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
75.63/100
前 1.8%
全站排名 #1,164
发表论文34 篇
平均评分
年均产出11.3 篇/年
Wangchunshu Zhou
研究方向
large language models · efficient deep learning · natural language generation · pertained language models · natural language processing
14
AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
ICLR 2026Poster
13
Reverse-Engineered Reasoning for Open-Ended Generation
ICLR 2026Poster
25
ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding
ICLR 2026Poster
23
IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs
ICLR 2026Poster
23
Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution
ICLR 2026Poster
通讯13
TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling
ICLR 2026Rejected
19
TaskCraft: Automated Generation of Agentic Tasks
ICLR 2026Poster
通讯33
A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
ICLR 2026Poster
通讯28
VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking
ICLR 2026Rejected
18
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
ICLR 2026Rejected
通讯17
ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
ICLR 2026Poster
通讯20
PERSONAFEEDBACK: A Large-scale Human-annotated Benchmark For Personalization
ICLR 2026Rejected
通讯5
MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants
ICLR 2026Rejected
通讯26
O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
ICLR 2026Withdrawn
通讯17
Towards Personalized Deep Research: Benchmarks and Evaluations
ICLR 2026Poster
通讯6
Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures
ICLR 2026Rejected
17
MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
ICLR 2026Withdrawn
15
O-Reseacher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL
ICLR 2026Rejected
通讯5
Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
ICLR 2026Withdrawn
通讯5
VideoScore2: Think before You Score in Generative Video Evaluation
ICLR 2026Withdrawn
5
Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning
ICLR 2026Withdrawn
通讯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19
KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation
NeurIPS 2025Spotlight
13
M+: Extending MemoryLLM with Scalable Long-Term Memory
ICML 2025Poster
19
ChemAgent: Self-updating Memories in Large Language Models Improves Chemical Reasoning
ICLR 2025Poster
33
ML-Bench: Evaluating Large Language Models for Code Generation in Repository-Level Machine Learning Tasks
ICLR 2025Rejected
28
MIO: A Foundation Model on Multimodal Tokens
ICLR 2025Rejected
32
AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
ICLR 2025Rejected
20
HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
ICLR 2025Withdrawn
6
Symbolic Learning Enables Self-Evolving Agents
ICLR 2025Rejected
一作