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

+1171新增论文
+938其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 17:46各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 17:47 — 2026-11-19 17:47(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-19 06:59最近发现新增版本:2026-11-19 17:46库内论文最新更新时间:2026-11-19 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。

27,410 已收录论文22,788 AI 相关8,343 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 20 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
新论文 · v1arXiv:2611.24098

RoughCut-Bench: A Benchmark for Automatic Video Rough-Cut with Large Vision-Language Models

Ruisi Zhao, You Li, Sihan Chen, Aosong Cheng, Chixiang Ma, Sen Pei, Zhen Yang, Hehe Fan 等 10 位作者

原文摘要

Video rough-cut is a core stage in media production workflows, organizing raw media materials into an initial video cut. Despite recent advances in large vision-language models (LVLMs) for video-related tasks, automatic rough-cut remains underexplored, without a comprehensive benchmark for evaluation or mature workflows for producing executable cut plans. To address the evaluation gap, we introduce RoughCut-Bench, which covers two practical settings: (1) a visually driven setting over video cases, covering highlight detection and selection, source-video ordering, and adherence to user requirements when provided; and (2) a speech-driven setting over automatic speech recognition (ASR) transcripts, covering filler removal, expression deduplication, and low-value content trimming. Across these settings, the benchmark contains 101 visually driven cases, including 831 raw videos with 1,476 highlight annotations. It also includes 84 speech-driven cases, each consisting of an ASR transcript with annotated cleanup spans. The evaluation compares cut plans with these annotations in both settings and additionally uses a human-aligned agentic evaluator to assess rendered-cut quality in the visual setting. To apply LVLMs to automatic rough-cut, we further propose agentic workflows that guide them to produce structured cut plans from input materials. Experiments show that current LVLMs remain limited in producing expert-aligned cut plans. Our benchmark, code, and prompts are released at https://whalesong-zrs.github.io/RoughCut-Bench-Project-Page.

cs.CV

版本更新 · v3arXiv:2606.07085

Porting Declarative UI to HarmonyOS: A Heuristic-guided Approach for lightweight LLMs

Kunwu Zheng, Pengyu Xue, Zhen Yang, Tianlong Chen, Xiran Lyu, Peishi Lai, Mengying Zhao, Junjie Chen 等 13 位作者

原文摘要

As an emerging operating system, HarmonyOS has a significant demand for software migration, where the User Interface (UI) translation accounts for a critical link. However, recent UI development has shifted to declarative paradigms, e.g., Kotlin Jetpack Compose (KJC) for Android, SwiftUI for iOS, and ArkUI for HarmonyOS, making prior translation approaches inapplicable because they target either backend logic or legacy imperative UIs. Thus, related research is limited. To systematically evaluate KJC/SwiftUI-to-ArkUI migration, we build a parallel benchmark of 100 KJC and 100 SwiftUI files across eight scenarios, plus 52 real-world UI pages from nine open-source apps. Evaluating nine direct-translation setups (including diverse LLMs and agents), we find Compilation Success Rate (CSR) spans 0.00%-35.00%; common strategies (reference screenshots and compiler-guided repair) lift capable setups to 94.00%-99.00% CSR but fail on lightweight LLMs. By manually analyzing a 3,102-sample subset, deriving a regular-expression pattern for each failure family, and applying these patterns to generalize the resulting taxonomy to the full 29,593-sample set, we find residual errors rooted in (1) broken structure, (2) nonexistent APIs, and (3) missing resources (e.g., colors, strings, and icons). Accordingly, we propose ArkTrans, a declarative UI translation framework that maps these roots to deterministic structure supply, ArkUI knowledge and resource reference injection via a demonstration example, and iterative repair targeting residual errors, via four steps: Metadata Extraction, Skeleton Construction, LLM-driven Translation, and Compiler-Guided Iterative Repair. With Qwen3.6-27B, ArkTrans raises CSR from 0.00% to 70.00% on KJC and 64.00% on SwiftUI, achieving strong visual fidelity, and attains 65.63%/80.00% CSR on real-world pages, far outperforming the best common strategy at lower token cost.

