跳到正文
研踪PaperTrail

论文库

检索计算机领域论文，按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-15 10:52 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-14 12:07 — 2026-11-15 12:07（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：2026-11-15 10:52最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 180 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-15 10:50（北京时间）
新论文 · v1arXiv:2611.16840

Kosmo-GFM: A Production-Ready Geometry Foundation Model

Sheng Tang, Shengzhe Wei, Tiancheng Chen, Wenhua Jin, Xinyang Lu, Tinghao Jiang, Shuoxuan Feng, Yupeng Liu 等 32 位作者

原文摘要

We present Kosmo-GFM, a scene reconstruction system that integrates a geometry foundation model (GFM), a pose optimization engine (PoseEngine), and reconstruction-derived supervision from KosmoWorld. GFM predicts camera parameters, depth, cross-view correspondences, and dynamic 3D points from images and videos. PoseEngine combines these predictions with geometric optimization to recover scene-level camera poses and geometry for downstream 3D and 4D Gaussian Splatting. KosmoWorld generates images and geometric supervision from reconstructed real-world scenes to improve GFM's geometric predictions. On the Sparse and Medium subsets of SpatialBench, GFM achieves the lowest absolute relative depth error and the highest relative-pose AUC at 5 degrees among the compared methods. It also achieves the lowest mean endpoint errors for dynamic points and scene flow across the five evaluated datasets. Across 34 scenes completed by all compared reconstruction systems, PoseEngine achieves the highest scene-averaged pose AUC at thresholds of 1, 3, and 5 degrees, with a cumulative runtime of 14.07 hours, approximately 20% of GLUEMAP's 69.67 hours. PoseEngine Flash provides a further accuracy-efficiency trade-off, with a measured mixed-precision runtime of 2.62 hours, approximately 4% of GLUEMAP's runtime. Separate scaling experiments show generally favorable trends with increased data, model computation, and training budgets. These results support the use of learned geometric priors within a scene-level reconstruction pipeline.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16591

Singularity-Bench: Can Agents Build Agents?

Yang Zhou, Krish Agarwal, Zhuoming Chen, Zerui Wang, Zhenyu Zhang, Wenshuang Li, Xinpeng Wei, Zhichen Zeng 等 19 位作者

原文摘要

Frontier AI agents increasingly succeed on realistic, long-horizon tasks and are beginning to improve the systems through which they operate. Yet existing benchmarks often restrict agents to narrow action spaces, use simplified environments, or rely on verification methods that are unreliable for evaluating arbitrary agent-generated systems. We introduce Singularity-Bench, an open-ended benchmark for autonomous AI development with six end-to-end tasks spanning pre-training, mid-training, post-training, inference, the agent harness, and cluster orchestration. Each task requires agents to implement core systems from a minimal starting point and evaluates them against mature human-engineered baselines on identical hardware. Additionally, through extensive red-teaming covering 9 of the 10 categories in the OWASP Top 10 for Agentic Applications, we expose reward-hacking vulnerabilities in the conventional Harbor framework and develop Breakwater, an extension of Harbor that blocks all attacks tested in our study. Across 11 agents built from 7 frontier models and 2 harnesses, Opus 5.5 with Claude Code matches or outperforms the human baseline on all six tasks with a Singularity-Index of 1.25, suggesting it may have the skills needed to reach the singularity. The remaining agents average only 0.58. Our vision is for Singularity-Bench to track how much of AI development agents can already automate and when they may transition from assisting to taking end-to-end responsibility for building stronger successors.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.08286

Interactive Visual Gym: Evaluating Visual Interaction Models with Simulated Users in Interactive Worlds

Chenhao Zheng, Zixian Ma, Kai Li, Kanchana Ranasinghe, Jieyu Zhang, Artemis Panagopoulou, Weikai Huang, Jianxu Shangguan 等 14 位作者

原文摘要

Visual interaction models that support users during ongoing physical tasks require evaluation in closed loop, where assistant responses can change subsequent user behavior and task outcomes. Existing benchmarks largely rely on offline replay and therefore cannot capture these effects. We introduce Interactive Visual Gym, a framework for closed-loop evaluation and training of visual interaction models through joint simulation of executable task environments and human users. We contribute three simulators that recreate everyday tasks and human-aligned action spaces across cooking, household manipulation, and mobile-interface domains, together with a persona-conditioned user simulation harness that collaborates with the assistant while incorporating controlled execution errors and other out-of-plan behaviors. We instantiate the framework as IVG-Bench, a benchmark with 315 interaction scenarios. Evaluating state-of-the-art VLMs as visual interaction models reveals substantial limitations: the best-performing model, Claude Opus 5.5, completes only 53.5% of tasks within the time limit, exhibits significant weaknesses in factual grounding and actionable guidance, and is often too slow to prevent errors when response latency is considered. We verify our evaluation protocol with a human study which finds 78.5% agreement between our interaction-quality metric and participant preferences. We further show that the environments provide useful learning signals: in a proof-of-concept GRPO experiment, closed-loop training improves both task success and interaction quality for Qwen3.5-4B model in our cooking environment.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16159

From Tokens to Behaviors: Rethinking Generative Recommendation for User Trajectory Prediction

Jiaqi Wang, Hanchen Yang, Hengyu Zhang, Hongxu Ma, Wenqi Rao, Hongyang Wang, Zhongbo Sun, Renliang Qian 等 15 位作者

