…https://huangrh99.github.io/AlphaGRPO/ View arXiv page View PDF Project page GitHub 50 Add to collection Community AlphaGRPO enables multimodal generation RL training across text and image generation for AR-Diffusion…
…AI-generated summary Biomolecular generators are often adapted with reward feedback to improve task-specific utility, but pushing utility alone can concentrate generation on a narrow family of candidates. Maintaining diversity is…
…A label-free policy learning converts free-form feedback into persistent parameter updates of the planner, reshaping subsequent coordination. These three layers co-evolve: reliable skills produce richer memory, richer memory informs…
…View arXiv page View PDF GitHub 0 Add to collection Community We introduce Omni-Persona, the first comprehensive benchmark for omnimodal personalization spanning text, image, and audio. Built on the Persona Modality…
…These fast "weights" can learn from textual feedback to absorb the task-specific information, while allowing slow weights to stay closer to the base model and persist general reasoning behaviors. Fast-Slow…
…https://github.com/slwang-ustc/nano-vllm-v1/tree/main I’d love for the community to try it out, give feedback, or contribute! The code is designed to be readable and…
…View arXiv page View PDF Project page GitHub 74 Add to collection Community Does a lexical retriever suffice for agentic search when agents can keep refining their queries? As LLMs become more…
…View arXiv page View PDF GitHub 0 Add to collection Community This is a work aimed for boosting RLVR performance using only minimal amount of SFT data in a unified training paradigm…
…While reinforcement learning from human feedback , particularly direct preference optimization , offers a potential solution, it necessitates the construction of strict preference pairs . However, curating such pairs for dynamic hand regions is prohibitively…
…rollout-feedback evolution yields more grounded SFT traces and better policy-matched RL tasks than static synthesis. View arXiv page View PDF Project page GitHub 26 Add to collection Community This work…