Furong Huang

20

Papers

418

Total Citations

1

Affiliations

Affiliations

University of Maryland

Papers (20)

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models

Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL

GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning

Decodable and Sample Invariant Continuous Object Encoder

A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)

WAVES: Benchmarking the Robustness of Image Watermarks

PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control

Position: On the Possibilities of AI-Generated Text Detection

MaxMin-RLHF: Alignment with Diverse Human Preferences

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

Position: TrustLLM: Trustworthiness in Large Language Models

Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension

Zero-Shot Vision Encoder Grafting via LLM Surrogates

Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss