Rahul Sajnani, Diego Romeres, Mingyuan Zhang, Kai Gao, Carl Qi, Baichuan Huang, Srinath Sridhar, Dylan Randle · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28626 · open-access PDF
Bermotivasi oleh kemampuan manusia untuk mengintegrasikan pengalaman di seluruh bahasa, persepsi, dan tindakan, kami memperkenalkan UniWALM, sebuah model bahasa aksi dunia yang bersatu yang mempelajari video, tindakan, dan bahasa dalam satu representasi bersama, di mana setiap modalitas adalah sinyal kondisioner dan sasaran pengawasan. Kami bertanya: dapat bahasa yang dihasilkan bersama memperkaya representasi bersama ini, meningkatkan manipulasi dan mendukung perilaku bergantung pada memori?
Machine translation (Meta M2M100); the English original follows.
Motivated by the human ability to integrate experience across language, perception, and action, we introduce UniWALM, a unified world-action-language model that learns video, action, and language in a single shared representation, where each modality is both a conditioning signal and a supervision target. We ask: can jointly generating language enrich this shared representation, improving manipulation and supporting memory-dependent behavior? Unlike prior approaches that attach a reasoning or vision-language model to a video-action backbone and run them as distinct stages, UniWALM unifies all
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28626, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange