NVIDIA, :, Anis Ahmad, Jon Allen, Malik Aqeel Anwar, Jesse Archer, Maciej Bala, Piotr Barejko 等 90 位作者
We present a shared framework that adapts Cosmos world foundation models for real-time interactive world simulation in Physical AI. By streaming visual observations in response to actions and scene controls, the framework enables users and embodied agents to interact with evolving virtual environments. It supports both predicting the visual consequences of actions and generating observations from physical state maintained by an external simulator. We demonstrate this approach across camera navigation and robot manipulation, controllable video transfer, and multi-view autonomous vehicle (AV) simulation. These examples provide a shared foundation for developing interactive virtual environments for Physical AI training and evaluation. Our code and model checkpoints are available at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3-examples. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos-simulation.
Zezhou Wang, Hanzhang Zhou, Panrong Tong, Quyu Kong, Pengxiang Li, Steven Hoi, Zhuzhong Qian, Yue Wang
Scaling GUI reinforcement learning requires environments that preserve real-app behavior. Yet coupling behavior inference with coding can turn partial traces into runnable mocks with incorrect state transitions. We introduce \textbf{Trace2World}, which separates global behavior reconstruction from implementation. It reconciles traces into a shared, source-linked app model, then compiles an executable environment. Independent replay of source workflows localizes mismatches for bounded implementation repair. Validated worlds then support learner-adaptive task and environment augmentation within source-supported behavior. From 1,570 traces, Trace2World constructs 50 environments. On 200 workflows across ten apps, 91.1% are reproduced end to end, versus 59.8% for the strongest matched task-local baseline. Source-grounded validation retains 94.0% of simulated training gains on real devices, versus 54.7% under self-validation. Learner guidance raises benchmark success from 56.9% to 61.1%. Training in Trace2World further improves the model by 20.2 points on our benchmark, 5.4--16.2 points across four external GUI benchmarks, and 16.3 points on 100 real-device tasks. Reliable reconstruction separates what behavior source evidence supports from whether the implementation preserves it.
Yuqian Wu, Qingxiang Liu, Yuxin Guo, Weifeng Su, Jian Li, Pengfei Xu, Xi Chen, Yutao Yue 等 9 位作者
Time series forecasting is critical for demand prediction and resource management in modern Web services, yet applying pretrained Time Series Foundation Models (TSFMs) to downstream tasks remains challenging due to domain shifts. Existing retrieval-augmented approaches typically retrieve coarse-grained window contexts and may introduce context-specific noise. To address this problem, we argue that temporal patterns should be reused at a decomposition level, as effective trend and seasonal dynamics may originate from different contexts. We propose \method, a two-stage \underline{F}ine-grained \underline{K}nowledge \underline{A}ugmentation framework that decouples and consolidates pre-training knowledge into compact, task-shared residual codebooks to enhance frozen TSFMs. Specifically, Stage I constructs dual-branch residual codebooks for decoupled trend and seasonal signals, while Stage II dynamically retrieves and merges these fine-grained patterns into target representations via task-adaptive aggregation and gate fusion. Extensive experiments across eight real-world benchmarks with four representative TSFM backbones demonstrate the superior effectiveness and computational efficiency of \method, while further validating the strong transferability of the residual codebooks across different backbones. The source code is available at the anonymous repository: https://github.com/yuppielqx/TSFM-Component-Token-Adapter
Coarse-to-fine image-to-point-cloud (I2P) registration risks discarding correct but ambiguous patch pairs, while retaining more candidates repeats fine matching over overlapping patches. SparseGraph-I2P aims to improve registration recall by increasing the inlier ratio at the pose solver, using sensor or monocular depth. A Coarse Hypothesis Graph combines appearance with depth-derived first- and second-order compatibility to select a fixed budget of patch pairs. Sparse Fine Matching decodes each queried pixel once and skips pixel--point comparisons covered by an ancestor patch paired with the same point-cloud region. With sensor depth, depth-aware filtering ranks correspondences by SC2 spectral support for a single EPnP solve. With monocular depth, depth or inverse depth is calibrated from correspondence geometry before filtering. SparseGraph-I2P achieves the highest registration recall and lowest latency among the compared methods on RGB-D Scenes V2 and 7-Scenes with sensor depth. With predicted depth, it retains the highest recall on RGB-D Scenes V2 at an additional calibration cost. Code will be released.