cs.SE

版本更新 · v2arXiv:2610.14629

Executable but Unfaithful: Mock Object, Stub, and Assertion Generation by LLMs and Coding Agents

Hao Ning, Jiahui Dong, Zhen Yang, Guanda Yan, Yichen Sun, Xuanyu Zhu, Zheng Shen, Yifei Pei 等 10 位作者

原文摘要

Mocking is a foundational practice in unit testing, enabling developers to isolate the code under test by replacing real dependencies with simulated alternatives. Automating the generation of mock objects, stubs, and mock assertions has been a long-standing research goal. However, capture-and-replay approaches rely on recording the runtime behavior of actual dependencies. Evolutionary approaches such as StubCoder overcome this requirement but constrain generation to predefined symbol pools. Large language models (LLMs) and coding agents offer an alternative by generating mocking artifacts from source code without requiring recorded dependency executions or fixed symbol pools. Yet, no systematic study has evaluated their capabilities across all three artifact types. To address this gap, we construct MockBench, a benchmark comprising 165 mock artifact generation tasks from real-world Java and Python projects, with validated reference mock objects, stubs, and mock assertions. We evaluate six LLMs and three coding agents in terms of executability, behavior fidelity, and interaction-fault detection capability, complemented by comparisons with existing tools and sensitivity analysis. Experimental results show that LLMs and coding agents indeed have been the state-of-the-art techniques in mock-based testing. More specifically, compared with LLMs, coding agents substantially improve executability, while these gains do not consistently translate into higher behavior fidelity or better interaction-fault detection. Furthermore, we analyze 660 failures from LLMs and coding agents, and identify ten error types across the three artifact categories, revealing behavioral deviations that passing tests can conceal. Our findings highlight the challenges of mock artifact generation and provide practical guidance for both developers and researchers.

cs.SE

新论文 · v1arXiv:2611.06069

SynMOE: A Syntax-Aware MOE-Guided Approach for PEFT-Based Code Intelligence Learning

Shuo Liu, Hao Ning, Jacky Keung, Zhen Yang, Xiao Yu, Xing Hu, Yicheng Sun

原文摘要

Parameter-Efficient Fine-Tuning (PEFT) has emerged as an important approach for adapting Language Models (LMs) in downstream tasks. However, in the domain of code intelligence, the performance of most PEFT methods relatively drops compared to Full fine-Tuning (FT), hindering their broader applicability. One of the main reasons is that current PEFT methods are generally based on assumptions about the low-rank nature or sparsity of parameter updates, lacking explicit modeling of code-related information. To tackle this limitation, we propose SynMOE, a syntax-aware MOE-guided approach for PEFT on code intelligence learning. Specifically, SynMOE contains two stages: syntactic information extraction and syntax-aware MOE-guided adaptation. It first obtains the syntactic labels of source code from Abstract Syntax Trees (ASTs), and then aligns the labels with the input tokens of code LMs. In the second stage, syntactic labels are integrated into the MOE module, participating in the routing decision of MOE for a more powerful syntactic-aware token representation. We evaluate the effectiveness of the proposed approach by applying it to two typical PEFT methods, LoRA and $(IA)^3$, across three diverse code intelligence tasks. Experimental results show that SynMOE achieves consistent and significant improvements. Even compared to FT, SynMOE achieves comparable or superior performance while being more computationally efficient. In addition, we also conduct ablation studies, hyperparameter analysis, and evaluation in the low-resource scenario to provide a comprehensive investigation of the proposed approach.

cs.SE

新论文 · v1arXiv:2611.04787

ReSI-Math: Exploring Recoverable Capability Frontiers for Efficient Reasoning Improvement