原文摘要

User behavior trajectory prediction (UBTP) aims to capture how a user's needs evolve over time by predicting the sequence of future interactions from that user's interaction history. Recent generative recommendation (GR) methods address this task through autoregressive generation of semantic IDs (SIDs). However, serial SID decoding couples token generation with behavior state transitions and requires multiple dependent steps per interaction. Discrete item feedback overlooks predictive uncertainty, and teacher-forced training leaves a training-inference gap in trajectory generation. To address these limitations, we propose TraGR, a behavior-aware generative recommendation framework that aligns generation, feedback, and learning with successive user behaviors. Its behavior-level architecture predicts SID tokens in parallel within each interaction and models behavioral transitions through recurrent state updates, with joint SID and item-level supervision. Probability feedback combines the selected behavior with a probability-weighted summary of alternatives to guide subsequent predictions. Relation-aware trajectory learning incorporates collaborative transition signals and later credit assignment into training on model-generated trajectories. Experiments on four public datasets demonstrate that TraGR consistently outperforms state-of-the-art baselines across different prediction horizons. Code: https://github.com/CalmaQi/GR4UBT.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16149

HyperPage: Learned Page Layouts for Disk-Resident Graph Vector Indexes

Xinyu Zhang, Jingze Li, Baihua Zheng, Weiwei Sun

原文摘要

Disk-resident graph indexes such as DiskANN store each vector with its graph edges as one record on SSD pages. A search needs the page of every record it expands, so its page reads depend on the page layout, that is, which records share a page. Search agents trained with reinforcement learning query one such index run after run, and every graph traversal can be logged with the records it expands. We therefore use the logs of a finished run to lay out the index for a declared memory budget, so later runs read fewer pages. In contrast, existing layouts such as Starling and MARGO are computed from the graph and vectors and use no logs. Learning a layout from logs is challenging, because the logs must stay valid under every layout, the saving depends on what the budget caches, and the best layout is NP-hard to find. Our key observation is that DiskANN-style search routes on in-memory codes and the records it expands, never on their page-mates. As a result, the logged traversals price every layout by replay, and cached records add no page reads. Accordingly, we propose HyperPage, which first builds layouts for the declared budget on the logged traversals of uncached records. It then selects one layout, together with the budget split between hot records and a page cache, by replaying validation steps. In addition, a Lagrangian lower bound shows how far a layout may be from the optimum. We learn from one Search-R1 agent run and test on a later run with a different reward, over 1M and 21M passages. Across seven cache budgets, HyperPage reads 5.2% to 21.2% fewer pages than MARGO, and no compared layout reads fewer. The advantage is largest when the cache is small. For example, at 1% of the 1M index, MARGO needs nearly 3 times the budget to read as few pages. On the 21M index, HyperPage also cuts search time per step by up to 10.4%. The saving holds for a second agent model and a second corpus.

cs.DB · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16148

Calibrated Early Termination with Bounded Optimality Gaps for Constrained Vector Search

Xinyu Zhang, Jingze Li, Baihua Zheng, Weiwei Sun

原文摘要

Vector search over learned embeddings is the retrieval layer of recommendation and retrieval-augmented generation, and many applications cap how many answer items one category may contribute. Graph indexes answer a query by best-first traversal, and where it stops determines its cost and whether its answer is exact. We study early termination for such constrained $k$-nearest-neighbor ($k$-NN) queries, with plain $k$-NN as a special case, and seek the cheapest stopping rule whose answer is exact with probability at least $1-\varepsilon$. Learned early-termination methods instead target average recall, which does not guarantee exact answers. Multiple testing can calibrate any parameterized stopping rule to our target, but it cannot tell how much a better rule with the same risk and observations would save. Answering this needs a lower bound on the optimum of a rule family too large to enumerate, valid for the query population. Our key idea is to declare the observations a rule may use and to consider every rule monotone in them. Risk-constrained stopping then becomes a linear program over an order polytope, whose Lagrangian minimizers form a nested chain of staircase rules computed exactly by dynamic programming. Fixed-sequence binomial tests along this chain calibrate our rule, CaST, whose failure probability is at most $\varepsilon$ with confidence $1-δ$. Lagrangian weak duality bounds the optimum of the declared class from below at all risk levels at once, without a union bound over the rules. On two datasets of one million items each, CaST replayed on logged searches costs at most 1.132 times the class optimum for risk levels from 0.03 to 0.10, at 95% joint confidence per setting. Larger savings thus need a rule outside the class. At a common risk target on held-out queries, CaST is faster than every other calibrated rule we time, which take 4.8% to 45.5% more mean time.

cs.DB · cs.IR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15789

VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in Blender

Yuzhe Chen, Muxi Diao, Lele Yang, Wenbin Xu, Xuyang Liu, Qile Su, Changyi Liu, Jiankang Chen 等 22 位作者

原文摘要

Controllable real-world video generation models can condition on a rendered graybox proxy video, which fixes layout, motion and camera. Coding agents can build such videos by reconstructing a 4D scene in Blender, yet no benchmark checks both these videos and the long, multi-shot scenes behind them. We introduce VibePrevisBench, a benchmark for 4D scene reconstruction: an agent turns a brief into an executable 4D scene and renders its proxy video. Its 242 tasks span four input kinds, including scripts, photos, continuations, and reference videos. Each delivery is scored along two evaluation dimensions. Rule-based Scene Check re-runs the code and compares the exported 4D scene with hidden ground truth facts in nine dimensions. VLM-based Screen Check asks a VLM judge whether the facts that pass can be recognized in the proxy video. We analyze the evaluation results and trajectories of 11 frontier coding agents and identify three key observations. First, multimodal understanding separates the agents, especially in understanding space and camera motion. Second, all agents seem to already master basic camera work and staging, and fail at challenging requests. Third, agents inspect their own renders but fail to correct their errors. Agents thus need better visual understanding of space and camera, explicit checks for challenging requests, and item-by-item verification of renders against the brief.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15167