Answering geographic queries over Earth observation (EO) archives requires solving a joint retrieval-and-derivation problem under strict spatiotemporal constraints. Existing LLM agents fail to ground observation items or suffer from search-space explosion. We propose OSGR, a two-stage framework that factorizes this search into offline symbolic concept deduction and online Relation-Conditioned Grounding. OSGR leverages an offline Observation-Support Graph to deduce valid target-to-result support paths at the concept level, and applies spatiotemporal compatibility kernels to instantiate grounded observation-item sets. On Earth-Bench and DisasterM3-Reason, OSGR improves GPT-4o accuracy from 49.3\% to 63.7\% while reducing the execution-step ratio from 2.9 to 2.5.
Humanoid locomotion requires deciding where to step and how to distribute contact forces. However, a disturbance can invalidate the nominal plan, requiring coordinated revision under constraints that switch with every footfall. To solve this online, the proposed approach employs the single-rigid-body model, which retains attitude dynamics and the full contact wrench. An iterative linear-quadratic-regulator MPC (iLQR-MPC) then jointly optimizes contact forces and footstep locations in a single receding-horizon problem, without a separate step planner. Specifically, contact and motion constraints are incorporated into the backward pass through augmented-Lagrangian and relaxed-barrier penalties. A whole-body controller subsequently maps the plan to joint torques at 500 Hz while preserving contact feasibility. The model-based formulation makes disturbance responses interpretable through explicit costs and constraints, and requires no platform-specific policy training. In MuJoCo simulations, the iLQR-MPC replans at 100 Hz (mean solve time 8.9 ms); the Unitree G1 sustains steady-state walking and recovers from impulsive 245 N forward and 175 N lateral pushes.
Language model agents often struggle with complex tasks even when equipped with expert-written skills. Such skills encode declarative knowledge, whereas successful execution requires procedural knowledge tailored to the task at hand. Natural language skills may leave conditions and dependencies implicit, and tasks involving multiple skills further require agents to coordinate intermediate results and execution order. We introduce Think with Skills, a method that trains reasoning models to turn relevant skill descriptions into task-specific pseudocode plans before execution. The pseudocode explicitly represents operations, conditions, intermediate results, and dependencies, providing a structured bridge from skill descriptions to agent actions. We construct training data that pairs tasks and skills with pseudocode plans and execution trajectories, use supervised fine tuning to initialize this behavior, and further optimize end-to-end task performance with Group Relative Policy Optimization. On SkillsBench, Think with Skills raises task success from 35.0% to 62.0%. These results show that proceduralizing expert knowledge before execution substantially improves skill use.
Diffusion Transformer (DiT)-based text-to-image models have recently achieved remarkable success in image synthesis. However, when directly applied beyond their training resolution, these models often suffer from severe semantic degradation, where meaningful semantic content disappears. Although existing training-free high-resolution generation methods can mitigate this issue, the inherent semantic degradation at high resolutions remains largely unresolved, leading to degraded fine-grained details. Furthermore, widely used structural guidance methods lack modeling of the structure and details in the intermediate trajectory, which degrades the quality of the generated results. In this paper, we propose a training-free framework for high-resolution image generation to address these challenges. First, we propose a text-visual scale-decoupled attention (TVSDA) module, which restores the model's ability to generate semantically meaningful content at high resolutions by preserving the global receptive field of text tokens while aligning the receptive field of image tokens with the training resolution. Second, we propose a structure-detail guidance (SDG) strategy that explicitly models structural information and fine details through scale-wise and temporal-wise guidance, overcoming the limitations of conventional low-resolution guidance. Extensive experiments demonstrate that our method significantly improves both structural coherence and detail fidelity over existing training-free DiT-based high-resolution generation approaches. The code is available at https://github.com/ljjcoder/Restoring-Semantic-Fidelity.
Weixin Chen, Shuchang Liu, Hailan Yang, Yuhan Zhao, Li Kang, Xuefeng Zhang, Chenghao Zhang, Xinyuan Wang 等 16 位作者
Query-based recommendation separates expressing user needs from locating matching items. Its central learning problem is how to turn item interactions into effective retrieval requests when interaction logs do not annotate queries. We present R2QRec, which uses a fixed retrieval system to construct query supervision and evaluate recommendation outcomes. Retrieval verification first selects generated expressions that recover observed items as supervised fine tuning targets, allowing retrieval behavior to determine the target wording. Policy refinement then evaluates generated query sets by the observed item's rank in their fused recommendation list. Log-rank feedback distinguishes outcomes beyond the recommendation cutoff, while a KL penalty constrains policy change relative to the supervised reference. The stages have distinct roles: verification identifies expressions to imitate, and policy refinement improves the combined ranking produced by newly generated queries. Only the query generator is trained; the retriever and item index remain fixed, and no query annotations or learned reward model are required. Across three public datasets, R2QRec achieves state-of-the-art overall recommendation performance among the evaluated methods. Extensive experiments demonstrate the effectiveness of the proposed design and its generalization across generators and domains.