Yao Cui, Zhen Yang, Yuandong Wang, Yangfu Zhu, Tianyu Wo, Zhenzhou Shao

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has become an effective approach for improving mathematical reasoning in large language models. However, a fundamental question remains: when a model fails to solve a problem, does it truly lack the underlying capability? In this work, we reveal that direct failure does not necessarily imply inability. Some reasoning failures can be recovered by exploring the model's own trajectories, exposing a recoverable capability frontier: a policy-dependent region where solutions are not reliably generated through direct decoding but can be elicited through trajectory-level search. Based on this observation, we introduce ReSI-Math, a framework that explores recoverable capability frontiers and converts recovered capabilities into data-efficient RLVR supervision. ReSI-Math uses Self-Judge-guided evolutionary search to identify recoverable failures under a fixed policy and adaptively selects frontier problems for sequential RLVR as the policy evolves. On Qwen3-VL-8B, correct-incorrect trajectory crossover produces 272 verifier-confirmed correct offspring from 621 attempts (43.8%). After three sequential one-shot RLVR stages, the MATH500 and WE-MATH average improves from 78.71 to 80.16. Under matched single-problem RLVR, random selection reaches only 53.31 versus 54.16 for frontier-guided Q1.

cs.CL · cs.AI

新论文 · v1arXiv:2611.04146

RGDM: Robust Graph Diffusion Model

Yancheng Wang, Ping Li, Dongfang Sun, Yingzhen Yang

原文摘要

Diffusion models represent a powerful class of generative models known for their solid theoretical foundations and remarkable performance across diverse tasks and domains. Existing node level diffusion methods synthesize nodes and edges within a graph, but are not designed to learn a robust generator from adversarially corrupted graphs. In this study, we introduce the Robust Graph Diffusion Model (RGDM), designed to generate labeled synthetic graph structures consisting of nodes and edges that integrate seamlessly into a given graph. The RGDM consists of a Robust Graph Autoencoder (RGAE) and a Latent Diffusion Model (LDM). Leveraging an edge selection mechanism and an innovative low-rank regularization on the latent feature, the RGDM produces clean and high-quality synthetic graph structures, even when trained on graphs subject to adversarial attacks. Comprehensive experimental evaluations reveal that Graph Neural Networks (GNNs) trained on the augmented graph, which is formed by merging the original attacked graph with the synthetic graph structures, exhibit significantly improved robustness against various graph adversarial attacks in the context of semi-supervised node classification. The code of the RGDM is available at https://github.com/Statistical-Deep-Learning/RGDM.

cs.LG

新论文 · v1arXiv:2611.03590

A Scaling Theory of Multi-Epoch Pretraining: Late-Time Overfitting and Ensembling

Zhen Yang, Yidi Miao, Blake Bordelon

原文摘要

In the near future language model pretraining will become bound by total data rather than total compute. Such a regime requires revisiting scaling laws and scaling law theory. Motivated by prior works that have found utility in ensembling, we study how the number of training epochs and ensemble size jointly shape generalization when training data are fixed. In language-model experiments on FineWeb, logit averaging reduces late-training deterioration, delays optimal stopping, and can outperform wider or deeper single models at matched parameter-token budgets over a common training horizon. To analyze this interaction between data reuse and ensembling, we derive a dynamical mean-field theory (DMFT) for multi-epoch stochastic gradient descent in power-law random-feature ensembles, tracking error correlations across epochs and models. Ensembling reduces the prediction variance responsible for late-time growth in expected test error, changing the optimal stopping time. We use these stopping times to derive compute-allocation laws at fixed data and individual model sizes. Under this allocation, ensemble size grows with compute at least as fast as training time per member, while excess test loss above the limiting loss decreases as a power of compute.

cs.LG

新论文 · v1arXiv:2611.02930

PointPilot: Unified Robotic Manipulation via Object-Centric 3D Point Flow Prediction

Yihan Fang, Yuxin Tian, Ruixiang Wang, Zhanqi Zhang, Xing Hu, Zhen Yang, Huayi Zhou, Yongyi Su 等 10 位作者

原文摘要

Generalization remains a central challenge in robotics, calling for policies that address domain variations from multiple dimensions such as diverse embodiments, camera poses, and/or scene layouts. In order to approach this problem, we introduce PointPilot, a task-focused and 3D aligned manipulation framework built on a 3D space point-flow prediction. Rather than modeling the global scene, PointPilot only represents task-focused objects (robot grippers treated as objects), avoiding the prediction of potentially redundant scene parts unrelated to the manipulation tasks. Moreover, PointPilot aligns 3D spatial representation in one unified coordinate and supports closed-loop and fully automatic action execution across different manipulation modes from object point flow without a separately trained action expert, while existing works typically need an extra action head or are (semi-)automatic and single-arm mode specific. Given sensor observations and language instructions, our model jointly learns subtask planning, task-relevant object grounding, and 3D point flow prediction in an end-to-end way. By processing heterogeneous data in a shared 3D point flow space, PointPilot is able to absorb demonstrations from different embodiments. Extensive simulative and real world experiments validate our method. Notably, we demonstrate zero-shot embodiment generalization with PointPilot. A single trained policy can be deployed on previously unseen embodiments and successfully complete manipulation tasks without any additional fine-tuning.

cs.RO

新论文 · v1arXiv:2611.01642

Sharp Generalization for Nonparametric Regression in Interpolation Space by Shallow Over-Parameterized Neural Networks with Channel Attention

Yingzhen Yang, Ping Li

原文摘要

We study nonparametric regression using an over-parameterized two-layer ReLU neural network with fixed covariance-based channel attention, trained by gradient descent with both layers updated simultaneously. The spherical covariates follow an arbitrary fixed non-atomic distribution, and the target function lies in an interpolation space with spectral bias widely studied in the statistical learning literature. We prove that early-stopped training achieves regression risk $\cO(\eps_n^2)$, where $\eps_n$ is the critical population rate of the attention kernel $\Kattn$. Its positive eigenvalues are $λ_j^{s'}$, where $λ_j$ are those of the ReLU feature covariance kernel $K$ and $s'=2s+3$ for $s\ge1$. Under polynomial eigenvalue decay $λ_j\asymp j^{-2α}$ with $α>1/2$, the regression risk bound $\cO(\eps_n^2)$ specializes to the minimax optimal rate $\cO(n^{-2αs'/(2αs'+1)})$. Our analysis is based on two new technical results on the optimization and generalization of the attention network. First, the neural network function after every gradient descent iteration admits a decomposition into a function with bounded Reproducing Kernel Hilbert Space (RKHS) norm and a uniformly small residual. Second, local Rademacher complexity converts this decomposition into a regression risk bound. Kernel gradient descent on the same ball attains the same rate, while our theorem gives explicit sufficient width and auxiliary-sample conditions for simultaneous network training. Our analysis is further extended to covariates supported on $\RR^d$ through a novel normalization method. Under a sub-Gaussian covariate distribution, the attention network achieves a nearly optimal regression risk $\cO((\log n)n^{-s'(d+3)/(s'(d+3)+d)})$ without a density assumption.

stat.ML · cs.LG

新论文 · v1arXiv:2610.37649HF 社区推荐

Can LLMs Uncover Hidden Physical Laws through Free Exploration?

Zhen Yang, Wen Wang, Xander Xu, Ying-Cong Chen

原文摘要

Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected behavior, such as heavier objects falling more slowly, and discover the law through experiments without being told what to investigate? To evaluate this ability, we introduce LongChang, an automated framework that creates simulated worlds with altered physics, where one or more laws differ from ordinary physics. The evaluated LLMs act as explorers, manipulating objects and building tools to investigate their own questions without research tasks or hints about these laws. Separate LLM agents generate and review scenes, review tool designs, and evaluate reports for correctness and experimental support using the altered physical laws and exploration records. These records guide scene evolution for further exploration, allowing the full cycle to run without human intervention. Among 12 LLMs, GPT-6-Astra achieves a discovery rate of 16.7%, while the other 11 score 0%. The exploration records reveal uninvestigated anomalies and only partial identification of the altered physical laws.

