Haonan Ping, Jianshu Hu, Yimin Wang, Yi Zhu, Pai Liang, Qiyan Jin, Qirui Bao, Ying Qian 等 15 位作者
Long-horizon dexterous manipulation remains a fundamental challenge for robot learning, requiring the composition of multiple skills, precise bimanual coordination, generalizable visual understanding, and robust skill transitions. Yet existing manipulation benchmarks largely emphasize isolated skills or support only a limited range of end-effectors, making these capabilities difficult to evaluate systematically. We introduce DexArena, a benchmark designed to evaluate learning and generalization in long-horizon bimanual dexterous manipulation. DexArena features 10 long-horizon tasks and 30 stage-level tasks spanning diverse household and industrial scenarios. Each long-horizon task is composed of explicitly defined stages with physically grounded success conditions, enabling reliable evaluation of both intermediate progress and end-to-end task completion. A unified benchmark interface and verified human-teleoperated demonstrations enable testing different policy learning algorithms, with standardized simulation configurations, scene randomization, trajectory replay, and task-level evaluation. Through extensive baseline experiments, we identify substantial challenges in precise manipulation, generalization to scene variation, and skill composition. DexArena establishes a challenging and reproducible benchmark for developing robot learning methods that move toward generalizable long-horizon dexterous behavior.
Unlike explicit attacks with obvious profanity, implicit hate speech hides malice within seemingly compliant expressions through metaphors and contextual hints, making its detection in online content review challenging. Many PLM- or LLM-based methods apply the same processing pipeline across samples, which may overlook differences in information requirements and introduce unnecessary computation. We observe that online hate speech is not monolithic but manifests in varied forms. We therefore define three fine-grained categories: Shallow, Targeted, and Context-Dependent. Accordingly, we propose Fine-grained Adaptive Implicit Hate speech Detection (FAID), a novel framework that first performs fine-grained classification and then adapts to specific categories. Specifically, for Shallow samples with surface-identifiable intents, the framework adopts lightweight Prompt-Tuning for rapid classification; for Targeted comments that bind malicious intent to concealed targets, we design knowledge augmentation to iteratively refine the model and reveal hidden targets; for Context-Dependent comments lacking background information, we utilize an agentic framework that automatically generates prompts to evolve context, infer missing background information and identify ambiguous malicious intents. This adaptive architecture focuses computational resources on complex implicit samples while avoiding redundant reasoning for shallow samples. Experiments on four benchmark datasets demonstrate that FAID significantly outperforms SOTA baselines.
Yuanyi Zhu, Zijian Li, Xin Ai, Zixuan Chen, Sen Liu, Yang Xu
Network simulation plays a crucial role in both networking research and industry. Existing commonly-used Discrete Event Simulations (DES) are based on the callback mechanism for discrete events. However, as network functions grow in complexity, callbacks reveal a fundamental structural limitation: a callback can only represent a single point in a blocking operation and cannot capture the full operation as a coherent whole. This forces developers to manually decompose sequential network logic into scattered callback fragments, leading to stack ripping, callback hell, and heavy development and debugging burdens. We propose CoDES (\textbf{Co}routine-based \textbf{DES}), a coroutine-based programming paradigm for network simulation that addresses this structural limitation. CoDES targets development productivity rather than execution performance. Realizing CoDES in existing DES simulators is non-trivial, as coroutine suspension must be coordinated with the event scheduler, introducing challenges in coroutine resource conflicts, operation-level computation requirements, compatibility with existing callback-based simulators, and overhead. We implement a CoDES-based framework in ns-3, address all four challenges, and release it as open source. We evaluate CoDES by implementing Message Passing Interface (MPI), High Precision Congestion Control (HPCC), and Routing Information Protocol (RIP) in ns-3, spanning the transport, congestion control, and routing layers. Compared with callback-based counterparts, CoDES reduces lines of code by up to 51.4% and nesting depth by up to 50%, with no accuracy loss and negligible runtime and memory overhead.
Remus Teodorescu, Nicolai A. Weinreich, Berke Bilgin, Yi Zhuang, Wenzel Prochazka
An electrochemical-thermal model of the 4680 cylindrical cell is presented: a Doyle-Fuller-Newman model of the electrode stack coupled to a two-node thermal balance of the roll and the can (a thermal DFN, TDFN), solved by an implicit finite-volume scheme. Two cells are parameterised from teardown geometry and open literature, with every value tagged by provenance: the Tesla NMC811/graphite tabless cell and the BYD FC4680 LiFePO4 multi-tab cell. The reaction heat is evaluated at the open-circuit potential of the particle-mean concentration, which restores the heat of mixing. Both sets are calibrated in the same way, with the test fixture identified from the measurement alone. Against the 1C and 2C charge test of Ank et al., the calibrated NMC set follows the mean can temperature within 0.52 and 1.46 K, with a contact heat of 0.94 mOhm matching the authors' estimate for their holder. For the LFP cell, 1C and 2C discharges to 2.0 V were measured on the authors' bench; the fixture conductance (0.337 W/K) follows from the energy balance and the heat capacity (277 J/K) from the cooling. With the end-of-lithiation drop of LiFePO4 restored in the cathode open-circuit potential, the calibrated set follows the can temperature within 0.44 K (1C) and 0.76 K (2C), reproduces the peaks and the relaxation after cut-off. What remains is what a single can node and a single representative particle do not describe: the axial gradient of the NMC can under contact heating, and a gradual decline of the LFP voltage before the knee at 2C, which points to the distribution of particle states in the electrode. The parameter sets (BPX, CSV) and the bench data are openly available.
Reinforcement learning has advanced large language models on tasks with reliable verifiers, where checking an outcome provides a clear basis for reward. Extending this approach to open-ended tasks requires environments that can both evaluate complex, partially successful outputs and turn these judgments into effective learning guidance. We propose a reinforcement learning framework built around a training environment that integrates human domain knowledge with model reasoning. Human domain knowledge, encoded in rubrics, anchors evaluation to task intent, while model reasoning combined with hierarchical rewards distinguishes complex open-ended outputs and links diagnosed failures to likely responsible output regions. Furthermore, these diagnostic attributions guide token-level weights in the GRPO objective, thereby translating the ambiguous notion of success in open-ended tasks into concrete guidance for policy optimization. We instantiate this framework in interactive web application generation, a representative open-ended generation task. The resulting model achieves an average pass rate of 41.25\% on MiniAppBench and 76.19\% on ArtifactsBench. Ablation studies show the contributions of individual components, while additional out-of-distribution evaluations support transferable gains without degrading performance on other evaluated tasks.
Graph neural networks (GNNs) rely critically on neighborhood aggregation, yet conventional mean aggregation may fail to capture class-relevant distributional information, particularly in heterophilic graphs. We propose ExpectileGCN, an adaptive graph aggregation framework that introduces a learnable expectile level to capture neighborhood information beyond the mean. The proposed operator continuously adjusts aggregation between minimum- and maximum-type behaviors, with mean aggregation as a special case. A differentiable approximation based on sigmoid smoothing and fixed-point iterations enables end-to-end optimization. Theoretically, we establish stability properties and transductive generalization guarantees for ExpectileGCN. We further investigate its classification risk under heterophilic neighborhood models. For informative neighborhoods, we show that expectile aggregation can exploit class-dependent scale differences to achieve a classification advantage over mean aggregation. Under a local asymptotic regime with diminishing per-neighbor label informativeness, we establish that this advantage can persist in terms of limiting classification risk. Experiments on homophilic and heterophilic benchmark graphs demonstrate strong predictive performance and improved robustness under feature corruption and structural perturbations.