Progress toward artificial general intelligence (AGI) has largely relied on scaling a resource-intensive executive, System-2, through larger models, more data and compute, longer reasoning, and more agents. We ask whether the next stage may come instead from co-designing it with System-1, a lightweight, semantically aware predictor that evaluates candidate interactions before execution, so that System-2 acts only on those worth their cost. Our answer is a qualified yes. We study \textit{conditional interaction}, a predict--gate--execute--update loop: System-1 estimates each candidate's utility, System-2 executes those admitted by an adaptive threshold, and the outcomes update System-1. The loop spans training, test-time reasoning, adaptive decision-making, and agentic tool use, with utility and cost defined by the application. Under ideal screening and equal execution costs, execution compute falls by a factor approaching $1/ρ_u$, where $ρ_u$ is the density of utility-relevant interactions (cost-weighted when costs differ); prediction errors, exploration, and distribution shift reduce the saving. We bound selection regret by predictor error and the utility margin. These results motivate our central hypothesis: $ρ_u$ is a measurable coordinate of scaling efficiency and makes informative compute a better description of scaling than total compute.
Yuqi Qiu, Zuyao Xu, Lu Sun, Xiang Li, Fasheng Miao, Fubin Wu, Haixin Duan, Zheli Liu
The Agentic Web needs to support continuous collaboration among agents from different organizations. These collaborative relationships may span multiple tasks, network connections and execution instances. Such interactions require stable communication entries, message reception when instances are offline, and source verification after delayed reading. How to organize these responsibilities so that cross domain communication does not depend on specific execution instances being continuously online is a key issue for building long term agent interaction infrastructure. We propose ATP (Agent Transfer Protocol), a cross organization agent communication protocol adopting a domain mediated architecture. In this architecture, administrative domains maintain stable addresses and receiving entries for logical agents. The domain servers of both parties continuously undertake cross domain transmission. The receiving domain verifies and saves messages for execution instances to read later. The sending domain signs the complete message envelope. This allows the receiving instance to independently reverify the domain source and content integrity after the original connection ends, provided the original verification public key is still trusted and obtainable. We implemented an ATP prototype and evaluated it through a controlled cross organization LLM agent workflow, mechanism checks and latency measurements. The workflow completed subsequent business processing after instances went offline or were replaced. The independent verifier successfully verified the domain source and content integrity of saved messages. Latency measurements further quantified the communication and processing overhead introduced by the continuous mediation of domain servers.
Language models increasingly create 3D content through code, with practical workflows often relying on editing existing programs rather than regenerating them, for speed and precise control. Such edits require understanding what a program builds and foreseeing how a change reshapes it, yet prior benchmarks mostly evaluate generation or simple edits against a reference. In this paper, we introduce 3DCodeEdit, a benchmark of 2,592 instruction-guided editing tasks over 108 Blender programs that construct objects entirely in code. Its edits range from parameter to structural changes, style redesign, and scene composition, and are judged from renders against human-reviewed checklists. Across 17 models, the average success rate is only 37%, and even the strongest models complete fewer than 60% of structural and style edits. As models become more capable, their failures shift to geometric foresight, where the code runs but builds the wrong shape. We therefore study whether multi-turn feedback can compensate for this missing foresight. Feedback from a separate reviewer model that describes how the renders differ from the request helps most, more than maximum reasoning effort or an agent harness, and can let a 27B model surpass the single-shot rate of a 2.8T-parameter model.