cs.CL · cs.AI · cs.MA

版本更新 · v3arXiv:2606.05158

Streaming Communication in Multi-Agent Reasoning

Zhen Yang, Xiaogang Xu, Wen Wang, Cong Chen, Xander Xu, Ying-Cong Chen

原文摘要

Multi-agent reasoning systems adopt a generate-then-transfer paradigm that forces end-to-end latency to scale linearly with pipeline depth. We introduce StreamMA, a multi-agent reasoning system that streams each reasoning step to downstream agents as soon as it is generated, pipelining adjacent agents and thus reducing latency. Surprisingly, this pipelining also improves effectiveness: because multi-step reasoning quality is non-uniform and early steps are more reliable than later ones, working with these reliable early steps instead of the full chain prevents error-prone late steps from misleading downstream agents. We formalize both advantages with the first closed-form joint analysis of stream, serial, and single protocols, deriving the effectiveness ordering, speedup upper bound, and cost ratio. Across eight reasoning benchmarks spanning mathematics, science, and code, three frontier LLMs (Claude Opus 4.6, GPT-5.4, and GLM-5.2), and three topologies (Chain, Tree, Graph), StreamMA outperforms both baselines (avg.+7.3pp, max +22.4pp on HMMT2026; Claude Opus 4.6-High). Beyond these contributions, we discover a step-level scaling law: increasing per-agent steps consistently improves both effectiveness and efficiency, a new scaling dimension orthogonal to and composable with agent-count scaling.

cs.CL · cs.AI · cs.MA

版本更新 · v5arXiv:2407.11353

Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping

Yingzhen Yang, Ping Li

原文摘要

We study nonparametric regression using an over-parameterized two-layer neural network trained with algorithmic guarantees in this paper. We consider the setting where the training features are drawn uniformly from the unit sphere in $\RR^d$, and the target function lies in an interpolation space commonly studied in statistical learning theory. We demonstrate that training the neural network with a novel Preconditioned Gradient Descent (PGD) algorithm, equipped with early stopping, achieves a sharp regression rate of $\cO(n^{-\frac{2αs'}{2αs'+1}})$, where $α$ parametrizes the polynomial eigenvalue decay of the regular Neural Tangent Kernel (NTK), $λ_j\asymp j^{-2α}$, and $2α=d/(d-1)$ under the spherical uniform design considered here. The target function is assumed to belong to the interpolation space $\bth{\cH_K}^{s'}$ with $s'\ge3$. This rate is even sharper than the currently known nearly-optimal rate of $\cO(n^{-\frac{2αs'}{2αs'+1}})\log^2(1/δ)$~\citep{Li2024-edr-general-domain}, where $n$ is the size of the training data and $δ\in (0,1)$ is a small probability. Our analysis is based on two key technical contributions. First, we present a principled decomposition of the network output at each PGD step into a function in the reproducing kernel Hilbert space (RKHS) of a newly induced integral kernel, and a residual function with small $L^{\infty}$-norm. Second, leveraging this decomposition, we apply local Rademacher complexity theory to tightly control the complexity of the function class comprising all the neural network functions obtained in the PGD iterates. Our results show how PGD changes the effective kernel in the reference training dynamics, inducing an integral kernel with lower complexity than the regular NTK arising from vanilla GD.

stat.ML · cs.LG · math.ST

新论文 · v1arXiv:2610.34073HF 社区推荐

Memory Tax: Dissecting the Net Value of Agent Memory

Xuan He, Sining Zhoubian, Ruozhen Yang, Yuhao Wen, Zhineng Wang, Yuyang Hu, Ke Yang, Yuyu Zhang 等 11 位作者

原文摘要

Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw history remains largely unclear. Through a large-scale evaluation across multiple benchmarks and model backbones, we find many dedicated memory systems underperform naive RAG in many cases, indicating a negative net value. Taking RAG as a reference, we dissect the net value of memory into the gains and losses over direct retrieval, termed memory benefit and memory tax. These gains and losses arise because memory process changes how the raw information is organized and accessed. We view such changes as the double-edged deviations from the raw history. They are originally designed and introduced to benefit the task, for example by reorganizing facts or distilling preferences, but some may also remove or obscure evidence, giving rise to memory tax. Since memory benefit reflects the expected gains of its design, we then focus more on the overlooked memory tax, study how it arises from the system and evaluation side, and generalize the concept to more application scenarios of memory. We hope the notion of memory tax can provide a new lens and shift more attention from standalone performance to the net value of memory, informing more reliable memory designs and evaluations. We will open-source the code and results to the community. Project Page: https://hexuan21.github.io/MemoryTax/

cs.CL

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1279ACL Anthology · ACL 2026

CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables

Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang Anhui University, Suping Sun, Ziwei Du Anhui University 等 14 位作者

