影响力指数

53.34/100

前 7%

全站排名 #4,501

发表论文14 篇

平均评分5.7

年均产出4.7 篇/年

Zheng Ge

Researcher@Stepfun·中国·OpenReview

研究方向

Alignment & Post Training for LLM/VLM · Large Multimodal Models · Unified Architecture for Next Generation Multimodal Models

4.7

Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

ICLR 2026Rejected

三作

4.5

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

ICLR 2026Oral

6.8

GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning

NeurIPS 2025Poster

6.5

Unhackable Temporal Reward for Scalable Video MLLMs

ICLR 2025Poster

6.4

Perception-R1: Pioneering Perception Policy with Reinforcement Learning

NeurIPS 2025Poster

6.4

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

合作者 (20)

Zheng Ge

Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning

Unhackable Temporal Reward for Scalable Video MLLMs

Perception-R1: Pioneering Perception Policy with Reinforcement Learning

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

Perception in Reflection

DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation

Reconstructive Visual Instruction Tuning

PerPO: Perceptual Preference Optimization via Discriminative Rewarding

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Seeking the Right Question: Towards High-Quality Visual Instruction Generation