PaperHub
影响力指数
91.64/100
前 0.5%
全站排名 #296
发表论文54 篇
平均评分5.0
年均产出18.0 篇/年

Wentao Zhang

Assistant Professor@Peking University·中国·OpenReview
研究方向

AI for Science · Data-centric Machine Learning · Graph Deep Learning · Machine Learning Systems · AutoMatic Machine Learning

6.0
12

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

ICLR 2026Poster
通讯
6.0
24

WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization

ICLR 2026Poster
6.0
21

Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions

ICLR 2026Poster
6.0
39

Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking

ICLR 2026Poster
5.5
20

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks

ICLR 2026Poster
通讯
5.3
25

Dripper: Token-Efficient Main HTML Extraction with a Lightweight LM

ICLR 2026Rejected
4.7
18

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

ICLR 2026Rejected
通讯
4.5
15

AhaTrans: A Hierarchical Adaptive Transfer Learning Framework for Cross-City Traffic Flow Prediction

ICLR 2026Rejected
4.5
20

PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning

ICLR 2026Withdrawn
通讯
4.5
20

SAS-Bench: A Fine-Grained Benchmark for Evaluating Short Answer Scoring with Large Language Models

ICLR 2026Rejected
4.0
5

Demystifying Numerosity in Diffusion Models — Limitations and Remedies

ICLR 2026Withdrawn
4.0
5

Boosting RL-based Multimodal Reasoning via Difficulty Prior

ICLR 2026Withdrawn
4.0
11

Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning

ICLR 2026Withdrawn
通讯
4.0
29

FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding

ICLR 2026Poster
通讯
4.0
25

Jarvis: Towards Personalized AI Assistant via Personal KV-Cache Retrieval

ICLR 2026Rejected
通讯
4.0
5

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

ICLR 2026Rejected
通讯
4.0
13

Towards General Agentic Intelligence via Environment Scaling

ICLR 2026Withdrawn
3.5
6

SQLGovernor: An LLM-powered SQL Toolkit for Real World Application

ICLR 2026Rejected
3.3
4

UniCTokens-R1: Boosting Unified Personalization via Reinforcement Learning

ICLR 2026Withdrawn
通讯
2.5
5

xVerify: Efficient Answer Verifier for Reasoning Model Evaluations

ICLR 2026Withdrawn
2.5
5

GovBench: From Natural Language to Executable Pipelines, A New Benchmark for Data Governance Automation

ICLR 2026Withdrawn
通讯
7.0
16

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens

NeurIPS 2025Poster
通讯
6.8
30

MaintainCoder: Maintainable Code Generation Under Dynamic Requirements

NeurIPS 2025Poster
通讯
6.8
29

Multi-step Visual Reasoning with Visual Tokens Scaling and Verification

NeurIPS 2025Poster
通讯
6.7
15

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning

ICLR 2025Poster
通讯
6.5
15

Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning

ICLR 2025Poster
6.4
27

HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation

NeurIPS 2025Poster
6.4
19

Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos

NeurIPS 2025Poster
6.4
32

Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning

NeurIPS 2025Poster
6.1
15

Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation

ICML 2025Poster
5.8
21

Semantic Score Distillation Sampling for Compositional Text-to-3D Generation

ICLR 2025Rejected
通讯
5.7
19

Consistency Flow Matching: Defining Straight Flows with Velocity Consistency

ICLR 2025Rejected
5.5
10

Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training

ICML 2025Poster
通讯
5.5
45

Multi-Agent Collaborative Data Selection for Efficient Language Model Pretraining

ICLR 2025Rejected
5.4
25

Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training

ICLR 2025Rejected
通讯
5.0
29

IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts

ICLR 2025Poster
5.0
16

SysBench: Can LLMs Follow System Message?

ICLR 2025Poster
4.8
5

Transfer learning in Scalable Graph Neural Network for Improved Physical Simulation

ICLR 2025Withdrawn
4.8
23

QAEncoder: Towards Aligned Representation Learning in Question Answering System

ICLR 2025Withdrawn
通讯
4.4
23

Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning

ICLR 2025Rejected
三作
4.3
5

BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search

ICLR 2025Withdrawn
通讯
4.3
5

MathScape: Evaluating MLLMs in Multi-modal Math Scenarios through a Hierarchical Benchmark

ICLR 2025Withdrawn
4.0
5

FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs' Responsiveness to Human Feedback

ICLR 2025Withdrawn
通讯
4.0
5

Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis

ICLR 2025Withdrawn
通讯
4.0
5

PAS: Plug-and-Play Prompt Augmentation System

ICLR 2025Withdrawn
3.0
6

Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Models

ICLR 2025Withdrawn
通讯
合作者 (20)