Research insights and technical deep-dives from the Gen-Verse team at Princeton.
Exploring how thought-augmented reasoning and template distillation can unlock stronger problem-solving capabilities in large language models — from Buffer of Thoughts to ReasonFlux.
Building AI systems that co-evolve environments, policies, and reward models — from code generation with reinforcement learning to personalized agent fine-tuning through natural conversation.
Advancing the frontier of diffusion-based language modeling — from reinforcement learning frameworks for discrete diffusion to multimodal generation and efficient parallel decoding.