AMARA: Compiler-Driven Accelerator Architecture Design for Graphical Probabilistic Sampling

Zhan Chen, Yihan Fu, Wenshuo Yue, Daijing Shi, Chenyun Yin, Mingrui Wu, Xiangyu Zhang, Yun Liang 等 9 位作者

原文摘要

Sampling methods are fundamental primitives for training and inference on probabilistic models. However, practical deployment of sampling algorithms such as Markov Chain Monte Carlo (MCMC) remains difficult on general-purpose processors. Existing hardware accelerators improve sampling efficiency, but they are typically specialized for a narrow class of models, graph topologies, or update schedules, making it difficult to support the diverse workloads used in real applications. This paper presents AMARA, an end-to-end compiler-driven accelerator framework for probabilistic sampling on arbitrary probabilistic graphical models. AMARA introduces MCMC-IR, a domain-specific intermediate representation that separates local factorized computation from global update dependencies. Based on this representation, the compiler performs architecture-aware partitioning, scheduling, and memory-access optimization to expose parallelism and reduce irregular graph communication. The optimized program is lowered to a compact ISA and executed on a programmable ASIC accelerator with specialized compute, sampling, and memory support. By co-designing the compiler and the architecture, AMARA bridges the gap between model generality and accelerator efficiency for practical MCMC-based probabilistic computing. We evaluate AMARA across representative workloads with different structures, including grid-structured and irregular energy-based models, and causal inference networks. The results show that AMARA supports a broad spectrum of discrete probabilistic models while achieving high sampling throughput and efficient hardware utilization. AMARA achieves an average of 6.1$\times$ (up to 16.3$\times$) higher sampling throughput than a JAX-GPU baseline on irregular workloads, and offers broader programmability than state-of-the-art accelerators.

cs.AR · cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15102

One Fabrication Is Enough: A Fake News Article Changes the Forecasts of LLM Forecasting Systems

Zeyu Zhang, Bradly C. Stadie

原文摘要

LLMs are increasingly used for forecasting, and the best forecasting systems retrieve news as evidence to strengthen their predictions. This also opens them to attack. We study the weakest attacker of this kind, who knows only the forecasting question and publishes fabricated news articles, with no access to the model, the retriever or its queries. We evaluate how far this attack reaches on stock questions and real prediction-market questions. Once the article is in the model's context, it reverses 74% to 82% of the forecasts that opposed it, on every frontier model we tested. The model cannot verify the fabrication and follows it anyway. Retrieval is the attack's entry point, and the systems built to retrieve well are the most exposed: the architectures of two leading deployed forecasting systems, whose agents search for every related article, retrieve the fabricated one in about 90% of runs. Accuracy cannot reveal this harm: the attacked forecaster is right when the attacker's direction turns out right and wrong otherwise, so its average accuracy barely changes while its forecasts follow the attacker's guess. We also propose a second attacker, who publishes two articles that argue opposite directions to make the forecaster unsure. The model does not hedge; it returns a confident forecast in a direction the attacker no longer controls. We then evaluate the two strongest published retrieval-time defenses, passage filtering and partitioned retrieval. Each stops the one-article attack but is bypassed by a one-prompt change to the attack. Together they stop both bypasses at four articles, but sixteen distorted copies beat them, and they change 29% of clean decisions and discard 39% of the genuine news. Partitioned retrieval also requires control of the retrieval index. Systems that search the open web have no such control and are left with the filter alone. For them, the attack still works.

cs.CR · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.16581

EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing

Panyu Zhang, Minseo Park, Soowon Kang, Tomiris Ismatzoda, Azizbek Mustafakulov, Otabek Najimov, Woohyeok Choi, Jumabek Alikhanov 等 10 位作者

原文摘要

We introduce a three-wave, in-the-wild multimodal dataset for affect sensing that integrates smartphone sensing, wearable sensing, and dense experience-sampling-method (ESM) labels collected annually from 2020 to 2022. The dataset supports moment-level affect modeling through a shared dimensional label core across all waves, with additional affective descriptors available in the third wave (D-3). We describe the resource in terms of study design, temporal density of in-situ labels, and sensing and label coverage across waves. To support evaluation within this resource, we define an initial three-setting benchmark spanning temporal prediction from within-user history, within-wave cross-user generalization, and cross-wave generalization in which each wave is treated as a separate dataset. Our benchmark results show that the strongest method family depends on the evaluation setting: supervised baselines perform best in the temporal setting, unsupervised domain adaptation is strongest overall in the within-wave cross-user setting, and domain generalization shows the strongest overall cross-wave performance, although its margin over strong baselines is modest. These findings indicate that robust mobile affective computing is constrained not only by label availability but also by substantial participant-level variability and realistic cross-wave differences inherent in longitudinal in-situ deployments.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2602.15342

