PaperHub

Heng Huang

~Heng_Huang1

49
论文总数
24.5
年均投稿
5.3
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

6.8
5

Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations

ICLR 2025Spotlight
7.5
5

On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization

NeurIPS 2025Spotlight
4.4
5

Data Efficient Continual Learning of Large Language Model

ICLR 2025Rejected
4.0
3

Achieve Performatively Optimal Policy for Performative Reinforcement Learning

ICML 2025Rejected
6.4
4

Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets

NeurIPS 2025Poster
4.5
4

Escaping Saddle Point Efficiently in Minimax and Bilevel Optimizations

ICLR 2025withdrawn
4.0
4

Hybrid Fine-Tuning of LLMs: Theoretical Insights on Generalized Smoothness and Convergence

ICLR 2025withdrawn
4.0
5

A Fast Federated Method for Minimax Problems with Sequential Convergence Guarantees

ICLR 2025withdrawn
3.5
4

Efficient Machine Unlearning for Deep Generative Models by Mitigating Optimization Conflicts

ICLR 2025withdrawn
2.5
3

Rectified Robust Policy Optimization for Robust Constrained Reinforcement Learning without Strong Duality

ICML 2025Rejected
6.8
4

Robust Distortion-Free Watermark for Autoregressive Audio Generation Models

NeurIPS 2025Poster
5.5
4

Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment

ICLR 2025Rejected
6.8
4

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

NeurIPS 2025Poster
7.6
3

Cost-Aware Contrastive Routing for LLMs

NeurIPS 2025Spotlight
4.0
4

Sharper Analysis of Data Echoing and New Communication-Efficient Algorithm for Data Parallelism

ICLR 2025Rejected
6.3
4

Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models

ICLR 2025Poster
5.8
4

Revisiting Convergence: A Study on Shuffling-Type Gradient Methods

ICLR 2025Rejected
6.1
4

Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness

ICML 2025Poster
3.8
4

Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment

ICML 2025Rejected
5.5
4

Bilevel ZOFO: Bridging Parameter-Efficient and Zeroth-Order Techniques for Efficient LLM Fine-Tuning and Meta-Training

ICLR 2025Rejected
4.8
3

De-mark: Watermark Removal in Large Language Models

ICML 2025Poster
6.6
5

Identification of Intermittent Temporal Latent Process

ICLR 2025Poster
5.0
4

Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework

ICLR 2025withdrawn
5.5
4

A Watermark for Order-Agnostic Language Models

ICLR 2025Poster
4.8
4

LLaVA-Critic: Learning to Evaluate Multimodal Models

ICLR 2025withdrawn
4.3
3

Pseudo- vs. True-Randomness: Rethinking Distortion-Free Watermarks of Language Models under Watermark Key Collisions

ICLR 2025withdrawn
4.2
5

From Pixels to Prose: A Large Dataset of Dense Image Captions

ICLR 2025withdrawn
3.5
4

RAG$^C$: Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models

ICLR 2025withdrawn
5.3
4

Towards Optimal Multi-draft Speculative Decoding

ICLR 2025Poster
4.2
5

OPTune: Efficient Online Preference Tuning

ICLR 2025withdrawn
6.0
4

OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities

ICLR 2025Poster

202418

6.5
4

Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models

NeurIPS 2024Poster
6.0
4

Model Sensitivity Aware Continual Learning

NeurIPS 2024Poster
5.6
5

Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling

NeurIPS 2024Poster
5.3
3

Escaping Saddle Point Efficiently in Minimax and Bilevel Optimizations

ICLR 2024Rejected
5.3
4

Prompting Language-Informed Distribution for Compositional Zero-Shot Learning

ICLR 2024Rejected
5.5
4

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

ICLR 2024Poster
5.8
6

On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning

ICLR 2024Poster
7.0
4

Dropout Enhanced Bilevel Training

ICLR 2024Spotlight
6.0
3

FedDA: Faster Adaptive Gradient Methods for Federated Constrained Optimization

ICLR 2024Poster
6.3
4

Robust Reinforcement Learning with General Utility

NeurIPS 2024Poster
5.3
4

A Unified and General Framework for Continual Learning

ICLR 2024Poster
5.7
3

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

ICLR 2024Rejected
4.5
4

DiPmark: A Stealthy, Efficient and Resilient Watermark for Large Language Models

ICLR 2024withdrawn
3.0
4

Enhancing Weakly Supervised 3D Medical Image Segmentation through Probabilistic-aware Learning

ICLR 2024withdrawn
5.3
4

ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark

NeurIPS 2024Poster
6.6
5

Unbiased Watermark for Large Language Models

ICLR 2024Spotlight
5.5
4

FedNovel: Federated Novel Class Learning

ICLR 2024Rejected
6.0
3

AlpaGasus: Training a Better Alpaca with Fewer Data

ICLR 2024Poster