Long-context multimodal document question answering (QA) has become an important yet challenging task for modern vision-language models (VLMs), as it requires reasoning over evidence dispersed across pages and modalities within limited input budgets. Current pipelines adopt retrieval-augmented generation (RAG) to select multimodal evidence for downstream VLMs. However, existing systems mainly rely on static selection rules over fixed-granularity retrieval units such as pages or blocks, resulting in information loss during retrieval and suboptimal performance in downstream reasoning. To alleviate these issues, we formulate the core task as budget-aware evidence selection over structured document evidence and propose HyperDoc, a document RAG framework that constructs compact yet sufficient evidence while preserving document relations. Specifically, HyperDoc constructs a document hypergraph to explicitly capture structural, logical, and cross-modal relationships among multimodal document elements. Over this structured evidence space, HyperDoc performs adaptive cost-aware hyperedge selection based on query intent and input budget. Extensive experiments on three representative benchmarks demonstrate that HyperDoc outperforms various types of state-of-the-art baselines.
Andrea Maracani, Savas Ozkan, Junyi Zhu, Sinan Mutlu, Mete Ozay
Named Entity Recognition (NER) is a key component in industrial information extraction pipelines, where systems must satisfy strict latency and throughput constraints in addition to strong accuracy. State-of-the-art NER accuracy is often achieved by span-based frameworks, which construct span representations from token encodings and classify candidate spans. However, many span-based methods enumerate large numbers of candidates and process each candidate with marker-augmented inputs, substantially increasing inference cost and limiting scalability in large-scale deployments. In this work, we propose SpanDec, an efficient span-based NER framework that targets this bottleneck. Our main insight is that span representation interactions can be computed effectively at the final transformer stage, avoiding redundant computation in earlier layers via a lightweight decoder dedicated to span representations. We further introduce a span filtering mechanism during enumeration to prune unlikely candidates before expensive processing. Across multiple benchmarks, SpanDec matches competitive span-based baselines while improving throughput and reducing computational cost, yielding a better accuracy–efficiency trade-off suitable for high-volume serving and on-device applications.
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
Jiacheng Liang, Tanqiu Jiang State University of New York at Stony Brook, Yuhui Wang State University of New York at Stony Brook, Rongyi Zhu Stony Brook University, State University of New York at Stony Brook, Fenglong Ma Pennsylvania State University, Ting Wang State University of New York at Stony Brook
This paper presents AutoRAN, the first framework to automate the hijacking of internal safety reasoning in large reasoning models (LRMs). At its core, AutoRAN pioneers an execution simulation paradigm that leverages a weaker but less-aligned model to simulate execution reasoning for initial hijacking attempts and iteratively refine attacks by exploiting reasoning patterns leaked through the target LRM’s refusals. This approach steers the target model to bypass its own safety guardrails and elaborate on harmful instructions. We evaluate AutoRAN against state-of-the-art LRMs, including GPT-o3/o4-mini and Gemini-2.5-Flash, across multiple benchmarks (AdvBench, HarmBench, and StrongReject). Results show that AutoRAN achieves approaching 100% success rate within one or few turns, effectively neutralizing reasoning-based defenses even when evaluated by robustly aligned external models. This work reveals that the transparency of the reasoning process itself creates a critical and exploitable attack surface, highlighting the urgent need for new defenses that protect models’ reasoning traces rather than merely their final outputs.
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
Shuang Liu Carnegie Mellon University, Ruijia Zhang, Ruoyun Ma ByteDance Inc., Yujia Deng Facebook, Lanyi Zhu University of Washington, Jiayu Li University of Chicago, Zelong Li Amazon, Zhibin Shen Columbia University 等 9 位作者
Large language models (LLMs) have precipitated a dramatic improvement in the legal domain, yet the deployment of standalone models faces significant limitations regarding hallucination, outdated information, and verifiability. Recently, LLM agents have attracted significant attention as a solution to these challenges, utilizing advanced capabilities such as planning, memory, and tool usage to meet the rigorous standards of legal practice. In this paper, we present a comprehensive survey of LLM agents for legal tasks, analyzing how these architectures bridge the gap between technical capabilities and domain-specific needs. Our major contributions include: (1) systematically analyzing the technical transition from standard legal LLMs to legal agents; (2) presenting a structured taxonomy of current agent applications across distinct legal practice areas; (3) discussing evaluation methodologies specifically for agentic performance in law; and (4) identifying open challenges and outlining future directions for developing robust and autonomous legal assistants.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表