AI 速览：作者构建了迄今规模最大的真实图像婴儿姿态数据集 InfantNet，并建立婴儿 2D 关键点检测与 3D 姿态形状恢复基准。
Infant pose and shape estimation is essential for applications in childcare, developmental monitoring, and medical diagnosis. However, existing methods and datasets are largely designed for adults, and direct transfer to infants fails due to substantial differences in body proportions, articulation limits, and frequent self-occlusion. To address this gap, we introduce InfantNet, the largest real-image infant dataset to date, comprising 108,902 RGB images of infants aged 6-18 months. Each image is annotated with 2D keypoints, and a curated subset of 11,642 images additionally includes 3D pose and shape annotations with full SMIL parameters, verified through multi-view rendering and reprojection-error filtering. We use an iterative annotation pipeline to ensure high fidelity across both 2D and 3D labels. InfantNet establishes a large-scale, comprehensive benchmark for infant 2D keypoint detection and 3D pose-and-shape recovery. Baseline experiments demonstrate that state-of-the-art adult pose estimators do not generalize well to infants, whereas fine-tuning on InfantNet yields a consistent improvement. The gains are even more pronounced for 3D pose and shape estimation, where SMIL-based estimation demonstrates robust performance with accuracy comparable to results reported for SMPL-based models. By releasing the InfantNet dataset and benchmark, we provide a vital resource for advancing infant pose analysis and related healthcare applications.
Yaxin Gong, Chongming Gao, Gangyi Zhang, Chenxiao Fan, Leyang Shen, Jiakai Wang, Dong Wang, Yang Liu 等 10 位作者
Multi-step Web tasks often require several LLM agents to gather and combine evidence. The communication graph of a fixed workflow restricts which agents can read each other's outputs: evidence retrieved by one agent may never reach the agent that needs it, leaving an information gap and an incomplete or incorrect answer. Adding a connection can deliver the missing evidence, but can also lead the receiver to adopt an incorrect upstream conclusion that displaces a correct answer; the final output alone does not separate the two. We propose Selective Probing and Link Insertion for Closing information gaps in multi-agent Execution (SPLICE), which locates information gaps per query and decides what to adopt after adding an edge. After the original workflow runs, SPLICE uses the query and node outputs to locate a possible gap, adds one directed edge from a source to a receiver to deliver the relevant evidence, and re-executes the receiver and affected downstream nodes, producing a candidate answer. The adoption decision reads both the final answers of the two runs and the process changes the edit caused inside the workflow: how far the receiver moved, where its new content came from, and whether the change reached the final answer. A selector trained on these process features chooses between adopting the candidate answer and retaining the original. On five benchmarks, SPLICE raises the task score on Web tool use by 8.0% and the mean score on four reasoning and planning benchmarks by 5.7% relative to the static skeleton, at 1.25 to 1.44$\times$ the skeleton's cost, and transfers zero-shot to four unseen backbones.
We study approximation algorithms for constructing sparse navigable graphs in general metrics. Given an $n$-point metric $(P,d)$ and a parameter $α\ge1$, a directed graph on $P$ is $α$-navigable if, for every pair of distinct points $s,t\in P$, the source $s$ has an outgoing neighbor $p$ with $d(p,t)<d(s,t)/α$. The objective is to minimize the number of edges. Recent independent works of Khanna, Padaki, and Waingarten (2026) and Conway et al. (2026) give $O(\log n)$-approximation algorithms and show that an $o(\log n)$ approximation is NP-hard in general. Before our work, the best known running time for such an approximation for general $α\ge1$ was $\widetilde O(\min\{n\operatorname{OPT}_α,n^{2.5}\})$, where $\operatorname{OPT}_α$ is the minimum number of edges in an $α$-navigable graph. In this paper, we give a randomized algorithm that, with high probability, runs in $\widetilde O(n^2)$ time and achieves an $O(\log n)$ approximation for every $α\ge1$. In general, these guarantees are nearly optimal up to constant factors in the approximation and polylogarithmic factors in the running time.
Chenxiao Fan, Chongming Gao, Gangyi Zhang, Yaxin Gong, Leyang Shen, Jiakai Wang, Dong Wang, Yang Liu 等 12 位作者
Complex information seeking on the Web often requires collecting evidence from multiple documents and reasoning across them, as in multi-hop question answering. Multi-agent systems address such tasks by dividing work among specialized agents, where upstream agents produce intermediate answers and supporting evidence that downstream agents build upon. However, upstream answers vary in correctness, and most systems provide no quantitative signal about it, leaving the downstream agent to judge whether to trust or verify what it receives based solely on the textual evidence. In this paper, we propose MASCAL. Each agent learns to produce a correctness probability for its answer by jointly optimizing task performance and confidence calibration in reinforcement learning; the upstream agent passes this probability at handoff, giving the downstream agent a quantitative basis for its decisions, and the final answer also carries a calibrated probability, quantifying the reliability of the system output. To guide the downstream agent in using this signal during training, we introduce confidence-aware weighting, which increases the learning weight at positions responsive to the upstream probability, so that the agent learns more from decisions where it actively uses the signal. Across three collaboration architectures spanning Web retrieval and reasoning tasks, MASCAL improves task accuracy and calibration quality for both agents, and generalizes to deeper collaboration chains and different model scales. Intervention analysis confirms that upstream confidence affects downstream decision behavior, and the learned final confidence supports selective answering and targeted rechecking.
Xiaoyi Chen, Yifei Gao, Yang Xu, Zhenlong Wang, Jian Yan, Jiming An, Xingxing Song, Liqun Deng 等 12 位作者
Exploratory GUI testing is a particularly demanding setting for MLLM agents: without predefined test scripts, an agent must autonomously navigate an application and discover defects through its own interaction. However, current evaluation falls short on two fronts. First, existing benchmarks focus almost exclusively on interaction defects, leaving display defects outside the evaluation frame. Second, evaluation protocols are bound to predefined defect annotations, collapsing the testing process into a single end-state judgment that conflates qualitatively distinct failure modes. To address these challenges, we present GUITestScape, an interactive benchmark covering 61 real-world Android applications and 508 preset defects spanning interaction and display types, and introduce GUIJudge, an open-set evaluator that decomposes an agent's testing trajectory into independently diagnosable capabilities. Experimental results demonstrate that GUIJudge achieves reliable process-aware evaluation beyond predefined annotations, substantially outperforming all baselines. Benchmarking on GUITestScape further reveals that detection remains the critical bottleneck for existing models across both defect types, and that integrating GUIJudge's verifiers into existing agents significantly boosts their detection performance without retraining.
Ke Zou, Nan Zhou, Tao Yang, Meng Liu, Linchao He, Zehui Liao, Ling Huang, Guangren Huang 等 12 位作者
Medical vision-language models (VLMs) show strong performance in radiology report generation (RRG) and medical visual question answering (Med-VQA), producing free-form clinical descriptions and answers from medical images. However, they may generate clinically meaningful statements that lack visual evidence or contradict image content. We refer to these errors as visually irrelevant hallucinations and investigate them at the phrase level. We propose CLEAR (Counterfactual Localized Evaluation of Alignment and Response), a model-agnostic post-hoc framework for phrase-level hallucination risk estimation. CLEAR decomposes generated responses into visually assessable clinical phrases. For each phrase, phrase-conditioned grounding identifies a candidate visual region, which is selectively perturbed by a localized counterfactual intervention. CLEAR characterizes the intervention using two complementary auditing cues: response cues, capturing semantic and clinically meaningful changes in the generated response, and alignment cues, measuring changes in image-phrase compatibility. These cues are normalized and jointly modeled to estimate phrase-level hallucination risk. Across four datasets spanning RRG and Med-VQA, CLEAR outperforms state-of-the-art hallucination detection baselines across multiple medical and general-purpose VLMs. On MIMIC-CXR, CLEAR improves AUPRC from 85.10% to 90.23%. Its effectiveness is further validated on a GT-derived controlled VIH benchmark. These results establish visually irrelevant hallucination as an important fine-grained reliability failure mode in medical VLMs and demonstrate the value of model-agnostic visual-support auditing for more trustworthy multimodal clinical generation.
Weiyu Han, Haoyu Jiang, Jie Sheng, Ruobing Zuo, Huilin He, Ze Zhao, Xiao Tan, Nairong Zhang 等 10 位作者
Ant International accumulates large volumes of transaction history across users and payment businesses. Confirmed fraud and chargeback outcomes, by contrast, are scarce, delayed, and specific to each business. A single encoder pretrained on unlabeled histories could serve all businesses, but only if pretraining captures the behavior that separates risk. Coarse activity differences can make contrastive pretraining on transaction logs too easy: transaction volume, amount, and timing can distinguish a history's continuation from arbitrary candidates without modeling how payment resources are used. We present TRIDENT-Seq, a transaction foundation model trained with Prefix-Future Contrast (PFC). PFC matches each prefix to a summary of its subsequent behavior among candidates with similar activity profiles; activity prediction and dispersion regularization act on the encoder output. Across three production payment businesses, the pretrained encoder improves average precision (AP) and recall at a 0.5% intervention budget over architecture-matched scratch training in all six business-budget settings. With a fixed validation set, it exceeds full-label scratch training in mean AP and recall using 10% of the training labels on Wallet and 25% on Shopping and SME. Pretraining only on another business's histories still helps. Replacing profile-matched candidates with random ones cuts recall from 24.62% to 5.64%. In Ant International's deployment evaluation, recorded amount-based chargeback and overall loss rates are 37.7% and 37.9% lower than those of the previous XGBoost-based system under the same intervention budget.