SACS: A Code Smell Dataset using Semi-automatic Generation Approach

Hanyu Zhang, Tomoji Kishi

原文摘要

Code smell is a great challenge in software refactoring, which indicates latent design or implementation flaws that may degrade the software maintainability and evolution. Over the past of decades, the research on code smell has received extensive attention. Especially the researches applied machine learning-technique have become a popular topic in recent studies. However, one of the biggest challenges to apply machine learning-technique is the lack of high-quality code smell datasets. Manually constructing such datasets is extremely labor-intensive, as identifying code smells requires substantial development expertise and considerable time investment. In contrast, automatically generated datasets, while scalable, frequently exhibit reduced label reliability and compromised data quality. To overcome this challenge, in this study, we explore a semi-automatic approach to generate a code smell dataset with high quality data samples. Specifically, we first applied a set of automatic generation rules to produce candidate smelly samples. We then employed multiple metrics to group the data samples into an automatically accepted group and a manually reviewed group, enabling reviewers to concentrate their efforts on ambiguous samples. Furthermore, we established structured review guidelines and developed a annotation tool to support the manual validation process. Based on the proposed semi-automatic generation approach, we created an open-source code smell dataset, SACS, covering three widely studied code smells: Long Method, Large Class, and Feature Envy. Each code smell category includes over 10,000 labeled samples. This dataset could provide a large-scale and publicly available benchmark to facilitate future studies on code smell detection and automated refactoring.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14997

Same Task, Different Statement: When and How Reformulation Helps LLM Problem Solving

Wentao Zhang, Xiaoyu Zhang, Chengwei Liu, Yutao Hu, Tao Zhang, Junsheng Wu, Hongping Gan, Yang Liu

原文摘要

When people face a hard problem, they often restate it in a clearer way before solving it. We study whether the same habit helps large language models by rewriting the statement of a problem. A legal rewrite must keep the meaning, the constraints, and the correct answer unchanged. We test three kinds of rewrites. Decomposition makes hidden subgoals explicit. Typed Reformulation casts the task into a more suitable solving frame. Concept Reduction removes surface detail and exposes the task structure. We evaluate them on eight math, logic, and code benchmarks with eight models, all under the same chain-of-thought solving prompt. The effect is large but depends on the problem type. An oracle that picks the best rewrite after the fact raises accuracy by +27.6% on average. Yet no single rewrite helps every problem, and a mismatched rewrite can hurt. Still, the effect follows clear patterns. Each kind of rewrite fits certain problem types. A simple fixed rule learned from one set of problems transfers part of the gain to new problems. It gains +11.0% on the problems it chooses to rewrite, while blind rewriting loses 5.6% on a similar share of problems. Rewriting is therefore not a universal way to solve problems. The question is when and how to rewrite.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14949

RSI-PDEbench: A Benchmark for Self-Improving Agents in PDE Solving

Binghang Lu, Lang Cao, Changhong Mou, Yige Sun, Cindy Xiangrui Kong, Zheyuan Deng, Tian Yuan, Bing Hu 等 11 位作者

原文摘要

Identifying and solving partial differential equations (PDEs) from sampled solution data often requires substantial expert effort in equation discovery, coefficient estimation, and numerical solver configuration, especially under noise and distribution shifts. Can large language model (LLM) agents automate this workflow accurately and efficiently? To investigate this question, we introduce \bench{}, a benchmark of 1,001 cases spanning 42 equation templates, including both classical and fractional PDEs. It provides three evaluation settings: Full evaluates performance on noise-free solution data; Noisy tests robustness to Gaussian noise with an RMS equal to 50\% of the clean-signal RMS; and Hard-OOD tests challenging out-of-distribution generalization to unseen equation templates and shifted coefficient ranges. We further introduce RSI-PDE, a recursively self-improving agent harness that shortlists candidate equations by residual loss, uses relative $L^2$ feedback to refine coefficients and numerical solvers, and applies a validation gate to policy and memory updates. We compare RSI-PDE with single-run baselines and native agent harnesses (Claude Code or Codex) across four frontier models. Across the three settings, RSI-PDE improves the pass rate averaged across the four models by 106.5--181.9\% relative to single-run baselines and by 3.0--19.6\% relative to native harnesses, while reducing total recorded model calls by 46.9\% across the 12 model--setting pairs. These results highlight the potential of validated recursive self-improvement in LLM agents to advance scientific computing.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14908

Hy ASR 3.0 Technical Report

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

原文摘要

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

cs.CL · eess.AS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.02985

Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores

Zeyu Zhang, Bradly C. Stadie

原文摘要

The standard check for contamination in LLM backtests is simple: compare scores before and after the training cutoff. We show this check is uninformative. Four flagship models fail it on questions they cannot have memorized: every scored question resolved after their cutoffs. The reason is structural. Models legitimately know more about times near their cutoff, so recency mimics leakage, and we prove no passive backtest can separate the two from genuine skill. Measurement, not just detection, requires information from outside the backtest. We supply it in two forms. A known cutoff identifies leakage at the boundary; a matched clean control identifies it globally and yields a leakage-adjusted score. Under a convex-pull model, leakage concentrates on outcomes that surprised the crowd and that training covered well. Partial memorization gives a large part of the full inflation. In twin models with planted leakage, the estimators detect and localize it, track its dose, and return null on clean questions. On frontier models, the estimators detect one cutoff-localized signature. They find no significant leakage at the tested boundaries in five models with positive naive gaps. Backtests need not be discarded; they need one defensible reference.