原文摘要

Recent progress in Large Language Model (LLM) based Table Question Answering (TableQA) has demonstrated strong performance on standard benchmarks. However, existing benchmarks mainly focus on well-structured tables and fail to reflect the irregular structures and complex reasoning commonly encountered in real-world scenarios. We propose CompTab, a benchmark designed to evaluate TableQA under complex reasoning and irregular table conditions. CompTab covers six representative types, including semantic ambiguity, multi-hop reasoning, transposed tables, merged cells, missing values, and outliers. It is constructed from real-world seed tables across multiple domains using controlled LLM based generation and human verification to ensure realism and diversity. In addition, to improve the generalization of LLMs under complex and irregular table settings, we propose a two-stage training framework that progressively aligns models with textual reasoning and executable decision signals, instantiated as CompTabLLM. Evaluations on 38 representative LLMs and CompTabLLM show clear limitations of existing LLMs under realistic conditions, while the proposed framework improves generalization. CompTab thus provides a challenging benchmark for advancing TableQA in real-world.

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.1747ACL Anthology · ACL 2026

Execution as Verification: Fine-Grained Self-Correcting Reasoning for Complex KBQA

Minghan Zhang, Zhen Yang, Haodong Zou, Jie Chen Anhui University, Zhen Duan Anhui University, Shu Zhao Anhui University

原文摘要

Knowledge Base Question Answering (KBQA) leverages structured knowledge bases to offer superior interpretability and hallucination resistance, making it a critical technology for precise knowledge reasoning. However, the prevailing LLM-based generate-then-execute formulation of semantic parsing is limited by strict syntactic constraints, making it primarily prone to structural deviations that render queries unexecutable, while suffering from semantic deviations that yield incorrect execution results. To address these challenges, we propose the Execution as Verification (EVER) framework, reframing semantic parsing as an iterative, self-correcting reasoning process driven by execution feedback. First, motivated by the insight that query executability serves as a strong proxy for answer correctness, we introduce Fine-Grained Execution-Aware Planning. This mechanism decomposes complex semantic parsing into a sequence of stepwise reasoning processes oriented by executability verification, ensuring high query executability. We further design a Self-Guided Semantic Correction mechanism based on execution result verification, utilizing execution feedback to verify and calibrate semantic deviations, thereby ensuring the semantic correctness of executable queries. Experimental results on the WebQSP and CWQ datasets demonstrate that our method achieves significant improvements in both query executability and answer accuracy, achieving state-of-the-art performance, particularly in complex multi-hop scenarios. Our code is available at https://github.com/ahu-zmh/EVER.

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.2198ACL Anthology · ACL 2026

MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning?

Yuandong Wang Capital Normal University, Yao Cui, Yuxin Zhao, Zhen Yang, Yangfu Zhu, Zhenzhou Shao

原文摘要

Recent advances in Vision-Language Models (VLMs) have achieved impressive progress in multimodal mathematical reasoning. Yet, howmuch visual information truly contributes to reasoning remains unclear. Existing benchmarks report strong overall performance but seldom isolate the role of the image modality, leaving open whether VLMs genuinely leverage visual understanding or merely depend on linguistic priors. To address this, we present MathSight, a university-level multimodal mathematical reasoning benchmark designed to disentangle and quantify the effect of visual input. Each problem includes multiple visual variants—original, hand-drawn, photocaptured—and a text-only condition for controlled comparison. Experiments on state-of-the-art VLMs reveal a consistent trend: the contribution of visual information diminishes with increasing problem difficulty. Remarkably, Qwen3-VL without any image input surpasses both its multimodal variants and GPT-5, underscoring the need for benchmarks like MathSight to advance genuine vision-grounded reasoning in future models. The project page is available at https://cnu-bot-group.github.io/MathSight/.

cs.CL · cs.CV

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.432ACL Anthology · ACL 2026

PAM: Enhancing General Alignment of Large Reasoning Models through Priority-Aware Metacognition

