Heng Huang

26

Papers

160

Total Citations

Papers (26)

A Unified and General Framework for Continual Learning

Prompting Language-Informed Distribution for Compositional Zero-Shot Learning

On the Role of Server Momentum in Federated Learning

Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation

Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment

Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold

Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models

De-mark: Watermark Removal in Large Language Models

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

ARGUS: Hallucination and Omission Evaluation in Video-LLMs

Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training

Delving into the Convergence of Generalized Smooth Minimax Optimization

Retrieval Across Any Domains via Large-scale Pre-trained Model

Accelerated Speculative Sampling Based on Tree Monte Carlo

LLaVA-Critic: Learning to Evaluate Multimodal Models

ODIN: Disentangled Reward Mitigates Hacking in RLHF

SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models

Federated Continuous Category Discovery and Learning

Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling

BilevelPruning: Unified Dynamic and Static Channel Pruning for Convolutional Neural Networks

Device-Wise Federated Network Pruning

Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch

InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models

Accelerated Policy Gradient for s-rectangular Robust MDPs with Large State Spaces

Defense against Model Extraction Attack by Bayesian Active Watermarking

A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models