cs.LG · cs.CL · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14487

Re-Search：通过双人提问游戏剖析大语言模型的研究构思过程

Re-Search: Dissecting LLM Ideation Through a Two-Player Questioning Game

Muhan Gao, Hangxiao Zhu, Xinqi Su, Yu Zhang, Daniel Khashabi, Kuan-Hao Huang

AI 速读 基于摘要

作者提出 Re-Search 基准，把研究构思改造成“二十问”式提问游戏，用来追踪大语言模型在二元反馈下逐步逼近论文核心想法的过程。

cs.AI

arXiv ↗PDF ↗
查看原文摘要

Research ideation is iterative: researchers refine their ideas step by step based on feedback. Yet existing evaluations obscure this search process, making it difficult to understand how LLMs explore the space of research ideas and what limits their progress. We introduce Re-Search, which adapts the format of Twenty Questions to research ideation: given only the research problem of a published paper, a model must rediscover the paper's core idea by asking yes-or-no questions. Built from 200 ICML 2026 papers, Re-Search tracks how a model's idea evolves as it asks questions and receives binary oracle feedback, isolating ideation from execution. Across six recent LLMs, nearly all progress happens within the first 30 of 100 questions, which largely decide how the game ends; after that, most models plateau. Through controlled interventions on the candidate questions and the hypothesis space, we find that the bottleneck is generation, not judgment: models recognize a good idea or a good question when one is offered, but often cannot produce it on their own. We further analyze the ideation traces and find that models fail by either over-exploiting one direction or over-exploring too many. These findings point to concrete design principles for autoresearch systems: since models can judge candidates they cannot produce, enriching the search with externally sourced ideas and questions may be more effective than improving any single model's generation ability.

新论文 · v1arXiv:2611.13807

Relaxing Cross-Modal Correspondence for Multimodal Remote Sensing Pretraining

Xianping Ma, Yu Zhang, Mingzhe Jiang, Wanxin Xie, Qing Zhu, Nan Xu, Xiaokang Zhang, Yuanxin Ye

原文摘要

Multimodal remote sensing pretraining commonly relies on exact instance-level correspondence across modalities, implicitly treating strictly paired observations as a prerequisite for learning transferable representations. In this work, we revisit this assumption by relaxing cross-modal correspondence from the instance level to the semantic level. We introduce Semantic Pairing (SemPair), a pairing-relaxed pretraining strategy that replaces exact instance pairs with class-consistent cross-instance pairs. To characterize the effect of correspondence relaxation, we formulate a latent-factor model that separates cross-modal dependence into shared semantic structure and instance-specific correlation, showing that SemPair preserves the former while marginalizing instance-specific cross-modal correlations in expectation. We further introduce Mixed Pairing (MixPair) as a controlled interpolation between semantic and exact pairing to study correspondence granularity along a continuous spectrum. Extensive experiments consistently show that SemPair achieves transfer performance comparable to exact pairing (ExaPair), while MixPair reveals a non-monotonic relationship between downstream transfer and the instance-pairing ratio. These results demonstrate that exact instance correspondence is not a prerequisite for effective multimodal remote sensing pretraining and establish cross-modal correspondence granularity as an important design dimension for transferable multimodal representation learning. More broadly, this finding suggests a practical route toward scaling multimodal pretraining with reduced dependence on costly instance-aligned data.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.06365

Transfer the Style, Not the Semantics: Mitigating Semantic Leakage in Image-Guided Stylization

Haojun Tang, Qiwei Lin, Tongda Xu, Wenda Zhao, Yian Zhao, Yu Zhang, Lida Huang, Yan Wang

原文摘要

Image-guided zero-shot style transfer enables training-free stylization of arbitrary content images using a reference style. Despite recent progress, existing methods commonly rely on self-attention manipulation to inject style information, which may transfer semantic content from the style image, leading to semantic leakage. In this work, we revisit this phenomenon from the perspective of key--value coupling in the self-attention of diffusion models. Our analysis shows that the native correspondence between style keys and values plays an important role in transferring semantic information from the style image. Motivated by this observation, we propose SuRe, a timestep-aware key--value regulation framework that mitigates semantic leakage by disrupting the native key--value correspondence while progressively restoring it for faithful style transfer. Specifically, we present value shuffle to decouple style keys and values while preserving the empirical distribution of the values, together with a progressive recoupling mechanism that gradually recouples them throughout the stylization process. Experiments against 18 representative methods demonstrate that SuRe maintains competitive style similarity while consistently improving content similarity across SD1.5, SDXL, SD3, and FLUX.1-dev, with natural generalization to multi-style transfer. The code will be publicly available at https://xinr-tang.github.io/SuRe-homepage/.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2611.05726

Do Language Models Know Which Constraints Belong Together?

