Publications
A complete list of my publications across journals, top CS proceedings, computational social science proceedings, and working papers. Use the filter buttons below to browse by research pillar.
2026
CVPR 2026 Modeling the Brain's Grammar: ROI-Guided fMRI Pretraining for Transferable and Interpretable Vision Decoding, Yulong Liu, Hua Xu, Yiyang Cai, Chunyang Jiang, Sirui Han*, Yike Guo*.
[GitHub]
[GitHub]
ICRA 2026 GSRender: Deduplicated Occupancy Prediction via Weakly Supervised 3D Gaussian Splatting, Qianpu Sun, Changyong Shu, ..., Sirui Han*, Yuan Chun*.
[arXiv] [GitHub]
[arXiv] [GitHub]
CHI 2026 CareerCraft: Supporting New Graduates on Job Hunting with LLM-Assisted Self-Construction of Career Profile, Xinyue Qi, Chengzhong Liu, Xiangyu Long, Zhizhuo Kou, Sirui Han*, Yike Guo*.
[GitHub]
[GitHub]
CHI 2026 Reimagining Legal Fact Verification with GenAI: Toward Effective Human-AI Collaboration, Sirui Han, Yuyao Zhang, Yidan Huang, Xueyan Li, Chengzhong Liu, Yike Guo*.
[arXiv] [GitHub]
[arXiv] [GitHub]
AAAI 2026 Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging, Lujun Li, Zhu Qiyuan, ..., Sirui Han*, Yike Guo*.
[arXiv] [GitHub]
[arXiv] [GitHub]
AAAI 2026 Outlier Matters: Efficient Long-to-Short Reasoning via Outlier-Guided Model Merging, Han, Sirui*; et al.
[GitHub]
[GitHub]
AAAI 2026 ManipDreamer3D: Synthesizing Plausible Robotic Manipulation Video with Occupancy-aware 3D Trajectory, Ying Li, Xiaobao Wei, ..., Sirui Han, Shanghang Zhang.
[arXiv] [GitHub]
[arXiv] [GitHub]
AAAI 2026 What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning, Han, Sirui*; et al.
[arXiv] [GitHub]
[arXiv] [GitHub]
ICLR 2026 Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding, Runqi Ouyang, ..., Sirui Han, Xingang Wang*.
[arXiv] [Project]
[arXiv] [Project]
ICLR 2026 EffiVMT: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning, Yue Ma, ..., Sirui Han*, Chenyang Qi*, Qifeng Chen.
[arXiv] [GitHub]
[arXiv] [GitHub]
ICLR 2026 EgoTwin: Dreaming Body and View in First Person, Jingqiao Xiu, ..., Sirui Han*, Liang Pan*, Ziwei Liu.
[arXiv] [Project]
[arXiv] [Project]
ICA 2026 When AI Manipulates: Context-Dependent Effect and the Psychology of University Student Trust on Social Media, Siyu Peng, Sirui Han*, Yike Guo.
ICA 2026 Deepfakes as Systemic Risk at the Media–Law Boundary: A Technology Neutral Assessment, Yidan Huang, Sirui Han*, Yike Guo.
ICA 2026 When Data Speaks for the North: Generative AI, Corpus Inequality, and the Reinforcement of Symbolic Power, Guoying Lu, Sirui Han*, Yike Guo.
UI JLTP 2026 Huang, Y.D.; Han, S.R.*; Guo, Y.K. Consumer Protection in AI–Governed Credit Markets: Algorithmic Bias and the Right to Explanation. University of Illinois Journal of Law, Technology & Policy (forthcoming).
GWJLT 2026 Wu, Y.Y.; Han, S.R.*; Guo, Y.K. Defining The Purpose of Training Data: A Critical Review on The Purpose Element of Copyright Exceptions For Training Data. George Washington Journal of Law & Technology (forthcoming).