Boyang Fu, Sameer Gabbita, George Dasoulas, Xiang Lin, Shanghua Gao, Xiaorui Su, Soumya Ghosh, Marinka Zitnik
Prediction of the transcriptional response of a cell to a genetic perturbation is a central problem in the computational modeling of gene regulation. Perturbations of the same gene can produce different transcriptional responses depending on the targeted locus, such as an alternative transcription start site or a distal regulatory element, and gene-level perturbation models represent these distinct interventions with a single gene identifier. We introduce STRAND, a generative model that encodes the regulatory DNA sequence at the perturbation locus and uses this encoding to parameterize a conditional transport process from control to perturbed single-cell states. Sequence conditioning enables zero-shot prediction for perturbation targets absent from training and supports locus-resolved inputs at 128 bp model resolution within a 524 kb sequence window. On CRISPRi screens in K562, Jurkat, and RPE1 cells, STRAND achieves the best average rank on few-shot and unseen-gene benchmarks, with gains of up to 33% in perturbation discrimination, and improves transfer to held-out cell lines by up to 0.12 in $Δ$Pearson. Ablation studies attribute these gains to sequence conditioning and to conditional transport. At the locus level, STRAND distinguishes alternative transcription start sites and validated regulatory elements that gene-identifier models represent as a single perturbation. STRAND is available at https://github.com/mims-harvard/STRAND.
Jiening Zhu, Chengzhu Zhang, Jason Fan, LiCheng Kuo, Weixing Cai, Xiuxiu He, Laura Cervino, Jean Moran 等 11 位作者
Cone-beam computed tomography (CBCT) is widely used for image-guided radiotherapy, but reducing the number of projections to lower dose and scan time makes reconstruction increasingly ill-posed. We present EUReCA (End-to-end Unified REconstruction across Clinical Acquisitions), a geometry-aware feed-forward model for variable-view clinical linac CBCT. For a given acquisition trajectory, EUReCA accepts 8-100 projections with a single set of weights, without view-count-specific retraining; the same architecture and training recipe extend unchanged to other clinical trajectories. It combines learned projection features with an in-frame Feldkamp-Davis-Kress (FDK) reconstruction. The model encodes each projection with a shared multiscale backbone, back-projects features into multiresolution 3D grids using the acquisition geometry, aggregates variable numbers of views at fixed computational cost, and refines the volume with a global 3D transformer and multilevel decoder. On simulated data, EUReCA achieved 29.9-33.2 dB PSNR with 10-100 views and outperformed all applicable feed-forward baselines; it also exceeded iterative optimization-based methods while running orders of magnitude faster. On 15 measured patient CBCT scans evaluated against vendor reconstructions, EUReCA achieved the best performance at every tested view count. These results suggest that geometry-aware, measurement-anchored feed-forward reconstruction can provide a practical and flexible foundation for variable-view linac CBCT.
Xiang Li, Chengting Yu, Jungang Li, Yilun Zheng, Junzhuo Li, Xingyao Zhang, Wenbo Su, Xuming Hu
We propose HiLo-RD (High-to-Low Budget Representation Distillation) to improve masked diffusion language models (MDLMs) under a limited generation budget. Unlike autoregressive models, MDLMs choose both what to generate and where to commit it. This creates two coupled challenges: predicting useful content before reasoning is complete, and deciding when to fix answer tokens that shape later predictions. We identify budget-induced premature commitment: even when a correct solution fits, the model can fix answer fragments near the window boundary before resolving intermediate steps. These fragments become context for later predictions and redirect subsequent reasoning. Existing post-training methods do not directly transfer the stronger trajectories that the same model follows with a larger window. HiLo-RD addresses this gap by (1) pairing large-window teacher states with cropped small-window views and (2) matching their hidden representations at committed positions. This supervision guides both token prediction and commitment order without an external teacher. Across mathematics benchmarks, HiLo-RD improves low-budget accuracy and shortens responses; these gains extend to code generation without code-domain training. On GSM8K, accuracy rises by 9.4 percentage points as mean readable length falls by about 25%. Attention diagnostics and fixed-budget order interventions support the proposed mechanism. Together, these results show that large-window reasoning can improve small-window decoding.
General-purpose embodied intelligence requires robots to coordinate diverse skills over long horizons, track task progress, and recover from failures. Specialist policies alone do not ensure task-level reliability, while powerful multimodal agents rely on costly reasoning and external experience that compact models struggle to reproduce. We introduce OmniBrain-0, a lightweight unified embodied agent that coordinates manipulation and navigation through a shared high-level decision model, integrating task understanding, planning, progress tracking, and feedback-driven recovery. Our progressive training framework combines embodied pretraining, domain-specialized agent distillation, and multi-teacher on-policy distillation (MOPD). It distills powerful teachers' interaction experience into manipulation and navigation experts, then consolidates their decision capabilities into OmniBrain-0. Unification therefore occurs within the learned decision model rather than only at the tool interface. We further introduce Rubric-Guided Recursive Self-Improvement (RSI), a data flywheel in which a Meta-Agent turns execution evidence into refined rubrics, step-level reminders, and verified trajectories for domain-expert updates before their reconsolidation into OmniBrain-0 through MOPD. We evaluate OmniBrain-0 on LIBERO-Pro, LIBERO-Plus, RoboCasa365, RoboTwin 2.0, and R2R-CE Val-Unseen, as well as multiple real-world manipulation tasks. OmniBrain-0 combines strong cross-domain task performance with substantially lower inference and execution overhead than its closed-source teacher, demonstrating efficient transfer and consolidation of embodied capabilities into a compact unified agent.
