Huan Zhang

On The Fragility of Benchmark Contamination Detection in Reasoning Models

DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty

BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning

When Reasoning Meets Its Laws

TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning

TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

DecepChain: Inducing Deceptive Reasoning in Large Language Models

Geometri-Disentangelment Unlearning

GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning

Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs

Guaranteed Bounding Meshes Extraction from Neural Implicit Surfaces via Neural Network Verification

A Game-Theoretic Analysis of Attack by Hiding Intent

Lookahead Branching for Neural Network Verification

SNOV: A Scalable Near-global Optimal Verifier for Neural Networks under Large Perturbations

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification

Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion

Abstract Rendering: Certified Rendering Under 3D Semantic Uncertainty

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming

DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural Dynamics

The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination

ControlAgent: Automating Control System Design via Novel Integration of LLM Agents and Domain Expertise

Certified Training with Branch-and-Bound: A Case Study on Lyapunov-stable Neural Control

SATE: A Two-Stage Approach for Performance Prediction in Subpopulation Shift Scenarios

SVIP: Towards Verifiable Inference of Open-source Large Language Models