IHRLR 2026 Li, R.X.; Han, S.R.*; Guo, Y.K. Simulated Justice: How AI Alignment Replaces Conflict with Coherence. Intercultural Human Rights Law Review (forthcoming).
UCLA JLT 2026 Li, R.X.; Han, S.R.*; Guo, Y.K. When AI Sounds Judicious: How AI Alignment Mimic Procedure While Evading Accountability. UCLA Journal of Law & Technology (forthcoming).
ESWA 2026 Han, J.J.; Ye, G.D.; Han, S.R.* An Image Steganography Algorithm using Selective Timestep Embedding and Diffusion Model. Expert Systems with Applications (forthcoming).
2025
NeurIPS 2025 Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback, Ji, Jiaming; ...; Han, Sirui; Guo, Yike; Yang, Yaodong.
[arXiv] [Code]
[arXiv] [Code]
NeurIPS 2025 Semantic-guided Diverse Decoding for Large Language Model, Shi, Weijie; ...; Han, Sirui*; ...; Zhou, Xiaofang*.
[arXiv] [Code]
[arXiv] [Code]
NeurIPS 2025 Learning Principles from Multi-modal Human Preference, Jiayi Zhou, ..., Sirui Han, Yike Guo, Yaodong Yang.
[arXiv] [Project]
[arXiv] [Project]
NeurIPS 2025 IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering, Hengyu Liu, ..., Sirui Han*, Brandon Y. Feng*.
[arXiv] [Project]
[arXiv] [Project]
NeurIPS 2025 InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback, Boyuan Chen, ..., Sirui Han, Yike Guo, Yaodong Yang.
[arXiv] [Project]
[arXiv] [Project]
CHI EA 2025 Scenario, Role, and Persona: A Scoping Review of Design Strategies for Socially Intelligent AI Agents, Niu, Ruowen; ...; Han, Sirui*; Guo, Yike*.
ACL 2025 LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning, Shi, Weijie; ...; Han, Sirui*; Guo, Yike*.
[arXiv] [Code]
[arXiv] [Code]
ACL 2025 PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance, Li, Haoran; ...; Han, Sirui*; ...; Song, Yangqiu.
[arXiv] [Code]
[arXiv] [Code]
ACL 2025 FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation, Luo, Junyu; ...; Han, Sirui*; Zhang, Ming*; Guo, Yike.
[arXiv] [Code]
[arXiv] [Code]
ACL 2025 PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs, Ji, Jiaming; ...; Han, Sirui; Guo, Yike; Yang, Yaodong.
[arXiv] [Code]
[arXiv] [Code]
ACL 2025 Findings Boosting Policy and Process Reward Models with Monte Carlo Tree Search, Chan, Chi-Min; ...; Han, Sirui*; Guo, Yike*.
[GitHub]
[GitHub]
ACL 2025 Findings SafeLawBench: Towards Safe Alignment of Large Language Models, Cao, Chuxue; ...; Han, Sirui*; Guo, Yike*.
[arXiv] [Code]
[arXiv] [Code]
ACL 2025 Findings Out-of-Distribution Detection via LLM-Guided Outlier Generation, Lv, Xiangwei; ...; Han, Sirui; Liao, Beishui.
[Code]
[Code]
ACL 2025 Findings Benchmarking Multi-National Value Alignment for LLMs, Ju, Chengyi; ...; Han, Sirui*; Guo, Yike*.
[arXiv]
[arXiv]
ICCV 2025 Efficient Fine-Tuning of Large Models via Nested Low-Rank Adaptation, Li, Lujun; ...; Han, Sirui*; Guo, Yike*.
[arXiv] [GitHub]
[arXiv] [GitHub]
ICCV 2025 AIRA: Activation-Informed Low-Rank Adaptation, Li, Lujun; ...; Han, Sirui*; Guo, Yike*.
ICCV 2025 DanceEditor: Iterative Editable Music-driven Dance Generation, Zhang, Hengyuan; ...; Han, Sirui*.
