Siyu Yuan

ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

Critique-RL: Training Language Models For Critiquing Through Two-Stage Reinforcement Learning

OS-Catalyst: Advancing Computer-Using Agents Efficiency through Adaptive Action Compression

WAPITI: A Watermark for Finetuned Open-Source LLMs

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation

ARIA: Training Language Agents with Intention-driven Reward Aggregation

ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints

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

The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement

CoSER: Coordinating LLM-Based Persona Simulation of Established Roles

WAPITI: A Watermark for Finetuned Open-Source LLMs