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
70.3/100
前 2.6%
全站排名 #1,672
发表论文17 篇
平均评分
年均产出5.7 篇/年
Banghua Zhu
研究方向
Reinforcement learning · computational economics · Foundation Models · Information Theory · Theoretical Statistics · Robust Statistics · Large Language Model
29
MMMG: A Comprehensive and Reliable Benchmark for Multitask Multimodal Generation
ICLR 2026Rejected
通讯18
Unlocking Long-Horizon Agentic Search with Large-Scale End-to-End RL
ICLR 2026Poster
19
Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression
ICLR 2026Poster
6
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
ICLR 2026Withdrawn
29
Taming Overconfidence in LLMs: Reward Calibration in RLHF
ICLR 2025Poster
三作25
How to Evaluate Reward Models for RLHF
ICLR 2025Poster
9
From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline
ICML 2025Poster
18
Watermarking using Semantic-aware Speculative Sampling: from Theory to Practice
ICLR 2025Rejected
19
Bench-O-Matic: Automating Benchmark Curation from Crowdsourced Data
ICLR 2025Rejected