Interactive environments offer a practical way to evaluate large language model (LLM) agents, and competitive games extend this evaluation to decisions shaped by competing goals and other agents' choices. Yet existing evaluations confined to individual games or execution frameworks leave unclear which competitive advantages persist across settings. We introduce DECE (Diverse Eurogame Competitive Environments), a unified arena spanning ten Eurogames with shared interfaces and evaluation protocols. These games combine lasting strategic commitments, competition over shared resources, and multiple routes to victory. Our primary study evaluates 12 model-harness configurations, spanning nine models and four execution harnesses, in 480 three-player matches across ten games. The main and supplementary studies comprise 1,032 completed matches in total. These comparisons reveal broad cross-game ranking agreement alongside game-specific strengths. Matched studies show that the same model can perform differently across execution harnesses, adding another source of variation to these profiles. These performance advantages do not consistently translate into better token or cost efficiency, making resource use an additional consideration when comparing configurations. Together, the findings support evaluating complete agent configurations by both their competitive performance across games and the resources needed to achieve it.
Publishing an email address makes a scholar reachable, but also exposes it to automated collection. Yet how email addresses are presented on the Web has not been measured systematically across their content, form, and location. We measure it across 32,413 homepage records of computer-science scholars listed in CSRankings with MailScope, which preserves raw and rendered HTML, extracts addresses with a three-stage cascade (rules, then large language models, then a crawling agent), and labels each address. Among 19,517 reachable homepages, we find an address for 17,712 scholars (90.8%). Our measurement yields four main findings. (i) Presentation is diverse: only 53.8% publish plain content, the others spread over 23 subtypes of symbol substitution, code, and semantic description, and 5.5% of scholars' addresses appear only after rendering. (ii) Presentation follows hosts rather than individuals: scholars on one host share a content class in 67.9% of pairs, compared with 38.8% across hosts of one institution, whereas research output and institution rank are barely related to presentation. (iii) Content and form are coupled through code-based links, and 6.2% of scholars with non-plain selected presentations have plain-text copies of the same address elsewhere. (iv) Plain addresses are more common behind passed bot challenges, and 36.1% of redirecting homepages no longer lead to scholars. Human assessment yields 94.4% weighted exact-set agreement on 143 judgeable pages, complemented by three 500-page review rounds with human verification. Presentation is diverse but clusters by shared host, and by our label-based estimate plain-string matching misses nearly half of the addresses.
CAPTCHAs and bot detection have helped protect Web services from automated abuse for decades by distinguishing humans from bots. However, the emergence of LLM-powered agents introduces a new setting: Web services increasingly accommodate agents as legitimate users. Without a way to distinguish agents from other automated clients such as simple bots and scripts, these services risk large-scale automated junk submissions that waste service resources and consume users' attention or tokens. In this paper, we investigate a novel question for today's Web: "How can a Web service obtain evidence that a client is an agent?" We introduce the concept of "Proof-of-Agentness" (PoA), a mechanism for distinguishing agents from other automated clients, motivated by the parallel between human attention and an agent's inference resources. We outline two approaches: active verification through challenge-response and passive analysis of service-visible signals. Eight language models achieve an overall accuracy of 96.5% on our challenges, with an average overhead of 1,647 tokens. For passive analysis, we conduct an IRB-approved user study comparing the Web interactions of twelve human participants and representative Bot and Agent implementations, achieving an average classification accuracy of 95.8% across four classifiers, motivating further study.
