影响力指数

53.05/100

前 7.1%

全站排名 #4,571

发表论文13 篇

平均评分4.9

年均产出4.3 篇/年

Alex Jinpeng Wang

Full Professor@Central South University·中国·OpenReview

研究方向

Data-centric AI · Large Language Model · Cross-modality Learning · Vision Language Model · Self-supervised Learning · Action Recognition · Video Understanding

5.5

OR-PRM: A Process Reward Model for Algorithmic Problem in Operations Research

ICLR 2026Poster

4.5

TextAtlas5M: A Large-Scale Dataset for Long and Structured Text Image Generation

ICLR 2026Rejected

一作

4.0

See the Text: From Tokenization to Visual Reading

ICLR 2026Rejected

二作

4.0

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models

ICLR 2026Withdrawn

4.0

Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT

ICLR 2026Rejected

3.3

Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought

NeurIPS 2025Poster

5.5

OmniContrast: Vision-Language-Interleaved Contrast from Pixels All at once

合作者 (20)

Alex Jinpeng Wang

OR-PRM: A Process Reward Model for Algorithmic Problem in Operations Research

TextAtlas5M: A Large-Scale Dataset for Long and Structured Text Image Generation

See the Text: From Tokenization to Visual Reading

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models

Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT

VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation

From Charts to Code: A Hierarchical Benchmark for Multimodal Models

Vision-centric Token Compression in Large Language Model

VaporTok: RL-Driven Adaptive Video Tokenizer with Prior & Task Awareness

Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought

OmniContrast: Vision-Language-Interleaved Contrast from Pixels All at once