Furong Huang's Lab at UMD

furonghuang-lab's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

minghuiliu 

updated a collection 16 days ago

Agent-Critic

Collection

3 items • Updated 16 days ago

russwang 

authored a paper 28 days ago

Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following

Paper • 2511.21662 • Published 30 days ago • 11

russwang 

authored a paper about 2 months ago

ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation

Paper • 2511.01163 • Published Nov 3 • 31

russwang 

authored 2 papers 3 months ago

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9 • 269

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Paper • 2509.23661 • Published Sep 28 • 47

russwang 

authored 3 papers 4 months ago

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding

Paper • 2506.06998 • Published Jun 8 • 1

CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning

Paper • 2507.00045 • Published Jun 23 • 1

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

Paper • 2509.00676 • Published Aug 31 • 84

furongh-lab 

authored a paper 6 months ago

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

Paper • 2506.10128 • Published Jun 11 • 22

russwang 

authored a paper 6 months ago

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

Paper • 2506.10128 • Published Jun 11 • 22

russwang 

authored a paper 7 months ago

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning

Paper • 2506.05523 • Published Jun 5 • 34

Zikui 

authored 5 papers 7 months ago

Cross-Modal Safety Alignment: Is textual unlearning all you need?

Paper • 2406.02575 • Published May 27, 2024 • 1

Single Layer Single Gradient Unlearning

Paper • 2407.11867 • Published Jul 16, 2024 • 1

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities

Paper • 2502.05209 • Published Feb 3 • 1

Zero-Shot Vision Encoder Grafting via LLM Surrogates

Paper • 2505.22664 • Published May 28 • 7

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning

Paper • 2506.05523 • Published Jun 5 • 34

Zikui 

updated a dataset 7 months ago

furonghuang-lab/morse-500

Updated Jun 9 • 11

Zikui 

published a dataset 7 months ago

furonghuang-lab/morse-500

Updated Jun 9 • 11