Chenyang Fan, Robert D. Sanders, Elie Matar, Yixuan Yuan, Xiang Li, Sharon L. Naismith, Fernando Calamante, Jinglei Lv
Diffusion MRI (dMRI) provides information about white matter microstructure that can support brain age prediction. However, many existing prediction models use diffusion tensor imaging (DTI) scalar metrics that omit orientation information. Deep learning is increasingly used for brain age prediction, but conventional CNNs do not explicitly respect the geometric structure of orientation-dependent features. We present an interpretable brain age prediction framework that combines white matter fiber orientation distributions (WM-FODs) with an SE(3) (Special Euclidean group in 3 dimensions) equivariant CNN. The network operates directly on spherical harmonic (SH) coefficients of the FOD, preserving their transformation properties under rotation. Evaluation in 692 participants aged 36-90 years from the Human Connectome Project Aging dataset showed that the combined framework outperformed the evaluated DTI-based models and conventional CNNs. Averaging predictions from five cross-validation models yielded a mean absolute error of 3.54 years and Pearson's correlation of 0.958. Our results indicated that the performance advantage depended on combining WM-FODs with equivariant processing. Prediction accuracy was highest at a maximum SH order of Lmax = 2 and declined at higher orders. Tract-level occlusion, where each segmented tract was masked in turn, revealed age-dependent patterns of model sensitivity, with importance peaks in frontal projection pathways at 36-44 years, the fornix at 45-54 years, the callosal isthmus at 55-64 years, the middle cerebellar peduncle at 65-74 years, and the callosal genu at 75-90 years. These findings support rotation-equivariant processing of WM-FODs for accurate brain age prediction with anatomically interpretable model sensitivity.
Zhicheng Ma, Xiang Liu, Zhaoxiang Liu, Ning Wang, Yi Shen, Kai Wang, Shuming Shi, Shiguo Lian
Large Language Models (LLMs) based on Mixture-of-Experts (MoE) are pivotal in industrial applications for their ability to scale performance efficiently. However, standard MoEs enforce uniform expert sizes, creating a rigidity that fails to align computational costs with varying token-level complexity. While heterogeneous expert architectures attempt to address this by diversifying expert sizes, they often suffer from significant system-level challenges, specifically unbalanced GPU utilization and inefficient parameter utilization, which hinder practical deployment.To bridge the gap between theoretical heterogeneity and robust industrial application, we propose Mixture of Heterogeneous Grouped Experts (MoHGE) which introduces a two-level routing mechanism to enable flexible, resource-aware expert combinations. To optimize inference efficiency, we propose a Group-Wise Auxiliary Loss, which dynamically steers tokens to the most parameter-efficient expert groups based on task difficulty.To address the critical deployment challenge of GPU load balancing, we introduce an All-size Group-decoupling Allocation strategy coupled with an Intra-Group Experts Auxiliary Loss. These mechanisms collectively ensure uniform computation distribution across GPUs.Extensive evaluations demonstrate that MoHGE matches the performance of MoE architectures while reducing the total parameters by approximately 20% and maintaining balanced GPU utilization. Our work establishes a scalable paradigm for resource-efficient MoE design, offering a practical solution for optimizing inference costs in real-world scenarios.
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 6: Industry Track) · 2026 · 正式发表
Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He 等 59 位作者
We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition. In the first stage, the model performs efficient layout analysis on downsampled images to identify structural elements, circumventing the computational overhead of processing high-resolution inputs. In the second stage, guided by the global layout, it performs targeted content recognition on native-resolution crops extracted from the original image, preserving fine-grained details in dense text, complex formulas, and tables. To support this strategy, we developed a comprehensive data engine that generates diverse, large-scale training corpora for both pretraining and fine-tuning. Ultimately, MinerU2.5 demonstrates strong document parsing ability, achieving state-of-the-art performance on multiple benchmarks, surpassing both general-purpose and domain-specific models across various recognition tasks, while maintaining significantly lower computational overhead.
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 6: Industry Track) · 2026 · 正式发表
Xiaoke Guo, Songze Li, Zhiqiang Liu, Zhaoyan Gong, Yuanxiang Liu, Huajun Chen Zhejiang University and ZJU-Hangzhou Global Scientific and Technological Innovation Center, Wen Zhang Zhejiang University
Table serialization remains a critical bottleneck for Large Language Models (LLMs) in complex table question answering, hindered by challenges such as structural neglect, representation gaps, and reasoning opacity. Existing serialization methods fail to capture explicit hierarchies and lack schema flexibility, while current tree-based approaches suffer from limited semantic adaptability. To address these limitations, we propose ASTRA (Adaptive Semantic Tree Reasoning Architecture) including two main modules, AdaSTR and DuTR. First, we introduce AdaSTR, which leverages the global semantic awareness of LLMs to reconstruct tables into Logical Semantic Trees. This serialization explicitly models hierarchical dependencies and employs an adaptive mechanism to optimize construction strategies based on table scale. Second, building on this structure, we present DuTR, a dual-mode reasoning framework that integrates tree-search-based textual navigation for linguistic alignment and symbolic code execution for precise verification. Experiments on complex table benchmarks demonstrate that our method achieves state-of-the-art (SOTA) performance.
