Li Xiaozhe

OPT-BENCH. [ACL 2026] OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces

SERL. Official implement on 'What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents'

NP-Engine. [ACL 2026] Official implement on 'Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs'

DMPO. [ICML 2026] Official implement on 'Beyond Mode Collapse: Distribution Matching for Diverse Reasoning'

Awesome-MLLM-Hallucination-and-Alignment. Recent works about (M)LLM hallucination and alignment.

COINBench. Python

Cinemadiff.github.io.

OliverLeeXZ.

OliverLeeXZ.github.io. CSS