hkust-nlp

Simple RL training for reasoning

Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

[ICML 2025 Oral] CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

An Analytical Evaluation Board of Multi-turn LLM Agents [NeurIPS 2024 Oral]

[KernelGYM & Dr. Kernel] A distributed GPU environment and a collection of RL training methods to support RL for Kernel Generations [ICML 2026]

Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]

The official repo of "WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents"

[NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*

B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

[ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning

Benchmarking multimodal agents on realistic, ultra-challenging visual scenarios requiring long-horizon hybrid tool use.

[ICLR2026] Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

[ICML 2025] Predictive Data Selection: The Data That Predicts Is the Data That Teaches

Benchmarking Language Agents Under Controllable and Extreme Context Growth

Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models" (NeurIPS 2023)

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)

[NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"