Knowledge Works Lab at Fudan University

university

Verified

http://kw.fudan.edu.cn

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

xjhuang authored a paper about 1 month ago

CCTU: A Benchmark for Tool Use under Complex Constraints

xjhuang authored a paper about 1 month ago

AI Can Learn Scientific Taste

xjhuang authored a paper 3 months ago

AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems

View all activity

submitted a paper to Daily Papers 3 days ago

GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)

Paper • 2604.17091 • Published 6 days ago • 9

authored 2 papers about 1 month ago

CCTU: A Benchmark for Tool Use under Complex Constraints

Paper • 2603.15309 • Published Mar 16 • 2

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published Mar 15 • 426

authored a paper 3 months ago

AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems

Paper • 2601.11354 • Published Jan 16 • 4

authored a paper 3 months ago

LSRIF: Logic-Structured Reinforcement Learning for Instruction Following

Paper • 2601.06431 • Published Jan 10 • 12

authored 2 papers 7 months ago

Lossless KV Cache Compression to 2%

Paper • 2410.15252 • Published Oct 20, 2024 • 2

Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought

Paper • 2505.15431 • Published May 21, 2025 • 2

authored a paper 10 months ago

Pre-Trained Policy Discriminators are General Reward Models

Paper • 2507.05197 • Published Jul 7, 2025 • 39

authored a paper 11 months ago

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles

Paper • 2505.19914 • Published May 26, 2025 • 46

authored 2 papers 11 months ago

WorldPM: Scaling Human Preference Modeling

Paper • 2505.10527 • Published May 15, 2025 • 34

A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models

Paper • 2505.07591 • Published May 12, 2025 • 11

authored a paper about 1 year ago

BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation

Paper • 2504.14538 • Published Apr 20, 2025 • 30

authored a paper about 1 year ago

TransMamba: Flexibly Switching between Transformer and Mamba

Paper • 2503.24067 • Published Mar 31, 2025 • 21

authored 2 papers about 1 year ago

Implicit Reasoning in Transformers is Reasoning through Shortcuts

Paper • 2503.07604 • Published Mar 10, 2025 • 23

CoSER: Coordinating LLM-Based Persona Simulation of Established Roles

Paper • 2502.09082 • Published Feb 13, 2025 • 32

authored a paper over 1 year ago

Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training

Paper • 2501.11425 • Published Jan 20, 2025 • 109

authored a paper over 1 year ago

ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning

Paper • 2501.06590 • Published Jan 11, 2025 • 11

authored a paper over 1 year ago

Scaling Laws for Floating Point Quantization Training

Paper • 2501.02423 • Published Jan 5, 2025 • 26

authored a paper over 1 year ago

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use

Paper • 2501.02506 • Published Jan 5, 2025 • 11

authored a paper over 1 year ago

OpenDevin: An Open Platform for AI Software Developers as Generalist Agents

Paper • 2407.16741 • Published Jul 23, 2024 • 77