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
Temporal Knowledge Graph Question Answering (TKGQA) is inherently challenging, as it requires sophisticated reasoning over dynamic facts with multi-hop dependencies and complex temporal constraints. Existing methods rely on fixed workflows and expensive closed-source APIs, limiting flexibility and scalability. We propose Temp-R1, the first autonomous end-to-end agent for TKGQA trained through reinforcement learning. To address cognitive overload in single-action reasoning, we expand the action space with specialized internal actions alongside external action. To prevent shortcut learning on simple questions, we introduce reverse curriculum learning that trains on difficult questions first, forcing the development of sophisticated reasoning before transferring to easier cases. Our 8B-parameter Temp-R1 achieves state-of-the-art performance on MultiTQ and TimelineKGQA, improving 19.8% over strong baselines on complex questions. Our work establishes a new paradigm for autonomous temporal reasoning agents. The code is available at https://github.com/zjukg/Temp-R1.
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
Weicong Liu, Zixuan Yang, Yibo Zhao East China Normal University, Xiang Li East China Normal University
Reviewer assignment is increasingly critical yet challenging in the LLM era, where rapid topic shifts render many pre-2023 benchmarks outdated and where proxy signals poorly reflect true reviewer familiarity. We address this evaluation bottleneck by introducing LR-bench, a high-fidelity, up-to-date benchmark curated from 2024–2025 AI/NLP manuscripts with five-level self-assessed familiarity ratings collected via a large-scale email survey, yielding 1,055 expert-annotated paper–reviewer–score annotations. We further propose a reviewer-centric ranking framework that distills each reviewer’s recent publications into compact keyword-based profiles and fine-tunes an embedding model with weak preference supervision constructed from heuristic retrieval signals, enabling to match each manuscript against a reviewer profile directly. Across the LR-bench and the CMU gold-standard dataset, our approach consistently achieves state-of-the-art performance, outperforming strong embedding baselines by a clear margin. We release LR-bench at https://huggingface.co/datasets/Gnociew/LR-bench, and an github repository at https://github.com/Gnociew/RATE-Reviewer-Assignment.
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
Xiqiao Xiong, Ouxiang Li, Zhuo Liu, Moxin Li, Wentao Shi, Fengbin Zhu, Qifan Wang Meta AI, Fuli Feng University of Science and Technology of China
Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment. This has led to the task of training automated multi-turn attackers to probe model safety vulnerabilities. However, existing approaches typically rely on turn-level optimization, which is insufficient for learning long-term attack strategies. To bridge this gap, we formulate this task as a multi-turn reinforcement learning problem, directly optimizing the harmfulness of the final-turn response as the outcome reward. To address the sparse supervision of the outcome reward, we introduce TROJail, which employs two process rewards to evaluate the utility of intermediate prompts and integrate them into advantage estimation. These rewards (1) penalize overly harmful prompts that trigger the model’s refusal mechanism, and (2) encourage steering the semantic relevance of responses toward the targeted harmful content. Experimental results show improved attack success rates across multiple models and benchmarks, highlighting the effectiveness of our approach. The code is available at https://anonymous.4open.science/r/TROJail. Warning: This paper contains examples of harmful content.
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
Zhiqing Cui Reading University and Nanjing University of Information Science & Technology, Binwu Wang University of Science and Technology of China, Qingxiang Liu, Yeqiang Wang Northwest A&F University, Zhengyang Zhou, Yuxuan Liang The Hong Kong University of Science and Technology (Guangzhou), Yang Wang University of Science and Technology of China
Large language models (LLM) have emerged as a promising avenue for time series forecasting, offering the potential to integrate multimodal data. However, existing LLM-based approaches face notable limitations—such as marginalized role in model architectures, reliance on coarse statistical text prompts, and lack of interpretability. In this work, we introduce Augur, a fully LLM driven time series forecasting framework that exploits LLM causal reasoning to discover and use directed causal associations among covariates. Augur uses a two stage teacher student architecture where a powerful teacher LLM infers a directed causal graph from time series using heuristic search together with pairwise causality testing. A lightweight student agent then refines the graph and fine tune on high confidence causal associations that are encoded as rich textual prompts to perform forecasting. This design improves predictive accuracy while yielding transparent, traceable reasoning about variable interactions. Extensive experiments on real-world datasets with 25 baselines demonstrate that Augur achieves competitive performance and robust zero-shot generalization.
