影响力指数
59.79/100
前 4.9%
全站排名 #3,134
发表论文22
平均评分4.7
年均产出11.0 篇/年

Yuanxing Zhang

Researcher@Kuaishou- 快手科技·中国·OpenReview
研究方向

Recommender System · Machine learning framework · Neural Architecture Search · Video Streaming and Content Delivery · Computer Network

7.0
30

AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration

ICLR 2026Poster
6.0
31

IF-VidCap: Can Video Caption Models Follow Instructions?

ICLR 2026Poster
二作
6.0
23

IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs

ICLR 2026Poster
二作
6.0
12

The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss

ICLR 2026Poster
5.5
33

VideoSearch Reasoner: Boosting Multimodal Reward Models through Think with Image Reasoning

ICLR 2026Rejected
5.5
33

ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation

ICLR 2026Rejected
4.7
30

VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks

ICLR 2026Poster
二作
4.7
4

A Reason-then-Describe Instruction Interpreter for Controllable Video Generation

ICLR 2026Withdrawn
三作
4.5
44

Transformers with Endogenous In-Context Learning: Bias Characterization and Mitigation

ICLR 2026Poster
4.5
44

OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

ICLR 2026Poster
4.5
13

OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing

ICLR 2026Rejected
4.5
26

HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs

ICLR 2026Withdrawn
4.0
6

Identifying Outcome-Oriented Root Causes via Cross Regression

ICLR 2026Rejected
4.0
5

Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM

ICLR 2026Rejected
4.0
17

MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

ICLR 2026Withdrawn
4.0
5

RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark

ICLR 2026Withdrawn
3.5
5

LVCap-Eval: Towards Holistic Long Video Caption Evaluation for Multimodal LLMs

ICLR 2026Withdrawn
三作
3.5
5

MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues

ICLR 2026Withdrawn
3.5
5

VideoScore2: Think before You Score in Generative Video Evaluation

ICLR 2026Withdrawn
2.5
5

Hybrid Attribution Priors for Explainable and Robust Model Training

ICLR 2026Withdrawn