原文摘要

Automated computational science could accelerate discovery by selecting, adapting and developing numerical methods. This prospect requires mathematical knowledge that AI systems can interpret and reuse with explicit guarantees. Here we present FARMS, a faithful and efficient foundation that transforms computational mathematics into AI-ready computing knowledge. FARMS connects formal statements to source context, algorithmic meaning and quantitative guarantees through source preparation, reusable representations and semantic review. Across 171 targets in randomized numerical linear algebra and numerical partial differential equations, 157 were accepted by the pipeline, with mean estimated costs of US \$0.85-2.29 per target across sources. Lean-checked implications from explicit source premises connect selected statements to computational skills, illustrated by a heat-flow solve and wave-response compression. FARMS therefore supports an affordable, reusable knowledge foundation for trustworthy automated computational science.

版本更新 · v3arXiv:2311.03977

线性优化的量子中心路径算法

A quantum central path algorithm for linear optimization

Brandon Augustino, Jiaqi Leng, Jialu Bao, Giacomo Nannicini, Tamás Terlaky, Xiaodi Wu

AI 速读 基于摘要

提出一种通过量子模拟中心路径、直接处理非线性互补方程来求解线性优化问题的量子算法。

quant-ph · cs.DS · math.OC

查看原文摘要

We propose a novel quantum algorithm for solving linear optimization problems by quantum-mechanical simulation of the central path. While interior point methods follow the central path with an iterative algorithm that works with successive linearizations of the perturbed KKT conditions, we perform a simulation working directly with the nonlinear complementarity equations. Using a two-stage quantum eigenpath traversal schedule, this approach yields an algorithm for solving linear optimization problems involving $m$ constraints and $n$ variables to $\varepsilon$-optimality using $\widetilde{O}\!\left((m+n)^{3/2}\,\varepsilon^{-1}+(m+n)^{1/2}\,\varepsilon^{-3/2}\right)$ queries to an oracle that evaluates a potential function. In the standard gate model (i.e., without access to quantum RAM), our algorithm can obtain $\varepsilon$-precise solutions to LO problems using at most $$\widetilde{O}\!\left(\left[\frac{(m+n)^{3/2}}{\varepsilon} + \frac{(m+n)^{1/2}}{\varepsilon^{3/2}}\right] \cdot \mathrm{nnz}(A)\right)$$ elementary gates, where $\mathrm{nnz}(A)$ is the total number of non-zero elements found in the constraint matrix.

新论文 · v1arXiv:2610.37645

Multi-State Linear Attention with Generalized Second-Order Routing

Hee Seung Hwang, Sanghyuk Chun, Xindi Wu, Olga Russakovsky, Zhiwei Deng

原文摘要

Self-attention plays a key role in long-sequence modeling, but its quadratic time complexity fundamentally limits the scaling of Large Language Models. Recently, Multi-State Linear Attention (MSLA) mechanisms have been proposed to make sequence modeling more efficient by splitting the context into segments and compressing each in its own memory state. MSLA aggregates the information extracted from each memory state using only the mean alignment between a query and each segment's keys, ignoring how the alignment is distributed within the segment. In order to model the relevance of a segment to a query more comprehensively and incorporate the variance of the alignment in the aggregation, we propose MERLIN (MomEnt Routing for multi-state LINear attention), a method that tracks the first and second moments of each segment's keys. Using the moments of keys, a query can recover both the mean and the variance of its alignment with each segment to perform a more content-aware aggregation of per-state readouts. Experiments on multi-state variants of Gated DeltaNet-1.3B and Mamba-2-780M show that MERLIN consistently outperforms existing aggregation methods on various long-context tasks. In particular, MERLIN outperforms baselines on RULER needle-in-a-haystack and long-context QA (+8.3% for Gated DeltaNet-1.3B and +7.0% for Mamba-2-780M) and diverse subtasks in LongBench (+13.5% and +12.0%). It even outperforms baselines that consume 4x more memory. MERLIN provides a simple and general routing mechanism for improving long-context capabilities of MSLA models.

