SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis received the 🏆 Best Paper Honorable Mention at DataWorld @ ICML 2025! Congrats to Zijian Wu, Jinjie Ni, Xiangyan Liu and our collaborators!
SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis

One paper will be presented at COLM 2025. Congrats to Keyu Duan and our collaborators!
Efficient Process Reward Model Training via Active Learning

Two papers will be presented at ICML 2025. Congrats to Guanzheng Chen, Qilong Feng, Keyu Duan, Yiran Zhao and our collaborators!
Unnatural Languages Are Not Bugs but Features for LLMs
Long-Context Inference with Retrieval-Augmented Speculative Decoding (Spotlight)

One paper will be presented at NAACL 2025. Congrats to Xiangyan Liu, and our collaborators!
CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases

Three papers will be presented at ICLR 2025. Congrats to Jinjie Ni, Yiran Zhao, Guanzheng Chen, and our collaborators!
MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures (Spotlight)
Identifying and Tuning Safety Neurons in Large Language Models
LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization

One paper will be presented at AAAI 2025. Congrats to Leon Lin, Hannah Brown and our collaborators!
Single Character Perturbations Break LLM Alignment

Two papers will be presented at NeurIPS 2024. Congrats to Yiran Zhao, Yuxi Xie and our collaborators!
Accelerating greedy coordinate gradient via probe sampling
Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning (Workshop)

Two papers will be presented at EMNLP 2024. Congrats to Esther Gan, Yiran Zhao, Hongfu Liu, Yuxi Xie and our collaborators!
Reasoning Robustness of LLMs to Adversarial Typographical Errors
Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models

Two papers will be presented at ACL 2024. Congrats to Kaixin Li, Qisheng Hu, Xuan Long Do, Yiran Zhao, Hannah Brown and our collaborators!
Prompt Optimization via Adversarial In-Context Learning (Oral)
Instructcoder: Instruction tuning large language models for code editing (Workshop)

One paper will be presented at NeurIPS 2023. Congrats to Yuxi Xie and our collaborators!
Self-Evaluation Guided Beam Search for Reasoning