Agent skills package instructions, scripts, and resources for specialized tasks and are increasingly distributed through public Web repositories. However, existing skill benchmarks primarily focus on downstream task execution, insufficiently assessing specification quality, behavioral robustness, semantic alignment, and responsibility boundaries. Their reliance on task-specific tools, environments, and repeated executions limits scalability and pre-deployment assessment. To address these challenges, we introduce SkillCT, a benchmark that broadens skill assessment from downstream utility to a multidimensional characterization of skill quality. SkillCT evaluates skills across nine complementary dimensions spanning three aspects: Static Assessment, which captures intrinsic properties of the skill specification; Dynamic Assessment, which measures whether the induced behavior remains stable across backbone models and request variations; and Human-Assisted Assessment, which examines behavior-chain consistency and task granularity. These dimensions provide a broader view of skill quality than execution success. Applying SkillCT to a public skill corpus establishes a reference benchmark for analyzing quality weaknesses and relationships across dimensions. Building on this benchmark, we propose an execution-free quality evaluation baseline that predicts the multidimensional quality profiles of unseen skills by retrieving and leveraging similar reference skills, without executing the skills under evaluation. This reduces token consumption and evaluation time, while preserving consistency with the full assessment. Furthermore, SkillCT-guided optimization improves downstream task success and execution efficiency, demonstrating its value for skill refinement. These findings highlight the effectiveness of SkillCT in supporting scalable skill assessment, optimization, and repository maintenance.
Real-world forgery is inherently heterogeneous: it manifests not only as digital manipulation but also as physical spoofing, and is carried not only by images but also by videos. Despite substantial progress, a unified anti-forgery foundation model covering such a broad threat spectrum remains absent. In this paper, we present Venus-DefakerOne2, which substantially extends the forensic capability boundary along both the forgery-form and media-type dimensions. Trained on tens of millions of open-source and in-house samples, it incorporates two key designs. Tide-Style-Tuning alternates LoRA and full-parameter fine-tuning to balance computational efficiency, generalization, and hard-sample fitting while mitigating catastrophic forgetting. Entropy-based Test Adaptation determines the optimal prediction modality by analyzing prediction entropy. Venus-DefakerOne2 achieves new state-of-the-art performance across a comprehensive suite of benchmarks, including DeepFake faces (96.7%), AI-generated images (93.3%), tampered documents (87.6%), manipulated natural images (89.6%), physical spoofs (93.1%), and AI-generated videos (96.0%). It significantly outperforms both specialized expert models and its predecessor, DefakerOne, establishing itself as a powerful and versatile foundation model for binary-decision forensic tasks.
Auto-bidding systems optimize bids to maximize value under efficiency constraints such as Cost-Per-Action (CPA). Existing methods treat each day as an independent episode. However, many advertisers produce value so sparsely that per-day efficiency ratios become statistically unreliable, undermining advertiser retention. Platforms therefore evaluate window-level efficiency over sliding windows of $W{=}7$ days, ensuring fair evaluation and long-term advertising effectiveness. This creates cross-episode coupling: each day's bidding decisions affect up to $W$ overlapping windows, so setting daily targets requires anticipating future market conditions. We propose SWAG-Bid (Sliding-Window Aware Generative Auto-Bidding), a hierarchical framework decomposing this challenge into episode-level planning and step-level execution. The planner uses a Masked Trajectory Model to forecast markets and generate candidate plans, scored across all overlapping windows by Multi-Window Model Predictive Control Sampling (MWMS) with exponential confidence decay. The controller adjusts reliance on this guidance through a state-adaptive gate, Per-Step Gated Adaptive Layer Normalization (PSG-AdaLN), complemented by Return-to-Go and Cost-to-Go channels carrying budget and constraint information. Experiments on AuctionNet-Sparse and online A/B tests on AliExpress show that SWAG-Bid achieves competitive constraint satisfaction and value acquisition under sliding-window evaluation.
Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, Lijie Hu
Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear, and no standard procedure tests an individual skill before installation. We present swe-skills-bench, a skill-centric, requirement-driven benchmark that measures how much individual agent skills improve performance on real-world software engineering (SWE) tasks. We start from 98 public SWE skills, each paired with a real GitHub repository pinned at a fixed commit. For each skill, we derive repository-specific requirements, create executable verifiers, and build a reproducible environment. Under each of four agent-model configurations, we run every task once without the skill and once with it, yielding 3,920 paired evaluations. For each requirement, we compute a paired delta, i.e., the change in outcome when the skill is added. We then aggregate these deltas across a skill's ten requirements into a per-skill utility profile, and use a statistical test to classify each skill as Golden (significantly helpful), Ineffective (no significant effect), or Harmful (significantly detrimental). Our results show that skills provide limited benefits: 92 of 98 skills have no statistically significant effect, and adding skills raises the average pass ratio only from 76.6% to 76.9%. The few helpful skills supply procedures that the agent would otherwise omit (gains of up to $+17.7$ points). In contrast, harmful skills anchor the agent on their own templates and override the task's explicit instructions (losses of up to -17.0 points). Our code is available at https://github.com/ControllableModel/SWE-Skills-Bench.