cs.CL

版本更新 · v2arXiv:2602.16704

Reinforced Fast Weights via Next-Sequence Prediction

Hee Seung Hwang, Xindi Wu, Sanghyuk Chun, Olga Russakovsky, Zhiwei Deng

原文摘要

Fast weight architectures offer a promising alternative to standard transformers for long-context modeling by replacing the KV-cache with a recurrently updated fixed-size memory. Despite this architectural shift, they are typically trained with the same next-token prediction (NTP) objective as standard transformers. This creates a mismatch: fast weight models rely on an evolving memory state to support future predictions, while NTP provides only token-level supervision for the immediate next token. We address this mismatch with next-sequence prediction (NSP), a sequence-level extension of NTP that trains models to produce coherent multi-token continuations from their recurrent memory state. To optimize this sequence-level objective, we propose ReFINE (Reinforced Fast weIghts via Next sEquence prediction). ReFINE selects informative token positions based on prediction entropy, generates multi-token rollouts, assigns sequence-level rewards, and optimizes the model with Group Relative Policy Optimization (GRPO). ReFINE is applicable throughout the training lifecycle of pre-trained language models: mid-training, post-training, and test-time training. Experiments on LaCT-760M and DeltaNet-1.3B show that ReFINE consistently outperforms NTP-based supervised fine-tuning in needle-in-a-haystack retrieval, long-context question answering, and diverse tasks in LongBench. ReFINE provides an effective and versatile framework for improving long-context modeling in fast weight architectures.

cs.CL

新论文 · v1arXiv:2610.35385

EmbodiedLab: Benchmarking Embodied Agents That Act to Know

Hongcheng Gao, Zelin Zheng, Alex Zhou, Jay Zhu, Shijia Ge, Yazhe Wang, Xiping Li, Jianshu Zeng 等 21 位作者

原文摘要

Embodied agents are expected to accomplish real-world goals by deciding for themselves how and when to interact with their surroundings. For many such goals, changing the physical state of the world is the means rather than the end: the agent changes the state of a system through interaction, observes the feedback, and explores until it either achieves the goal itself (e.g., discovering physical laws) or learns what the goal requires; it acts to know. Manipulation benchmarks stop at acting to change, with the target state given; scientific discovery benchmarks evaluate knowing but replace physical experimentation with symbolic actions or numerical queries. We introduce EmbodiedLab, a benchmark in which a robot must act to know. Quantitative science experiments make this setting controllable: the parameters of the system are resampled for every instance, so the result cannot be known in advance, yet it can be scored exactly. Across 30 experiments in five disciplines on 14 apparatus platforms, the agent receives an objective and the apparatus, chooses its own procedure, and operates a physics-based simulated laboratory, reading the instruments through its cameras. Evaluation checks what the agent came to know, grounded in readings recorded during the episode, as well as the physical state the task requires; every experiment is verified to be solvable. We evaluate six frontier models in their developers' coding agents with native observation and control, with added perception and motion planning, and with manipulation skills distilled from the strongest agents. With native control, even the strongest agent succeeds less than half the time; for every agent, most failures arise in interacting with the apparatus, and manipulation skills help weaker agents more than perception and planning. The benchmark and its evaluation code are available at https://github.com/HexaFuture/EmbodiedLab.

cs.RO

版本更新 · v3arXiv:2602.16444

RoboGene: Diversity-Driven Agentic Task Generation Framework for VLA Pre-training

Yixue Zhang, Kun Wu, Zhi Gao, Zhen Zhao, Pei Ren, Zhiyuan Xu, Fei Liao, Xinhua Wang 等 15 位作者

原文摘要

The pursuit of general-purpose robotic manipulation is hindered by the scarcity of diverse, real-world interaction data. Unlike large-scale web vision-language data, robotic data collection incurs prohibitive physical costs. The key challenge is thus not merely to collect more robot data, but to obtain informative training data that broadens behavioral coverage across objects, scenes, and skills. Yet automatically curating task proposals to maximize the utility of collected data remains under-explored. We introduce RoboGene, an agentic framework for generating diverse, informative manipulation tasks across single-arm, dual-arm, and mobile robots. RoboGene combines (1) diversity-driven sampling for broad task coverage, (2) agentic self-reflection for task-quality assessment, and (3) human-verified feedback memory for execution-grounded validation and continual refinement. Through quantitative analysis and large-scale real-world experiments, we collect 18k trajectories and introduce metrics for task feasibility and diversity. RoboGene significantly outperforms frontier foundation models, including GPT-4o and Gemini 2.5 Pro. VLA models trained on RoboGene-generated data achieve higher success rates and stronger generalization, highlighting the value of high-quality task generation. Project page: https://robogene-boost-vla.github.io/. Datasets: Hugging Face (https://huggingface.co/datasets/X-Humanoid/RoboGene) and ModelScope (https://modelscope.cn/datasets/X-Humanoid/RoboGene_tasks).

