影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
73/100
前 2.2%
全站排名 #1,394
发表论文12 篇
平均评分
年均产出4.0 篇/年
Haizhong Zheng
研究方向
Efficient machine learning · Coreset selection; Data condensation · Adversarial training · adversarial machine learning
12
OPPO: Accelerating PPO-based RLHF via Pipeline Overlap
ICLR 2026Poster
25
Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?
ICLR 2026Poster
一作28
XRPO: Pushing the Limits of GRPO with Targeted Exploration and Exploitation
ICLR 2026Rejected
19
Jackpot: Align Actor-Policy Distribution for scalable and stable RL for LLM
ICLR 2026Poster
25
CamoDocs: Poisoning Attack against Retrieval-Augmented Language Models
ICLR 2026Rejected
二作21
Kinetics: Rethinking Test-Time Scaling Law
NeurIPS 2025Poster
三作17
ELFS: Label-Free Coreset Selection with Proxy Training Dynamics
ICLR 2025Poster
一作14
Plato: Plan to Efficient Decode for Large Language Model Inference
COLM 2025Poster
22
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
NeurIPS 2025Poster
一作