Zhangkai Wu, Xu Zhang, Zhihong Cui, Yiqi Wang, Yi Zhang
Tabular foundation models (TFMs) are being applied to Web data streams such as network intrusion detection, where they adapt by updating the labelled rows of their context without retraining. When a past concept returns after leaving the context, a TFM faces a recall-or-relearn decision between restoring stored rows of the concept and relearning it from new labels. We propose MICE (Mixture of In-Context Experts), a training-free learner that cuts the stream into segments at detected changes. It merges a closed segment into a stored context when the TFM's estimated additional error on the segment is within a tolerance, under a capacity limit on stored contexts. A fast level weights the stored contexts and first-in-first-out (FIFO) windows by the log-loss of their predictions on the last labelled batch. We show that, with pure stored contexts and a margin condition, this fast level gains over relearning, in expected accuracy, the normalised positive area between the stored context's accuracy and the TFM's learning curve, up to a first-batch term. A slow level mixes the fast level's prediction with that of the FIFO window of the last labelled rows and bounds the discounted half-Brier regret of MICE against this window at every time. Learning curves measured beforehand predict the ordering of the observed recall gains. MICE outperforms reset, which empties the context at detected drifts, on grid streams with random boundary phases. Merging keeps fewer experts than pools that store every segment, and with fixed segmentation a time-matched snapshot pool matches MICE on the shifted grid. On real streams, MICE has the highest mean accuracy of all policies we compare.
Multi-path reasoning methods such as self-consistency (SC) sample $K$ reasoning paths and choose the most frequent answer. However, their gains quickly plateau as $K$ increases, and locating this saturation point currently requires fitting a scaling model to accuracies measured at several values of $K$ or stopping online per query. We formalize multi-path LLM reasoning as a diversity combining problem from wireless communications: each path is a noisy channel observation, and the pairwise correlation of path correctness caps the design-effect effective sample size of the vote at a finite ceiling. Generalized least squares (GLS) analysis shows that, for paths with equal gains, the optimal linear combiner of latent embeddings is uniform exactly when every row of the path covariance has the same sum, as under exchangeability, supporting majority vote as the natural default in standard SC while leaving room for weighting or pruning under heterogeneous prompt-template branches. Across 5 models and 12 benchmarks, prompt-template diversity reduces path correlation in $55$ of $60$ model-benchmark cells, with a mean relative reduction of $16\%$ and reductions in every task domain. We derive an Adaptive-K rule that uses a four-path pilot to select $K^*$, retaining $96$--$103\%$ of MV@$K{=}32$ accuracy across Math, QA, and NLU.
Clinical trial prescreening requires distinguishing unmet conditions from insufficient evidence in patient records. Given patient records, criterion questions, and predefined answer options, we retrospectively compared JEV, a non-generative decision model returning native option probabilities, with schema-constrained Qwen Flash across 2,048 test patient-condition pairs from TrialGPT and question-answer datasets derived from MIMIC-III and MIMIC-IV, all evaluated under strict Zero Data Retention (ZDR) policies to ensure clinical data privacy. Both models assessed conditions individually or in batches sharing the same patient context, with performance measured against reference labels. In batch mode, JEV and Qwen achieved similar macro-F1 scores on TrialGPT (0.652 vs. 0.660) and MIMIC-IV (0.807 vs. 0.814), whereas JEV substantially outperformed Qwen on MIMIC-III (0.768 vs. 0.534; $Δ$ = +0.234, 95% CI: 0.187-0.281). This advantage largely reflected higher recall for conditions labeled as having insufficient information (56.3% vs. 9.9%). Across all three datasets, JEV also had lower observed median job latency (1.18-1.40 vs. 2.80-8.90 s) and 53%-74% lower estimated cost per condition. These findings position JEV as an initial assessment component that provides criterion-level judgments and flags potential information gaps for review. JEV's observed errors in interpreting clinical evidence underscore the need to verify its outputs against patient records before they inform eligibility decisions.
Ziyun Chen, Yijun Wang, Chuanyi Zhang, Liang Yao, Yuexuan An, Xiang Gu, Wei Zhou, Fan Liu
Referring expression segmentation (RES) aims to localize targets at the pixel level guided by human instructions. However, current models predominantly follow a text-centric paradigm that treats discrete text as the primary interaction medium for these human instructions. This assumption is especially limiting in unmanned aerial vehicle (UAV) applications, where rapid response, hands-free operation, and natural communication are often critical. In this paper, we reconstruct UAV referring expression segmentation through an audio-centric perspective. Grounded in information theory, we demonstrate that raw audio provides a higher upper bound for extracting rich semantic features than transcribed text. To achieve this, we construct an audio-driven UAV referring expression segmentation benchmark named Aerial-AudioRES by augmenting VisDrone with synthesized speech, forming "audio-text-image-mask" quadruples. Specifically, we employ an ambiguity filtering mechanism to ensure referential uniqueness, and incorporate eight distinct timbres alongside 4 realistic noises to simulate authentic environments. To drive the paradigm shift from text-centric to audio-centric, we propose the end-to-end Audio-centric Referring Expression Segmentation Network (ARES-Net). Distinct from discrete text-visual matching, our approach learns to establish a direct soft alignment between continuous acoustic manifolds and multi-scale visual representations. Comprehensive experiments show that our method obtains a peak accuracy of 64.23% in oIoU and demonstrates robust generalization on a collected real-human test set. Furthermore, it significantly reduces total interaction latency to one-third of the text-based method. Our code is available at https://github.com/LemonGauss/ARES-Net.