cs.RO · cs.AI · cs.LG

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1192ACL Anthology · ACL 2026

VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval

Di Wu, Yixin Wan University of California, Los Angeles, Kai-Wei Chang University of California, Los Angeles and Amazon

原文摘要

Text-to-image retrieval (T2I retrieval) remains challenging because cross-modal embeddings often behave as bags of concepts, underrepresenting structured visual relationships such as pose and viewpoint. We proposeVisualize-then-Retrieve (VisRet), a retrieval paradigm that mitigates this limitation of cross-modal similarity alignment. VisRet first projects textual queries into the image modality via T2I generation, then performs retrieval within the image modality to bypass the weaknesses of cross-modal retrievers in recognizing subtle visual-spatial features. Across four benchmarks (Visual-RAG, INQUIRE-Rerank, Microsoft COCO, and our new Visual-RAG-ME featuring multi-entity comparisons), VisRet substantially outperforms cross-modal similarity matching and baselines that recast T2I retrieval as text-to-text similarity matching, improving nDCG@30 by 0.125 on average with CLIP as the retriever and by 0.121 with E5-V. For downstream question answering, VisRet increases accuracy on Visual-RAG and Visual-RAG-ME by 3.8% and 15.7% in top-1 retrieval, and by 3.9% and 11.1% in top-10 retrieval. Ablation studies show compatibility with different T2I instruction LLMs, T2I generation models, and downstream LLMs. VisRet provides a simple yet effective perspective for advancing in text-image retrieval. Our code and the new benchmark are publicly available at https://github.com/xiaowu0162/Visualize-then-Retrieve.

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.1495ACL Anthology · ACL 2026

Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge

Xin Sun, Di Wu, Sijing Qin Hitotsubashi University, Isao Echizen National Institute of Informatics, Abdallah El Ali Utrecht University and Centrum voor Wiskunde en Informatica, Saku Sugawara University of Tokyo and National Institute of Informatics

原文摘要

Large language models (LLMs) are increasingly used as automated evaluators (LLM-as-a-Judge). This work challenges its reliability by showing that trust judgments by LLMs are biased by disclosed source labels. Using a counterfactual design, we find that both humans and LLM judges assign higher trust to information labeled as human-authored than to the same content labeled as AI-generated. Eye-tracking data reveal that humans rely heavily on source labels as heuristic cues for judgments. We analyze LLM internal states during judgment. Across label conditions, models allocate denser attention to the label region than the content region, and this label dominance is stronger under Human labels than AI labels, consistent with the human gaze patterns. Besides, decision uncertainty measured by logits is higher under AI labels than Human labels. These results indicate that the source label is a salient heuristic cue for both humans and LLMs. It raises validity concerns for label-sensitive LLM-as-a-Judge evaluation, and we cautiously raise that aligning models with human preferences may propagate human heuristic reliance into models, motivating debiased evaluation and alignment.

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.1822ACL Anthology · ACL 2026

On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied Planning

Di Wu, Jiaxin Fan tongji university, Chloe Gu, Guanbo Wang, Wei Yin, Wenhao Li Tongji University, Bo Jin Tongji University

原文摘要

Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and verbal goals. While recent vision-language models (VLMs) excel at static perception tasks, they struggle in interactive environments. Reinforcement learning (RL) offers a natural way to address this limitation, yet online RL approaches suffer from costly interaction and sparse rewards in embodied settings. This paper introduces ORBIT, an On-policy Reinforcement fine-tuning (RFT) framework with offline rewards for EmBodIed Task Planning, that preserves the generalization benefits of RFT while addressing the challenges of costly interaction and sparse rewards, supported by solid theoretical guarantees. Our approach is evaluated on EmbodiedBench, a recent benchmark for interactive embodied tasks, covering both in-domain and out-of-domain scenarios. Experimental results show that ORBIT achieves SOTA performance on EB-ALFRED, outperforming all closed-source and online-RL-based methods, while being substantially more efficient in training speed and computational cost, remaining robust to sub-optimal expert trajectories, and exhibiting strong generalization to unseen environments. We released all code and data at https://github.com/mail-taii/Reinforced-Reasoning-for-Embodied-Planning.

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