影响力指数
75.63/100
前 1.8%
全站排名 #1,164
发表论文34
平均评分4.9
年均产出11.3 篇/年

Wangchunshu Zhou

Researcher@Guangdong OPPO Mobile Telecommunications Corp.,Ltd.·中国·OpenReview
研究方向

large language models · efficient deep learning · natural language generation · pertained language models · natural language processing

6.0
14

AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?

ICLR 2026Poster
6.0
13

Reverse-Engineered Reasoning for Open-Ended Generation

ICLR 2026Poster
6.0
25

ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding

ICLR 2026Poster
6.0
23

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

ICLR 2026Poster
5.6
23

Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution

ICLR 2026Poster
通讯
5.5
13

TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling

ICLR 2026Rejected
5.5
19

TaskCraft: Automated Generation of Agentic Tasks

ICLR 2026Poster
通讯
5.0
33

A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning

ICLR 2026Poster
通讯
5.0
28

VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking

ICLR 2026Rejected
4.7
18

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

ICLR 2026Rejected
通讯
4.5
17

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems

ICLR 2026Poster
通讯
4.0
20

PERSONAFEEDBACK: A Large-scale Human-annotated Benchmark For Personalization

ICLR 2026Rejected
通讯
4.0
5

MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants

ICLR 2026Rejected
通讯
4.0
26

O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents

ICLR 2026Withdrawn
通讯
4.0
17

Towards Personalized Deep Research: Benchmarks and Evaluations

ICLR 2026Poster
通讯
4.0
6

Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

ICLR 2026Rejected
4.0
17

MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

ICLR 2026Withdrawn
3.5
15

O-Reseacher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL

ICLR 2026Rejected
通讯
3.5
5

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

ICLR 2026Withdrawn
通讯
3.5
5

VideoScore2: Think before You Score in Generative Video Evaluation

ICLR 2026Withdrawn
3.0
5

Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning

ICLR 2026Withdrawn
通讯
3.0
5

COIG-Writer: A High-Quality Chinese Creative Writing with Thought Process Dataset

ICLR 2026Withdrawn
-1

Compressed Step Information Memory for End-to-End Agent Foundation Models

ICLR 2026Withdrawn
通讯