ACM MM 2025 Consistent and Invariant Generalization Learning for Short-video Misinformation Detection, Guo, Hanghui; ...; Han, Sirui*.
ACM MM 2025 Outlier-Aware Model Merging for Efficient Multitask Inference, Zhu, Qiyuan; ...; Han, Sirui*; Guo, Yike*.
EMNLP 2025 Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning, Hu, Wenbin; ...; Han, Sirui; ...; Song, Yangqiu.
[arXiv] [Code]
[arXiv] [Code]
EMNLP 2025 DIDS: Domain Impact-aware Data Sampling, Shi, Weijie; ...; Han, Sirui*; Xu, Jiajie; Zhou, Xiaofang.
[arXiv] [Code]
[arXiv] [Code]
EMNLP 2025 Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving, Cao, Chuxue; ...; Han, Sirui*; Guo, Yike*.
[arXiv] [Code]
[arXiv] [Code]
EMNLP 2025 Findings Automate Strategy Finding with LLM in Quant Investment, Kou, Zhizhuo; ...; Han, Sirui*; Guo, Yike*.
[arXiv] [Code]
[arXiv] [Code]
Information Fusion 2025 Qi, X.Q.; ...; Han, S.R.*; ...; Guo, Y.K.* CoCoGesture: Towards coherent co-speech 3D gesture generation in the wild. Information Fusion, 103613.
[arXiv] [Project]
[arXiv] [Project]
2024 and Earlier
IRLE 2024 Han, S.R.*; Lu, H.T.; Wu, H. ESG Disclosure, Investor Awareness, and Carbon Risk Pricing. International Review of Law and Economics.
CAFR 2024 Han, S.R.*; Lu, H.T.; Wu, H. Revolutionizing Finance with Bitcoin and Blockchain: A Literature Review and Research Agenda. China Accounting and Finance Review.
ICCLR 2024 Han, S.R. Harmonizing Arbitration Rules for Non-Signatories in International Trade. International Company and Commercial Law Review, 2024(2), 90.
AJLE 2024 Han, S.R. Does Antitakeover Provision Harm Shareholders? Asian Journal of Law & Economics.
Frontiers 2023 Ye, F.F.; Han, S.R.*; Lu, H.T. Carbon Emissions Management Efficiency Evaluation. Frontiers in Environmental Science, 11, 1301091.
Sustainability 2023 Ye, F.F.; ...; Han, S.R.*; Yang, L.H. The Classification Impact of Different Types of Environmental Regulation on Chinese Provincial Carbon Emission Efficiency. Sustainability, 15, 12092.
ISKE 2023 Han, S.R.*; Lu, H.T.; Wu, H. Topic Modelling of Collision Reports in Autonomous Driving Systems. ISKE 2023 (Best Paper Award).
ICCLR 2022 Han, S.R. Self-regulatory Measures as Securities Regulation. ICCLR, 33(6), 350.
JCL 2016 Zou, M.; Pan, X.M.; Han, S.R. Regulating Collective Labour Disputes in China. Journal of Comparative Law, 10, 276.
GJCL 2015 Han, S.R. et al. Making, Enforcing and Accessing the Law. German Journal of Chinese Law, 22(1).
Working Papers & Preprints
arXiv 2026 AM3Safety: Towards Data Efficient Alignment of Multi-modal Multi-turn Safety for MLLMs
[arXiv]
[arXiv]
arXiv 2026 Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning
[arXiv]
[arXiv]
arXiv 2026 Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection
[arXiv]
[arXiv]
arXiv 2026 Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
[arXiv]
[arXiv]
arXiv 2026 Reinforcement Learning of Large Language Models for Interpretable Credit Card Fraud Detection
[arXiv]
[arXiv]
arXiv 2026 TwinRL-VLA: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation
[arXiv]
[arXiv]
arXiv 2026 Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training
[arXiv]
[arXiv]
arXiv 2025 InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents
[arXiv]
[arXiv]
arXiv 2025 MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery
[arXiv]
[arXiv]