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
Xiang Li The Hong Kong University of Science and Technology (Guangzhou), Penglei Sun, Wanyun Zhou, Zikai Wei, Yongqi Zhang The Hong Kong University of Science and Technology (Guangzhou), Xiaowen Chu Hong Kong University of Science and Technology (Guangzhou)
Individual investors are significantly outnumbered and disadvantaged in financial markets, overwhelmed by abundant information and lacking professional analysis. Equity research reports stand out as crucial resources, offering valuable insights. By leveraging these reports, large language models (LLMs) can enhance investors’ decision-making capabilities and strengthen financial analysis. However, two key challenges limit their effectiveness: (1) the rapid evolution of market events often outpaces the slow update cycles of existing knowledge bases, (2) the long-form and unstructured nature of financial reports further hinders timely and context-aware integration by LLMs. To address these challenges, we tackle both data and methodological aspects. First, we introduce the Event-Enhanced Automated Construction of Financial Knowledge Graph (FinKario), a dataset comprising over 305,360 entities, 210,328 relational triples, and 19 distinct relation types. FinKario automatically integrates real-time company fundamentals and market events through prompt-driven extraction guided by professional institutional templates, providing structured and accessible financial insights for LLMs. Additionally, we propose a Two-Stage, Graph-Based retrieval strategy (FinKario-RAG), optimizing the retrieval of evolving, large-scale financial knowledge to ensure efficient and precise data access. Extensive experiments show that FinKario with FinKario-RAG achieves superior stock trend prediction accuracy, outperforming financial LLMs by 18.81% and institutional strategies by 17.85% on average in backtesting. [Our code is available at https://github.com/Jackson906E/FinKario.]
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
Ziyang Wang, Jiangfeng Xiao Shenzhen University, Chuan Xiao Osaka University, Ruoxiang LI Shenzhen University, Rui Mao Shenzhen Institute of Computing Sciences and Shenzhen University, Jianbin Qin Shenzhen University
Large language models (LLMs) are expensive to serve because dense FFN blocks, multi-head attention, and KV caches dominate memory, making structured pruning a natural way to reduce serving costs under tight parameter and memory budgets. We present GRASPrune, a global budgeted structured pruning framework applied post-hoc to a pretrained model that jointly prunes FFN channels and attention KV head groups under a single global parameter budget. GRASPrune attaches lightweight learnable gates to prunable units and optimizes only these gates on a small unlabeled language-modeling calibration set, keeping all backbone weights frozen while enforcing the target sparsity at every step. A final budget-preserving scaling calibration reweights the surviving channels and heads to correct scale shifts introduced by pruning. On LLaMA-2-7B, GRASPrune removes 50% of parameters and achieves 12.18 perplexity on WikiText-2 while maintaining competitive average zero-shot accuracy on five downstream benchmarks, using a short calibration run of four epochs on 512 unlabeled sequences on a single NVIDIA A100 80GB GPU, all without any full-model fine-tuning.
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
Yuhang Zhou, Yixin Cao Fudan University, Yuchen Ni, Shihan Dou, Xutian Chen, Ge Zhang ByteDance Inc., Xiang Liu, Guangnan Ye Fudan University
Standard evaluators, such as reward models, compress diverse human judgments into a single scalar, conflating valid Subjective Preference with Cognitive Uncertainty. This structural mismatch often leads to brittle alignment and reward hacking. To address this, we propose PRISM which reinterprets reward evaluation as a conditional distribution parameterized by a Mixture of Gaussians. PRISM structurally disentangles these factors: distinct Gaussian experts emerge to capture conflicting preference dimensions, while their variance estimates quantify uncertainty, acting as a dynamic reliability gate during optimization. We introduce a two-stage training strategy to learn these disentangled representations from scalable pairwise comparisons without requiring massive fine-grained annotations. Empirical results show that PRISM significantly outperforms scalar baselines in both accuracy and generalization. Furthermore, in downstream Reinforcement Learning, PRISM effectively mitigates reward hacking, yielding policies that are more robust and resilient to distribution shifts.
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