Jiacheng Zhang, Xueyi Zhang, Xin Lu, Siqi Cai, Haizhou Li
Electroencephalography (EEG) is widely used in clinical assessment, brain-computer interfaces, and cognitive-state analysis, yet EEG modeling remains fragmented across task paradigms. Recent multimodal large language models (MLLMs) provide a promising interface for flexible multimodal reasoning, but their ability to understand EEG inputs remains limited. In this work, we propose OneEEG, a unified EEG-MLLM framework for multi-task EEG understanding. By training on our curated OneEEG-Instruct, a multi-task EEG instruction-tuning dataset, OneEEG jointly models numerical EEG representations and visual EEG representations, and introduces a task-aware Mixture of Projectors (MoP) to align heterogeneous EEG features across different task families with the LLM embedding space. We further establish OneEEG-Bench, a benchmark for evaluating current MLLMs and our method on multi-task EEG understanding. Experiments show that existing MLLMs have limited ability to interpret EEG inputs, while OneEEG achieves stronger performance by integrating numerical and visual EEG representations with task-aware EEG-to-LLM projection. Extensive ablations and analyses further reveal the effects of visual EEG renderings, MoP variants, router behavior, and feature dispersion across EEG tasks.
Yixuan Chen, Hongyu Zhan, Jie Sheng, Weiyu Han, Shuai Chen, Tianyi Zhang, Xiao Tan, Jun Xia
Financial fraud detection increasingly relies on heterogeneous transaction graphs, in which entities such as cards and merchants play distinct business roles and the risk meaning of an attribute depends on the entity's role: a high transaction volume may be routine for a merchant but unusual for a card. Heterogeneous graph neural networks preserve typed entities and relations but typically treat these attributes as role-agnostic inputs and leave their business meaning implicit. Meanwhile, most existing methods integrating large language models (LLMs) with graphs focus on homogeneous graphs or heterogeneous graphs with naturally available textual attributes, leaving their use on transaction graphs with structured attributes underexplored. To address this issue, we propose SemHGT, an LLM-enhanced framework that interprets structured attributes according to entity roles and makes the business semantics explicit in three stages: (1) role-aware prompts elicit risk-related business descriptions from node attributes, and a text encoder maps them to semantic vectors that enrich node representations; (2) semantic similarity guides multi-round sampling of target-specific path instances under transaction-to-transaction schemas; (3) schema-level tokens that combine local path evidence with global neighbor summaries are processed together with the target transaction by a unified transformer. Across three benchmark datasets, SemHGT leads the evaluated baselines on most dataset--metric comparisons. Further analyses provide additional evidence for the effectiveness of SemHGT's design and clarify how its semantic modeling and evidence selection contribute to fraud detection. Code is available at https://anonymous.4open.science/r/SemHGT-528A/.
Runsong Jia, Qian Chang, Mengjia Wu, Ciprian Doru Giurcăneanu, Jie Lu, Yi Zhang
Retrieval-augmented generation (RAG) grounds language models in retrieved evidence, but its outputs often contain claims unsupported by that evidence. Recent multi-agent RAG systems decompose the pipeline into cooperative decisions, yet they typically optimize all agents under a shared task reward such as EM or F1, which measures answer overlap rather than faithfulness to evidence. We propose a hallucination-aware multi-agent RAG framework that combines the task reward with an internal hallucination-risk signal computed from the generator's attention-head norms. Three role-specific LoRA adapters, a query planner, an evidence selector, and an answer generator, share a frozen backbone. A lightweight critic is trained once on TruthfulQA truthful/false pairs and then kept frozen, providing a complementary risk score that is added to the shared reward during cooperative PPO training. Across three backbones (Qwen3-8B, Llama3-8B, Llama2-13B) and three benchmarks (RAGTruth, HotpotQA, 2WikiMultiHopQA), our method improves task performance and reduces hallucination rates over the strongest multi-agent baseline. Ablations and critic diagnostics show that the TruthfulQA-calibrated signal provides useful reward shaping that transfers across RAG tasks.
Guoyi Zhang, Yanjin Du, Guangsheng Xu, Zhengyao Zhao, Siyang Chen, Jingjing Gao, Yuezheng Zhou, Yiyang Wu 等 19 位作者
Small uncrewed underwater vehicles are proliferating and threaten maritime security, yet evade sonar and magnetic sensors built for larger submarines. Infrared thermal wakes, generated by hydrodynamic displacement that modulates the cold-skin layer, offer a non-acoustic, non-magnetic alternative even without cooling-water discharge. Existing studies, however, rely on idealized simulations that fail to capture real-world backgrounds, offering limited guidance for target-background discrimination. We establish AVP-IR-Wake, the first large-scale, real-world, physically diverse benchmark of 161,485 frames collected over three years. We show that thermal wakes are extended structures of discrete vortices, violating the compactness assumption of conventional targets. We reveal local indistinguishability: individual wake vortices are statistically identical to wind-induced background vortices in temporal, frequency, and sparse domains, sharing low-frequency information and long-range correlations. This challenges the assumptions of compact, transient, high-frequency targets in conventional detection. Yet we establish global morphological separability: although locally inseparable, the wake as a whole is organized by vehicle trajectory, whereas background clutter is organized by wind-driven thermal fronts. This explains why representative detectors fail and shows that reliable detection must shift from local feature extraction to global trajectory-constrained physical modeling. Because the cold-skin layer varies globally and seasonally, forecasting wake observability will require integrating physical oceanography and atmospheric science, linking underwater surveillance to the changing ocean surface.
Yuyi Zhang, Boyu Tang, Tianjie Ju, Sufeng Duan, Gongshen Liu
Latent tokens are gaining attention for enhancing reasoning in large language models (LLMs), yet their internal mechanisms remain unclear. This paper examines the problem from a reliability perspective, uncovering fundamental weaknesses: latent tokens function as uninterpretable placeholders rather than encoding faithful reasoning. While resistant to perturbation, they promote shortcut usage over genuine reasoning. We focus on Chain-of-Continuous-Thought (COCONUT), which claims better efficiency and stability than explicit Chain-of-Thought (CoT) while maintaining performance. We investigate this through two complementary approaches. First, steering experiments perturb specific token subsets, namely COCONUT and explicit CoT. Unlike CoT tokens, COCONUT tokens show minimal sensitivity to steering and lack reasoning-critical information. Second, shortcut experiments evaluate models under biased and out-of-distribution settings. Results on MMLU and HotpotQA demonstrate that COCONUT consistently exploits dataset artifacts, inflating benchmark performance without true reasoning. These findings reposition COCONUT as a pseudo-reasoning mechanism: it generates plausible traces that conceal shortcut dependence rather than faithfully representing reasoning processes.
Zezhou Wang, Ziyun Zhang, Xiaoyi Zhang Microsoft, Zhuzhong Qian, Yan Lu Microsoft Research Asia
Vision-language models are increasingly deployed as computer-use agents (CUAs) that operate desktops and browsers. Top-performing CUAs are framework-based systems that decompose planning and execution, while end-to-end screenshot-to-action policies are easier to deploy but lag behind on benchmarks such as OSWorld-Verified. GUI datasets like OSWorld pose two bottlenecks: they expose only a few hundred interactive, verifiable tasks and environments, and expert trajectories must be gathered by interacting with these environments, making such data hard to scale. We therefore ask how reinforcement learning from verifiable rewards (RLVR) can best exploit a small pool of exist expert trajectories to train end-to-end policies. Na"ively mixing these off-policy traces into on-policy RLVR is brittle: even after format conversion, expert trajectories exhibit structural mismatch and distribution shift from the learner. We propose BEPA (Bi-Level Expert-to-Policy Assimilation), which turns static expert traces into policy-aligned guidance via self-rolled reachable trajectories under the base policy (LEVEL-1) and a per-task, dynamically updated cache used in RLVR (LEVEL-2). On OSWorld-Verified, BEPA improves UITARS1.5-7B success from 22.87% to 32.13% and raises a held-out split from 5.74% to 10.30%, with consistent gains on MMBench-GUI and Online-Mind2Web. Our code and data are available at an anonymous repository: https://anonymous.4open.science/r/ACL_BEPA.
尚无 AI 解读，展示原文摘要
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
Xianzhen Luo Harbin Institute of Techology, Wenzhen Zheng, Qingfu Zhu Harbin Institute of Technology, Rongyi Zhang, Houyi Li Fudan University, Siming Huang, YuanTao Fan, Wanxiang Che Harbin Institute of Technology
Code Large Language Models (LLMs) are revolutionizing software engineering. However, scaling laws that guide the efficient training are predominantly analyzed on Natural Language (NL). Given the fundamental differences like strict syntax between code and NL, it is unclear whether these laws are directly applicable to code. To address this gap, we conduct the first large-scale empirical study of scaling laws for code, comprising 117 experimental runs with model sizes from 0.2B to 3.8B and training tokens from 2B to 128B. We fit the Chinchilla law and the Farsser law. First, the results show that the more expressive Farseer law offers greater accuracy. Second, the analysis reveals that Code LLMs scale effectively with model size. Crucially, code represents a more data-hungry regime, requiring a substantially higher data-to-parameter ratio than NL. Finally, two additional sets of experiments on code-NL mixtures show that NL benefits resource-constrained scenarios, but becomes a detriment at higher compute budgets.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yifei Gao, Junhong Ye Beijing Jiaotong University, Yifan Yang, Jiaqi Wang, Yi Zhang Ant Group, Zhang Ruichen, Jitao Sang Beijing Jiaotong University
Recent advances in large language models (LLMs) have enabled increasingly capable web agents, yet training such agents still relies on high-quality interaction trajectories that are difficult to obtain at scale. We identify two key challenges: (1) Infrastructure Overhead, where network instability and website access restrictions limit data collection scalability; and (2) Constrained Exploration, where irreversible state transitions preclude tree-based search and thus limit trajectory diversity. To address these challenges, we introduce WebSynthesis, a framework for scalable trajectory synthesis. WebSynthesis employs an LLM-based World Model to simulate state transitions without network dependencies, and integrates Monte Carlo Tree Search to enable reversible exploration over the simulated state space. Experiments on WebArena, WebVoyager, and Mind2Web-Online demonstrate that agents trained exclusively on synthesized trajectories outperform those trained on real-world data, providing a viable alternative to costly real-world data collection.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yuyi Zhang South China University of Technology, Junle Liu, Peirong Zhang, Jianliang Liu South China University of Technology, Zhenhua Yang, Lianwen Jin
Inscriptions are invaluable cultural heritage, yet centuries of degradation (e.g., fractures, erosion, oxidation) have rendered many partially illegible. Existing Historical Inscription Restoration (HIR) methods rely on task-separated pipelines with irreversible error accumulation and patch-based generation that sacrifices page-level consistency. Therefore, we present UniHIR, the first unified MLLM for end-to-end historical inscription restoration. It integrates two novel designs, Draft-Guided Localization and Hierarchical Self-Refinement, to enable accurate damage localization and illegible-content prediction via iterative reasoning and self-correction. This unified approach enables true page-level restoration with consistent typography and style. To support training under high-resolution inputs and long sequences, we design UHIRFactory and construct HIRBench, enabling step-wise, memory-efficient instruction tuning with step-aware annotations for intermediate drafts and refinements. Experiments demonstrate that UniHIR achieves superior performance in both text restoration accuracy and appearance restoration quality, validating that HIR can be effectively tackled by a standalone model in a unified manner. The model and code are available at https://github.com/ZZXF11/UniHIR.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Ziyun Zhang, Zezhou Wang, Xiaoyi Zhang Microsoft, Zongyu Guo Microsoft Research, Jiahao Li Microsoft Research Asia, Bin Li Microsoft, Yan Lu Microsoft Research Asia
GUI agents that interact with graphical interfaces on behalf of users are a promising direction for practical AI assistants, yet training them is hindered by scarce suitable environments. We present InfiniteWeb, a system that automatically generates functional web environments at scale for GUI agent training. While LLMs perform well on generating a single webpage, building a realistic and functional website with many interconnected pages faces challenges. We address these challenges through unified specification, task-centric test-driven development, and combining website seed variation with reference design images. Our system also generates verifiable task evaluators enabling dense reward signals for reinforcement learning. Experiments show that our system surpasses commercial coding agents at realistic website construction, and GUI agents trained on our generated environments achieve significant performance improvements on OSWorld and Online-Mind2Web, demonstrating the effectiveness of the proposed system.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Weicheng Lin Shenzhen University, Yi Zhang Shenzhen University, Jiawei Dang Shenzhen University, Liang-Jie Zhang Shenzhen University
Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning method for large language models, with its effectiveness largely influenced by the allocation of ranks and scaling factors, as well as initialization. Existing LoRA variants typically address only one of these factors, often at the cost of increased training complexity or reduced practical efficiency.In this work, we present Task-aware Low-Rank Adaptation (TLoRA), a unified framework that jointly optimizes initialization and resource allocation at the outset of training. TLoRA introduces a data-driven initialization strategy that aligns the LoRA A matrix with task-relevant subspaces by performing singular value decomposition on the product of pre-trained weights and input activation covariance. After this, the A matrix is frozen, and only the B matrix is trained. Furthermore, TLoRA employs a sensitivity-based importance metric to adaptively allocate ranks and scaling factors across layers under a fixed parameter budget.We conduct extensive experiments that demonstrate TLoRA consistently performs excellently across various tasks, including natural language understanding, commonsense reasoning, math reasoning, code generation, and chat generation, while significantly reducing the number of trainable parameters. Our code are available at https://github.com/Rambo-Yi/TLora/tree/main
