Jing Huo

Distractor-free Generalizable 3D Gaussian Splatting

SpatialComposer: 3D Spatial Object Insertion via Image Gaussian Composition

MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems

SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks

Identity-Preserving Human Reconstruction from a Single Image via Explicit 3D Reasoning

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation

RoboHiMan: A Hierarchical Evaluation Paradigm for Compositional Generalization in Long-Horizon Manipulation

DGPO: Mitigating Likelihood Displacement with Bidirectional KL Divergence Gap

R2Q: Residual Refinement Quantization for Robust 2-Bit Large Language Models

Multi-Agent Reinforcement Learning with Communication-Constrained Priors

Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment

Causal Information Prioritization for Efficient Reinforcement Learning

Towards Empowerment Gain through Causal Structure Learning in Model-Based Reinforcement Learning

GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation

Enhancing Trust-Region Bayesian Optimization via Derivatives of Gaussian Processes