Zhipeng Wang

Users can now prove the legitimacy of their crypto deposits without sacrificing privacy, shifting compliance from platforms to individuals.

Mags-RL lets multimodal LLMs see the forest *and* the trees, using reinforcement learning to guide a super-resolution agent that selectively enhances image regions for improved reasoning without extra annotations.

Training on 500K automatically-curated ophthalmology instructions lets a vision-language model leapfrog general medical models in a specialized domain.

Overconfident tokens, often missed by entropy-based methods, carry surprisingly dense corrective signals in on-policy distillation, allowing for near-baseline performance with <10% of tokens.

Reasoning models aren't just verbose, they're actively *harmed* by their own verbosity, but a simple self-distillation trick can compress their outputs by up to 59% while boosting accuracy by up to 16 points.