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Jiayi Zhang, Shu Yang, Junchao Wu University of Macau, Derek F. Wong University of Macau, Di Wang KAUST
Fine-tuning Large Language Models on a political topic will significantly manipulate their political stance on various issues and unintentionally affect their stance on broad topics. While previous studies have proposed this issue, there is still a lack of understanding regarding the internal representations of these stances and the mechanisms that lead to unintended cross-topic generalization. In this paper, we systematically explore the internal mechanisms underlying this phenomenon from a neuron-level perspective and how to mitigate the cross-topic generalization of political fine-tuning. Firstly, we propose Political Neuron Localization through Activation Contrasting (PNLAC) to identify two distinct types of political neurons: general political neurons, which govern stance across multiple political topics, and topic-specific neurons that affect the model’s political stance on individual topics. We find that these political neuron types exist in the middle and later layers across four models and datasets through activation patching experiments. Leveraging these insights, we introduce InhibitFT, an inhibition-based fine-tuning method that effectively mitigates the cross-topic stance generalization. Experimental results demonstrate the robustness of the identified neuron types across various models and datasets and show that InhibitFT significantly reduces the cross-topic stance generalization by 20% on average while preserving topic-specific performance. Moreover, we demonstrate that selectively inhibiting only 5% of neurons is sufficient to effectively mitigate the cross-topic stance generalization.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zihan Gu Institute of Information Engineering, Chinese Academy of Sciences, TianYi Zhang University of the Chinese Academy of Sciences, Xinyan Zhang independent, Zhiyuan Wang, Han Zhang, Yuhao Wei, Jiacheng Lu Shanghai Jiao Tong University, Tianyi Ma 等 11 位作者
Model editing provides a promising mechanism for updating large language models (LLMs) without expensive retraining. Existing approaches, particularly locate-and-edit methods based on least-squares optimization, aim to introduce targeted knowledge changes while preserving pre-trained behavior. In this work, we show that this objective is fundamentally fragile under standard single-edit evaluation protocols. We first develop a unified theoretical framework that characterizes activation-based editing as a constrained intervention on intermediate representations. Within this framework, we demonstrate that least-squares edits cannot, in general, isolate target updates from unrelated activations, giving rise to unavoidable interference that accumulates with successive edits. Crucially, this degradation can remain undetected in single-edit settings when assessed using conventional success and locality metrics. To expose such hidden instabilities, we introduce an uncertainty-based evaluation protocol that combines structured semantic perturbations with uncertainty quantification based on Sampling with Perturbation for UQ. By measuring edit-induced growth in aleatoric and epistemic uncertainty, our method reveals local knowledge conflicts that are invisible to existing benchmarks. Extensive experiments across multiple models, datasets, and editing algorithms show that both least-squares and other parameter-update-based methods consistently increase post-edit uncertainty. Together, our results suggest that current evaluation practices substantially overestimate the reliability of single-edit model editing, and that uncertainty-based diagnostics are necessary for assessing edit stability.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yunzhe Wang University of Southern California, Runhui Xu University of Southern California, Kexin Zheng University of Southern California, Tianyi Zhang, Jayavibhav Niranjan Kogundi, Soham Hans University of Southern California, Volkan Ustun USC Institute for Creative Technologies, University of Southern California
Multimodal LLMs are increasingly deployed as perceptual backbones for autonomous agents in 3D environments, from robotics to virtual worlds. These applications require agents to perceive rapid state changes, attribute actions to the correct entities, and reason about concurrent multi-agent behaviors from a first-person perspective, capabilities that existing benchmarks do not adequately evaluate. We introduce GameplayQA, a framework for evaluating agentic-centric perception and reasoning through video understanding. Specifically, we densely annotate multiplayer 3D gameplay videos at 1.22 labels/second, with time-synced, concurrent captions of states, actions, and events structured around a triadic system of Self, Other Agents, and the World, a natural decomposition for multi-agent environments. From these annotations, we refined 2.4K diagnostic QA pairs organized into three levels of cognitive complexity, accompanied by a structured distractor taxonomy that enables fine-grained analysis of where models hallucinate. Evaluation of frontier MLLMs reveals a substantial gap from human performance, with common failures in temporal and cross-video grounding, agent-role attribution, and handling the decision density of the game. We hope GameplayQA stimulates future research at the intersection of embodied AI, agentic perception, and world modeling.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI · cs.MA · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Chien Van Nguyen University of Oregon, Huy Huu Nguyen, Ruiyi Zhang, Hanieh Deilamsalehy Adobe Systems, Puneet Mathur Adobe Systems, Viet Dac Lai Adobe Systems, Haoliang Wang Adobe Research, Jayakumar Subramanian Adobe Systems 等 13 位作者
We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe computational and memory bottlenecks with long sequences due to the quadratic complexity of softmax attention and the growing Key-Value (KV) cache that makes inference memory-bound by context length. Lizard addresses these limitations by introducing a subquadratic attention mechanism that closely approximates softmax attention while preserving model quality. Unlike prior linearization methods constrained by fixed, non-adaptive structures, Lizard augments the architecture with compact, learnable modules that enable adaptive memory control and robust length generalization. Moreover, we introduce a hardware-aware algorithm that solves numerical instability in gated attention to accelerate training. Extensive experiments show that Lizard achieves near-lossless recovery of its teacher model’s performance, significantly outperforming previous methods by up to 9.4 - 24.5 points on the 5-shot MMLU benchmark and demonstrating superior associative recall.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表