Junbo Jacob Lian, Kaixuan Chen, Hanzhang Qin, Huiling Chen, Chaoyu Zhang, Chung-Piaw Teo

原文摘要

Dantzig--Wolfe reformulation strengthens the linear relaxation of a mixed-integer program by convexifying constraint families, and each candidate costs a column generation run. The choice is hard when families strengthen the bound only together, as in classical lot-sizing, network-design, and facility-location formulations. We prove that when an evaluation convexifies at most $s$ of $k$ families, methods that observe only bounds need of order $k^w$ evaluations to find a hidden group of $w$ families in the worst case. A prediction missing $e$ members reduces this to $Θ(k^e)$ through a staged search that need not know $e$. The orders extend to several groups, prices, and growing evaluation costs. We study two predictors: a lookahead at an optimal LP dual, which vanishes on groups whose families share no variable, and language models reading the model, verified by the staged search in JointDW. Such groups appear in three of ten MIPLIB-NL models whose bound can be improved and in all 59 benchmark instances. Given the coefficients of models with up to 16 families, one language model names a true group first in 249 of 252 answers. On the benchmark instances, decompositions chosen by language models from the text solve faster than those of GCG's detector.

cs.LG · cs.AI · cs.DS · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13578

POEM: Output-Relative Block-Sparse Attention for Long-Context Prefilling

Haoyi Wu, Yunkai Dang, Wanyu Zhang, Lei Wang, Wenbin Li

原文摘要

Large language models (LLMs) have shown strong capabilities across diverse applications, making both safety and utility essential for reliable deployment. Jailbreak attacks use diverse forms of adversarial prompting to bypass alignment safeguards and induce LLMs to generate harmful responses. Some representation-based defenses regulate internal activations using predefined steering directions or learned safety regions. However, adapting intervention to each input without a predefined representational target while limiting over-refusal remains a challenge. In this paper, we propose Target-free Entropy-guided Residual Modulation (TERM), an inference-time defense that uses prompt-calibrated attention entropy deviations to guide adaptive modulation of the model's own residual updates. Attention patterns vary across prompts and decoding steps, making raw entropy values difficult to interpret as a consistent signal for intervention. We therefore calibrate attention entropy against each prompt's own prefill baseline to establish an input-specific reference for reducing unnecessary intervention on benign requests. Adaptive scale normalization and temporal accumulation then account for differences in deviation scale and persistence to determine intervention strength. The resulting signal controls bounded scaling of the model's own residual updates, without relying on a predefined safety direction. We compare our method with seven defenses on seven jailbreak attacks and two over-refusal benchmarks across Llama, Qwen, and Gemma models, including Qwen3 models from 0.6B to 32B. Results show our method improves jailbreak robustness while maintaining low over-refusal on benign safety-sensitive requests with modest inference overhead.

cs.CR · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13577

TERM: Target-Free Jailbreak Defense via Entropy-Guided Residual Modulation

Yunkai Dang, Wanyu Zhang, Meiyi Zhu, Qi Fan, Tianyu Ding, Wenbin Li

原文摘要

Large language models (LLMs) have shown strong capabilities across diverse applications, making both safety and utility essential for reliable deployment. Jailbreak attacks use diverse forms of adversarial prompting to bypass alignment safeguards and induce LLMs to generate harmful responses. Some representation-based defenses regulate internal activations using predefined steering directions or learned safety regions. However, adapting intervention to each input without a predefined representational target while limiting over-refusal remains a challenge. In this paper, we propose Target-free Entropy-guided Residual Modulation (TERM), an inference-time defense that uses prompt-calibrated attention entropy deviations to guide adaptive modulation of the model's own residual updates. Attention patterns vary across prompts and decoding steps, making raw entropy values difficult to interpret as a consistent signal for intervention. We therefore calibrate attention entropy against each prompt's own prefill baseline to establish an input-specific reference for reducing unnecessary intervention on benign requests. Adaptive scale normalization and temporal accumulation then account for differences in deviation scale and persistence to determine intervention strength. The resulting signal controls bounded scaling of the model's own residual updates, without relying on a predefined safety direction. We compare our method with seven defenses on seven jailbreak attacks and two over-refusal benchmarks across Llama, Qwen, and Gemma models, including Qwen3 models from 0.6B to 32B. Results show our method improves jailbreak robustness while maintaining low over-refusal on benign safety-sensitive requests with modest inference overhead.

cs.CR · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06788

Integrated Identity Protection for Semantic Communications in Embodied IoT Systems

Yu Zhang, JingQi Liu, Shuangrui Zhao, Yuanyu Zhang, Yulong Shen, Xiaohong Jiang

原文摘要

Embodied Internet of Things (IoT) systems are promoting the adoption of task-oriented semantic communication (SemCom), in which the trustworthy task decisions increasingly require both semantic reliability and source legitimacy. However, existing trustworthy SemCom designs mainly focus on semantic content recovery and protection, with limited attention to source identity protection. Motivated by this limitation, this paper establishes a new information exploitation perspective for integrated SemCom-identity protection that leverages task-level error tolerance to coordinate semantic information and source identity information carried by the same waveform. We first examine these two information resources and then analyze their integration feasibility at the observation, processing, and decision levels. To exploit these resources for different identity protection objectives, we further develop a dual-branch identity protection mechanism with two operating modes. In the authentication mode, semantic recovery and physical-layer source verification are performed in parallel using the same received observation. In the concealment mode, identity exposure is suppressed while semantic reconstruction quality is maintained to support anonymous transmission. Finally, two representative case studies on active source impersonation and passive identity inference are presented to evaluate the proposed framework.

cs.CR · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12445

LongSCOP: Semantically Consistent Long Video Outpainting

Yu Tang, Zhiyuan You, Zhixiao Wang, Fanghua Yu, Qingyu Zhang, Xiang Yin, Chao Dong, Jinjin Gu

