3 papers
cs.CV2026
The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors
Shu Zhao, Tan Yu
Visual in-context learning (ICL) enables vision-language models (VLMs) to adapt at test time via demonstration examples, but its effectiveness depends critically on the examples se…
cs.CL2026
TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning
Muyu Pan, Shu Zhao, Nan Zhang +4
This paper investigates large language model (LLM) abstention learning, specifically using ternary reward, which incentivize truthfulness in large language models. This paper exten…
cs.AI2026
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
Aili Chen, Aonian Li, Baichuan Zhou +215
We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The…