-
University of Illinois Urbana-Champaign
- Urbana, Illinois
- https://xiusic.github.io/
- https://orcid.org/0000-0002-9713-8000
- @XtremSup
- in/xiusi-chen-53180583
Highlights
- Pro
Stars
Official Repository for our paper: AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
[ICLR'26] RM-R1: Unleashing the Reasoning Potential of Reward Models
Can large language models provide useful feedback on research papers? A large-scale empirical analysis.
Our library for RL environments + evals
My learning notes for ML SYS.
[ICLR'24 spotlight] Tool-Augmented Reward Modeling
An Open-source RL System from ByteDance Seed and Tsinghua AIR
[ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Replicating the Illinois letterhead in latex
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
A bibliography and survey of the papers surrounding o1
Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".
MATCH: Metadata-Aware Text Classification in A Large Hierarchy (WWW'21)
HiGitClass: Keyword-Driven Hierarchical Classification of GitHub Repositories (ICDM'19)
Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains (AAAI'24)
Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding (Findings of EMNLP'23)
The Effect of Metadata on Scientific Literature Tagging: A Cross-Field Cross-Model Study (WWW'23)
Minimally Supervised Categorization of Text with Metadata (SIGIR'20)
Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification (WWW'22)