原文摘要

Video out-painting is an important problem, yet existing research focuses primarily on short clips, leaving long video out-painting largely underexplored. Extending video out-painting to long videos poses substantial challenges. A natural solution is iterative out-painting, i.e., generating videos chunk by chunk, but this introduces two major issues: generation instability or even failure caused by inter-chunk inconsistencies and error accumulation, and semantic drift over long temporal horizons. In this paper, we propose LongSCOP, short for Semantically Consistent long Video Out-Painting. First, we introduce a training recipe with three components for smooth and stable long-horizon generation: self-forcing training, latent calibration, and future references. Beyond generation stability, we recognize that the rich temporal context of long videos provides valuable references for maintaining semantic consistency. We therefore develop a VLM-based agent that automatically selects the most informative reference frames from the entire video to maintain consistent subjects, scenes, and backgrounds throughout long-horizon generation. We also construct a high-quality training dataset of 62K video clips. To facilitate research on this underexplored problem, we introduce LVO-Bench, a benchmark curated by human experts to assess long-horizon stability and semantic consistency. Extensive experiments demonstrate that our method outperforms existing approaches in both generation stability and semantic coherence.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12296

RecoGEM: A Serving System for Production-Scale Generative Recommendation

Xiangrui Yang, Yunfeng Zhao, Jiawei Yang, Fangyu Zhang, Enrui Zhao, Liang Zeng, Cheng Peng, Minhui Xie 等 11 位作者

原文摘要

Generative recommendation (GR) is moving industrial recommender systems (RecSys) from scoring candidate items to autoregressively generating item identifiers. This shift promises higher recommendation quality, but makes serving substantially harder: each request executes a short sequence of dependent decoding steps that explore a large item space and select promising candidates on the latency-critical path. GR not only creates structural mismatches with conventional RecSys pipelines, but also challenges the architectural and optimization assumptions of LLM serving stacks, making direct adoption of existing systems difficult. We present RecoGEM, our production GR serving system. RecoGEM uses a runtime--engine decoupling architecture to move GR-specific serving responsibilities, such as candidate-state transitions and live artifact updates, to a dedicated runtime. Its execution engine exploits GR's short token sequences, large candidate populations, and predictable step shapes to optimize self-attention, candidate selection, and execution planning. RecoGEM has been deployed for over nine months across our production lines, serving applications with hundreds of millions of users and supporting more than ten GR model families. On our OneModel production workloads, RecoGEM reaches over 1,000 QPS per serving instance with P99 latency below 35 ms and a 2.88$\times$ throughput improvement over representative baselines.

cs.DC · cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2508.14948

LFM4Ads: Large Foundation Model for Ads Recommendation

Jie Jiang, Shangyu Zhang, Shijie Quan, Zhongren Wang, Tianqu Zhuang, Junwei Pan, Bo Fu, Yilong Sun 等 35 位作者

原文摘要

Recent work leverages large-scale pretrained foundation models (FMs) to transfer generalizable representations to downstream advertising tasks. Most existing approaches transfer user representations (URs) and item representations (IRs), while underutilizing the user-item cross representations (CRs) generated by deeper interaction layers. Although a recent work transfers target-aware embeddings (TAEs), it requires real-time upstream FM inference alongside the downstream, introducing additional engineering complexity and overhead. To address these limitations, we propose Large Foundation Model for Ads Recommendation (LFM4Ads), an efficient pretrain-then-transfer paradigm for cross-domain ad recommendation. LFM4Ads jointly exploits URs, IRs, and CRs from the upstream FM. It extracts sample-level CRs from pretrained interaction layers and aggregates them into user-level CRs using a time-aware exponential moving average, thereby decoupling upstream inference from downstream online serving. To use CRs efficiently, we propose three downstream usages at different levels of granularity: feature-level gating to fuse CRs into downstream embeddings, module-level fine-tuning to yield downstream CRs, and model-level retrieval by matching CRs with IRs. LFM4Ads has been deployed on Tencent's advertising platform since Q4 2024. It has supported 10+ launches across major scenarios, yielding a platform-wide gross merchandise value (GMV) lift of 2.45% and annual revenue gains in the hundreds of millions of dollars. Offline experiments on KuaiRand-1K further demonstrate our effectiveness. Our code is available at https://github.com/ZhuangQu/LFM4Ads.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12072

Learning Contextual Motion Constraints for Object Rearrangement Exploration

Lexing Zhang, Zeyu Zhang, Gang Zeng, Hangxin Liu

原文摘要

The motion of an articulated part in cluttered surroundings is constrained not only by an object's intrinsic joint limits but also by extrinsic obstacles. However, existing approaches primarily consider object articulation properties alone. Here we present Motion Constraint Prediction Network (MoCo-Net), a two-stream neural network that jointly predicts the continuous motion ranges of articulated parts and obstacle heatmaps highlighting potential collision regions from partial-view point cloud observation. By capturing both internal and external motion constraints, MoCo-Net produces more accurate feasible motion range prediction and obstacles recognition, improves generalization for novel objects in new scenes, and enables robots to construct a scene configuration space for efficient exploration of rearrangement actions. Our experiments show that MoCo-Net's two-stream design enhances each other to deliver more accurate predictions, which subsequently form a compact configuration space for a customized planner to efficiently rearrange the scene.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12013

Enhancing Multi-Step Chemical Mechanism Prediction with Graph-Guided Preference Data

Yu Zhang, Ruijie Yu, Xuelin Zhao, Jinming Yang, Feng Zhu, Xiaokang Yang, Yaohui Jin, Yanyan Xu