Zhihao Xu, Fuzhen Yang, Liang Lin, Xiting Wang Renmin University of China

原文摘要

Recent advancements in Large Reasoning Models (LRMs) have showcased strong performance across various reasoning tasks by leveraging System-2 thinking capabilities. However, existing studies indicate that this reasoning ability alone does not reliably transfer to the general alignment domain. Inspired by cognitive science and how humans solve tasks, we argue that LRMs must be equipped with metacognitive knowledge to fully utilize their System-2 capabilities. In this paper, we propose Priority-Aware Metacognition (PAM), which guides the model to first identify the top-level human preference (e.g., harmlessness) as a means of understanding the alignment task’s nature, and then apply other kinds of metacognitive knowledge to better monitor and regulate the model’s thinking process. We implement PAM via a two-stage pipeline: a cold-start phase that collects structured metacognitive knowledge based on Flavell’s theoretical framework, and a preference-optimization phase that further reinforces such metacognition. Extensive experiments validate the effectiveness of PAM. Under the same training pipelines, PAM consistently yields higher performance, improving general domain alignment performance by ~10 points on the helpfulness and harmless benchmarks. Code is available at https://anonymous.4open.science/r/PAM-RM-02DF.

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.496ACL Anthology · ACL 2026

How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study

Zhen Yang, Ping Jian Beijing Institute of Technology, Zhongbin Guo, Zuming Zhang Nanyang Technological University, Chengzhi Li Beijing Institute of Technology, Yonghong Deng Beijing Institute of Technology, Xinyue Zhang, Wenpeng Lu

原文摘要

Over the past year, spatial intelligence has drawn increasing attention. Many prior works study it from the perspective of visual-spatial intelligence, where models have access to visuospatial information from visual inputs. However, in the absence of visual information, whether linguistic intelligence alone is sufficient to endow models with spatial intelligence, and how models perform relevant tasks with text-only inputs still remain unexplored. Therefore, in this paper, we focus on a fundamental and critical capability in spatial intelligence from a linguistic perspective: viewpoint rotation understanding (VRU). Specifically, LLMs and VLMs are asked to infer their final viewpoint and predict the corresponding observation in an environment given textual description of viewpoint rotation and observation over multiple steps. We find that both LLMs and VLMs perform poorly on our proposed dataset while human can easily achieve 100% accuracy, indicating a substantial gap between current model capabilities and the requirements of spatial intelligence. To uncover the underlying mechanisms, we conduct a layer-wise probing analysis and head-wise causal intervention. Our findings reveal that although models encode viewpoint information in the hidden states, they appear to struggle to bind the viewpoint position with corresponding observation, resulting in a hallucination in final layers. Finally, we selectively fine-tune the key attention heads identified by causal intervention to improve VRU performance. Experimental results demonstrate that such selective fine-tuning achieves improved VRU performance while avoiding catastrophic forgetting of generic abilities.

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.921ACL Anthology · ACL 2026

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention

Zhen Yang The Hong Kong University of Science and Technology, Mingyang Zhang Alibaba Group, Feng Chen University of Adelaide, Ganggui Ding, Liang Hou Kuaishou Technology, Xin Tao Kuaishou, Ying-Cong Chen The Hong Kong University of Science and Technology

原文摘要

Recent progress in large language models (LLMs) has focused on test-time scaling to improve reasoning via increased inference computation, but often at the cost of efficiency. We revisit test-time behavior and uncover a simple yet underexplored phenomenon: reasoning uncertainty is highly localized—only a small subset of high-entropy tokens dominantly affects output correctness. Motivated by this, we propose Minimal Test-Time Intervention (MTI), a training-free framework that enhances reasoning accuracy and stability with minimal overhead. MTI includes: (i) Selective CFG intervention, applying classifier-free guidance only at uncertain positions; and (ii) Lightweight negative-prompt guidance, reusing the main model’s KV cache to approximate unconditional decoding efficiently. MTI yields consistent gains across general, coding, and STEM tasks—e.g., +9.28% average improvement on six benchmarks for DeepSeek-R1-7B and +11.25% on AIME2024 using Ling-mini-2.0—while remaining highly efficient.

cs.CL

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

版本更新 · v5arXiv:2403.05530Google Research

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent 等 1137 位作者

原文摘要

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

cs.CL · cs.AI