Hua Wei

Latent Adaptation of Foundation Policies for Sim-to-Real Transfer

Trajectory Graph Copilot: Pre-Action Error Diagnosis in LLM Agents

Where Reasoning Fails: Step-wise Confidence Attribution in Black-box LLMs

Leveraging Generative Trajectory Mismatch for Cross-Domain Policy Adaptation

CAR-LoRA: Training Compression-Aware and Robust LoRA Adapters for Evolving LLMs

Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations

Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology

Fully Heteroscedastic Count Regression with Deep Double Poisson Networks

RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation

Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models

Flexible Heteroscedastic Count Regression with Deep Double Poisson Networks

Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape

Segment as You Wish: Free-Form Language-Based Segmentation for Medical Images