Furong Huang Lab at UMD

furongh-lab's activity

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

upvoted a paper 1 day ago

On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective

Paper • 2502.14296 • Published 4 days ago • 42

liked a Space 5 months ago

Running

4

4

Erasing the Invisible

🌊

Upload images to detect and rank watermark removal

authored 17 papers 11 months ago

Decodable and Sample Invariant Continuous Object Encoder

Paper • 2311.00187 • Published Oct 31, 2023 • 1

MaxMin-RLHF: Towards Equitable Alignment of Large Language Models with Diverse Human Preferences

Paper • 2402.08925 • Published Feb 14, 2024 • 1

AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models

Paper • 2310.15140 • Published Oct 23, 2023 • 1

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

Paper • 2310.07220 • Published Oct 11, 2023 • 1

Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences

Paper • 2401.10529 • Published Jan 19, 2024 • 1

Explore Spurious Correlations at the Concept Level in Language Models for Text Classification

Paper • 2311.08648 • Published Nov 15, 2023 • 2

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Paper • 2310.19668 • Published Oct 30, 2023 • 3

TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning

Paper • 2306.13229 • Published Jun 22, 2023 • 3

Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy

Paper • 2207.12141 • Published Jul 25, 2022

Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function

Paper • 2302.01244 • Published Feb 2, 2023

Benchmarking the Robustness of Image Watermarks

Paper • 2401.08573 • Published Jan 16, 2024 • 1

PRISE: Learning Temporal Action Abstractions as a Sequence Compression Problem

Paper • 2402.10450 • Published Feb 16, 2024 • 1

PARL: A Unified Framework for Policy Alignment in Reinforcement Learning

Paper • 2308.02585 • Published Aug 3, 2023

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies

Paper • 2402.12673 • Published Feb 20, 2024

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

Paper • 2305.17342 • Published May 27, 2023

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

Paper • 2307.12062 • Published Jul 22, 2023

Reviving Shift Equivariance in Vision Transformers

Paper • 2306.07470 • Published Jun 13, 2023 • 1

authored a paper about 1 year ago

Premier-TACO: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

Paper • 2402.06187 • Published Feb 9, 2024 • 11