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
59.79/100
前 4.9%
全站排名 #3,134
发表论文22 篇
平均评分
年均产出11.0 篇/年
Yuanxing Zhang
研究方向
Recommender System · Machine learning framework · Neural Architecture Search · Video Streaming and Content Delivery · Computer Network
30
AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
ICLR 2026Poster
31
IF-VidCap: Can Video Caption Models Follow Instructions?
ICLR 2026Poster
二作23
IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs
ICLR 2026Poster
二作12
The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss
ICLR 2026Poster
33
VideoSearch Reasoner: Boosting Multimodal Reward Models through Think with Image Reasoning
ICLR 2026Rejected
33
ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation
ICLR 2026Rejected
30
VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks
ICLR 2026Poster
二作4
A Reason-then-Describe Instruction Interpreter for Controllable Video Generation
ICLR 2026Withdrawn
三作44
Transformers with Endogenous In-Context Learning: Bias Characterization and Mitigation
ICLR 2026Poster
44
OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs
ICLR 2026Poster
13
OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing
ICLR 2026Rejected
26
HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs
ICLR 2026Withdrawn
6
Identifying Outcome-Oriented Root Causes via Cross Regression
ICLR 2026Rejected
5
Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM
ICLR 2026Rejected
17
MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
ICLR 2026Withdrawn
5
RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark
ICLR 2026Withdrawn
5
LVCap-Eval: Towards Holistic Long Video Caption Evaluation for Multimodal LLMs
ICLR 2026Withdrawn
三作5
MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues
ICLR 2026Withdrawn
5
VideoScore2: Think before You Score in Generative Video Evaluation
ICLR 2026Withdrawn
5
Hybrid Attribution Priors for Explainable and Robust Model Training
ICLR 2026Withdrawn