Heng Huang
~Heng_Huang1
49
论文总数
24.5
年均投稿
平均评分
接收情况25/49
会议分布
ICLR
34
NeurIPS
10
ICML
5
发表论文 (49 篇)
202531 篇
5
Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations
ICLR 2025Spotlight
5
On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
NeurIPS 2025Spotlight
5
Data Efficient Continual Learning of Large Language Model
ICLR 2025Rejected
3
Achieve Performatively Optimal Policy for Performative Reinforcement Learning
ICML 2025Rejected
4
Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets
NeurIPS 2025Poster
4
Escaping Saddle Point Efficiently in Minimax and Bilevel Optimizations
ICLR 2025withdrawn
4
Hybrid Fine-Tuning of LLMs: Theoretical Insights on Generalized Smoothness and Convergence
ICLR 2025withdrawn
5
A Fast Federated Method for Minimax Problems with Sequential Convergence Guarantees
ICLR 2025withdrawn
4
Efficient Machine Unlearning for Deep Generative Models by Mitigating Optimization Conflicts
ICLR 2025withdrawn
3
Rectified Robust Policy Optimization for Robust Constrained Reinforcement Learning without Strong Duality
ICML 2025Rejected
4
Robust Distortion-Free Watermark for Autoregressive Audio Generation Models
NeurIPS 2025Poster
4
Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment
ICLR 2025Rejected
4
Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training
NeurIPS 2025Poster
3
Cost-Aware Contrastive Routing for LLMs
NeurIPS 2025Spotlight
4
Sharper Analysis of Data Echoing and New Communication-Efficient Algorithm for Data Parallelism
ICLR 2025Rejected
4
Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models
ICLR 2025Poster
4
Revisiting Convergence: A Study on Shuffling-Type Gradient Methods
ICLR 2025Rejected
4
Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness
ICML 2025Poster
4
Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment
ICML 2025Rejected
4
Bilevel ZOFO: Bridging Parameter-Efficient and Zeroth-Order Techniques for Efficient LLM Fine-Tuning and Meta-Training
ICLR 2025Rejected
3
De-mark: Watermark Removal in Large Language Models
ICML 2025Poster
5
Identification of Intermittent Temporal Latent Process
ICLR 2025Poster
4
Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework
ICLR 2025withdrawn
4
A Watermark for Order-Agnostic Language Models
ICLR 2025Poster
4
LLaVA-Critic: Learning to Evaluate Multimodal Models
ICLR 2025withdrawn
3
Pseudo- vs. True-Randomness: Rethinking Distortion-Free Watermarks of Language Models under Watermark Key Collisions
ICLR 2025withdrawn
5
From Pixels to Prose: A Large Dataset of Dense Image Captions
ICLR 2025withdrawn
4
RAG$^C$: Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models
ICLR 2025withdrawn
4
Towards Optimal Multi-draft Speculative Decoding
ICLR 2025Poster
5
OPTune: Efficient Online Preference Tuning
ICLR 2025withdrawn
4
OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities
ICLR 2025Poster
202418 篇
4
Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models
NeurIPS 2024Poster
4
Model Sensitivity Aware Continual Learning
NeurIPS 2024Poster
5
Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling
NeurIPS 2024Poster
3
Escaping Saddle Point Efficiently in Minimax and Bilevel Optimizations
ICLR 2024Rejected
4
Prompting Language-Informed Distribution for Compositional Zero-Shot Learning
ICLR 2024Rejected
4
Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
ICLR 2024Poster
6
On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning
ICLR 2024Poster
4
Dropout Enhanced Bilevel Training
ICLR 2024Spotlight
3
FedDA: Faster Adaptive Gradient Methods for Federated Constrained Optimization
ICLR 2024Poster
4
Robust Reinforcement Learning with General Utility
NeurIPS 2024Poster
4
A Unified and General Framework for Continual Learning
ICLR 2024Poster
3
InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
ICLR 2024Rejected
4
DiPmark: A Stealthy, Efficient and Resilient Watermark for Large Language Models
ICLR 2024withdrawn
4
Enhancing Weakly Supervised 3D Medical Image Segmentation through Probabilistic-aware Learning
ICLR 2024withdrawn
4
ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark
NeurIPS 2024Poster
5
Unbiased Watermark for Large Language Models
ICLR 2024Spotlight
4
FedNovel: Federated Novel Class Learning
ICLR 2024Rejected
3
AlpaGasus: Training a Better Alpaca with Fewer Data
ICLR 2024Poster