原文摘要

Predicting multi-step chemical reaction mechanisms requires identifying plausible intermediates and correctly ordering the elementary reaction steps. Existing computational methods focus on single-step elementary reaction prediction, limiting their ability to generalize to unseen reaction spaces. We introduce a graph-guided framework for multi-step chemical mechanism prediction that leverages a chemical mechanism knowledge graph (ChemMechKG) to guide large language models (LLMs). To improve pathway prediction, we develop a graph-aligned reaction mechanism predictor (GRMP) that uses graph neural networks to generate synthetic candidate pathways for pathway optimization. During inference, we design a relation retrieval (RR) module to extract relevant graph evidence from the KG for pathway refinement. Experiments show that GRMP achieves the highest pathway accuracy among all compared methods on ChemMechQA and oMe-Gold, reaching 48.1% and 57.9%, respectively. On a fixed sample of 110 out-of-distribution reactions from ChemMechQA-Hard, GRMP achieves 36.4% top-1 pathway accuracy. LLM-as-Judge and human assessment further demonstrate its ability to generalize to unseen reactions.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11771

ARMOR: Adaptive Curriculum Meta-Learning for Noise-Robust RAG Reasoning

Yan Wang, Yuxin Zhang, Shenyu Zhang, Yongrui Chen, Sheng Bi, Guilin Qi

原文摘要

Retrieval-Augmented Generation (RAG) systems have demonstrated remarkable effectiveness in mitigating hallucinations by incorporating external knowledge. However, the retrieval process inevitably introduces noise, posing significant challenges to RAG robustness. Fundamentally, noise robustness is a composite competency encompassing noise identification, retrieval filtering, and robust reasoning. Unfortunately, existing methods often fail to capture this holistic nature, typically restricted to single-dimensional enhancements or hampered by noise-induced optimization interference. To address these limitations, we decompose RAG robustness into three sub-tasks: knowledge boundary perception, retrieval verification, and robust reasoning. Accordingly, we propose ARMOR, an Adaptive Curriculum Meta-Learning for Noise Robust RAG Reasoning. Inspired by the teaching process, ARMOR introduces an adaptive task scheduler as a teacher to curate training plans according to the absolute learning progress of RAG generators (Student). Distinct from GRPO, ARMOR utilizes inter-group advantage estimation during learning to effectively mitigate mode collapse caused by limited output spaces. Experiments on three complex reasoning datasets (2WikiMultiHopQA, MusiQue, and HotPotQA) indicate that ARMOR achieves synergistic improvements in retrieval noise robustness, significantly outperforming baselines in output quality.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.11560

LiveAsset: Learning Intent Assets from Corrective Interactions for Agent Runtime Control

Guanming Liu, Weihang Wang, Peng Zhang, Meng Wu, Kainan Tu, Jiahao Liu, Yu Zhang, Liuxin Zhang 等 11 位作者

原文摘要

Large language model (LLM) agents acting across web applications and online services often need multi-turn corrections to align their work with users' underspecified goals and preferences. In practice, users may identify problems in the current outcome without specifying the desired result, so learning user intentions requires interpreting each correction against the agent's preceding and revised outcomes. These expectations are often connected to a particular context, making it hard to know when they apply and how to ensure the agent later acts as the user expects. To this end, we propose LiveAsset, an intent harness that learns reusable intent assets from corrective interactions and uses them for runtime control of agent execution. LiveAsset jointly interprets each correction with the agent's original and revised results to infer user intent, incrementally updating the assets while preserving earlier requirements that remain applicable. The learned requirements guide agent execution from task entry and provide criteria for runtime verification, which uses the explanations to assess applicability before each reply is delivered and directs the agent to revise the result to address unmet requirements while preserving those already satisfied. Following a learning phase in which simulated users progressively reveal requirements through multi-turn corrections, we evaluate LiveAsset using same-task replay of the original requests on π-Bench, PERMA, and Vita and cross-task transfer on PAST-Bench and SkillEvolBench. Experiments show that LiveAsset better fulfills requirements learned from corrective interactions and improves performance on these benchmarks compared with memory, skill, and rule-based harness baselines. Code is available at github.com/landian60/LiveAsset.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.03325

IntPro: Context-Aware Intent Inference via Selective Retrieval from User History

Guanming Liu, Meng Wu, Peng Zhang, Yu Zhang, Yubo Shu, Xianliang Huang, Kainan Tu, Ning Gu 等 11 位作者

原文摘要

Accurately understanding user intent in context is essential for large language models (LLMs) to provide effective assistance. However, observed behavior may support multiple plausible intents, making the current context alone insufficient for identifying the user's underlying goal. A user's interaction history may contain recurring context-to-intent patterns that help disambiguate the current intent. Leveraging such historical patterns requires deciding whether to invoke retrieval for the current context and, if so, forming queries that express plausible intents rather than relying on contextual similarity alone. We present IntPro, a proxy agent that learns to either infer intent directly from the current context or generate candidate intent explanations to retrieve intent-aligned records from the user's history. We design intent explanations as a shared intent-oriented natural-language form that expresses the observed action, its functional goal, and a cue-to-intent rationale. Label-conditioned explanations represent historical records, while candidate explanations generated from the current context serve as retrieval queries in the same form. IntPro first learns direct and retrieval-conditioned inference through Direct-and-Retrieval supervised fine-tuning (SFT). IntPro then uses multi-turn GRPO with a retrieval-decision reward to jointly optimize intent prediction and selective retrieval mechanism. Experiments across three scenarios and three model backbones demonstrate that IntPro consistently improves context-aware intent inference.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