SH
Sirui Han
cs.AIcs.CLcs.CVcs.LGcs.ROcs.CEcs.MMcs.GRcs.HCcs.CR
On Valency
published · living versionsW_8n8b89ac·v1 · currentpublished
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
with Zhiwei Li, Lei Zhu, Hao Gu, Xiang Hu +4
1 version
Preprints & journals
82 papers in the corpus · 2024–2026HarnessSQL: Harness-Native Training for SQL Agents in Realistic Database Environments2610.12274v3 · Haolin Yang, Jipeng Zhang, Zhiqiang Qian et al.2026 · 0 citationsarXiv
From bits to atoms: A survey of cross-layer safety in Embodied AI2610.14038v1 · Tuo Feng, Yue Zhang, Shiji Zhou et al.2026 · 0 citationsAI Plus 1 (2026) 98-122
Token-World: World Modeling in Vision-Language Model Token Space for Robot Manipulation2610.00575v2 · Chuyao Fu, Xiaowei Chi, Yuhan Rui et al.2026 · 0 citationsarXiv
DexRoam: Learning Mobile Bimanual Dexterous Manipulation from Egocentric Whole-Body Human Demonstrations2609.35761v1 · Rui Zhou, Yibo Yuan, Junkai Zhao et al.2026 · 0 citationsarXiv
PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety2609.28197v1 · Jiapeng Sun, Yujin Zhou, Han Zhu et al.2026 · 0 citationsarXiv
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking2609.13141v1 · Zhiwei Li, Lei Zhu, Hao Gu et al.2026 · 0 citationsarXivon Valency
LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents2609.09754v1 · Yujin Zhou, Mingxuan Zheng, Chuxue Cao et al.2026 · 0 citationsEMNLP 2026 Main
OMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit2609.31631v2 · Dezhi Li, Lujun Li, Qiyuan Zhu et al.2026 · 0 citationsarXiv
Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations2608.09268v1 · Weijie Liang, Yuanfeng Song, Xing Chen et al.2026 · 0 citationsarXiv
SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent2608.07449v1 · Mingxuan Zheng, Yujin Zhou, Chuxue Cao et al.2026 · 0 citationsarXiv
Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning2608.04771v1 · Qiyuan Zhu, Dezhi Li, Pengyu Cheng et al.2026 · 0 citationsarXiv
Data Pyramid for Embodied Manipulation: A Survey2607.24744v2 · Yifan Ye, Yankai Fu, Yaoxu Lv et al.2026 · 0 citationsarXiv
Hierarchical Denoising For Multi-Step Visual Reasoning2607.15278v1 · Zezhong Qian, Xiaowei Chi, Chak-Wing Mak et al.2026 · 0 citationsarXiv
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling2607.02980v1 · Xiang Hu, Xinyu Wei, Hao Gu et al.2026 · 0 citationsarXiv
WAM4D: Fast 4D World Action Model via Spatial Register Tokens2606.14048v3 · Ying Li, Xiaobao Wei, Jiajun Cao et al.2026 · 0 citationsarXiv
Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulation2606.08737v1 · Yunfan Lou, Yifan Ye, Yankai Fu et al.2026 · 0 citationsarXiv
Self-Evolving Deep Research via Joint Generation and Evaluation2606.04507v1 · Han Zhu, Chengkun Cai, Yuanfeng Song et al.2026 · 0 citationsarXiv
RW-TTT: Batched Serving for Request-Owned Test-Time Training State2605.28053v2 · Jian Yang, Zhizhuo Kou, Yao Tian et al.2026 · 0 citationsarXiv
IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference2605.25475v2 · Xintong Yang, Hao Gu, Binxing Xu et al.2026 · 0 citationsarXiv
KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning2605.14907v2 · Yisen Gao, Jiaxin Bai, Haoyu Huang et al.2026 · 0 citationsarXiv
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation2605.10813v2 · Jinhang Xu, Qiyuan Zhu, Yujun Wu et al.2026 · 0 citationsarXiv
ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution2604.25329v1 · Chuyao Fu, Shengzhe Gan, Zhuoli Ouyang et al.2026 · 0 citationsarXiv
When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models2604.17375v1 · Cui Yakun, Xingqun Qi, TianTian Geng et al.2026 · 0 citationsarXiv
ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance2604.12308v1 · Haoran Li, Yulin Chen, Huihao Jing et al.2026 · 0 citationsarXiv
QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch2604.07853v1 · Hao Gu, Hao Wang, Jiacheng Liu et al.2026 · 0 citationsarXiv
Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs2604.07888v1 · Binxing Xu, Hao Gu, Lujun Li et al.2026 · 0 citationsarXiv
LABSHIELD: A Multimodal Benchmark for Safety-Critical Reasoning and Planning in Scientific Laboratories2603.11987v1 · Qianpu Sun, Xiaowei Chi, Yuhan Rui et al.2026 · 0 citationsarXiv
Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors2603.12397v1 · Pengcheng Wen, Yanxu Zhu, Jiapeng Sun et al.2026 · 0 citationsarXiv
DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning2603.08095v1 · Chi-Min Chan, Ehsan Hajiramezanali, Xiner Li et al.2026 · 0 citationsarXiv
Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training2603.07223v1 · Chuxue Cao, Honglin Lin, Zhanping Zhong et al.2026 · 0 citationsarXiv
What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning2602.08346v1 · Yujin Zhou, Pengcheng Wen, Jiale Chen et al.2026 · 0 citationsarXiv
TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation2602.09023v4 · Qinwen Xu, Jiaming Liu, Rui Zhou et al.2026 · 0 citationsarXiv
MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory2602.07885v3 · Zhenyuan Zhang, Xianzhang Jia, Zhiqin Yang et al.2026 · 0 citationsarXiv
Reimagining Legal Fact Verification with GenAI: Toward Effective Human-AI Collaboration2602.06305v2 · Sirui Han, Yuyao Zhang, Yidan Huang et al.2026 · 3 citationsarXiv
Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models2602.02244v3 · Hao Wang, Hao Gu, Hongming Piao et al.2026 · 0 citationsarXiv
Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification2601.22642v2 · Chuxue Cao, Jinluan Yang, Haoran Li et al.2026 · 0 citationsarXiv
Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning2601.13942v2 · Hongbo Bai, Yujin Zhou, Yile Wu et al.2026 · 0 citationsACL 2026 Findings
LRAS: Advanced Legal Reasoning with Agentic Search2601.07296v1 · Yujin Zhou, Chuxue Cao, Jinluan Yang et al.2026 · 0 citationsarXiv
Reinforcement Learning of Large Language Models for Interpretable Credit Card Fraud Detection2601.05578v1 · Cooper Lin, Yanting Zhang, Maohao Ran et al.2026 · 0 citationsarXiv
MMFCTUB: Multi-Modal Financial Credit Table Understanding Benchmark2601.04643v2 · Cui Yakun, Yanting Zhang, Zhu Lei et al.2026 · 0 citationsarXiv
Towards Multi-modal Multi-turn Safety: From Agentic Interaction to Strategic Alignment2601.04736v2 · Han Zhu, Jiale Chen, Chengkun Cai et al.2026 · 0 citationsarXiv
Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test2601.04137v1 · Chun-Kai Fan, Xiaowei Chi, Xiaozhu Ju et al.2026 · 0 citationsarXiv
CaveAgent: Transforming LLMs into Stateful Runtime Operators2601.01569v4 · Maohao Ran, Zhenglin Wan, Cooper Lin et al.2026 · 0 citationsarXiv
MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data2512.13297v2 · Zhenghao Zhu, Chuxue Cao, Sirui Han et al.2025 · 0 citationsarXiv
InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents2511.22884v2 · Zhenghao Zhu, Yuanfeng Song, Xin Chen et al.2025 · 0 citationsarXiv
Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection2510.24816v2 · Cui Yakun, Peng Qi, Fushuo Huo et al.2025 · 1 citationarXiv
SafeMT: Multi-turn Safety for Multimodal Language Models2510.12133v1 · Han Zhu, Juntao Dai, Jiaming Ji et al.2025 · 0 citationsarXiv
WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation2510.07313v1 · Zezhong Qian, Xiaowei Chi, Yuming Li et al.2025 · 0 citationsarXiv
Can World Models Benefit VLMs for World Dynamics?2510.00855v1 · Kevin Zhang, Kuangzhi Ge, Xiaowei Chi et al.2025 · 0 citationsarXiv
GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners2509.24418v2 · Haoran Li, Jingru Zeng, Yulin Chen et al.2025 · 0 citationsarXiv
Career total: 179 works. 82 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.