BLM 1 : A Boundless Large Model for Cross-Space, Cross-Task, and Cross-Embodiment Learning
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 9402-9411
Abstract
No abstract availableFunding Information
- Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China (JYB2025XDXM103)
- New Generation Artificial Intelligence-National Science and Technology Major Project (2025ZD0123000)
- Central Guidance on Local Science and Technology Development Fund of Shanghai City (YDZX20253100002004)
- AI for Science \"Hundred Teams, Hundred Projects\" Program (2025-GZL-RGZN-BTBX-02020)
This publication has 28 references indexed in Scilit:
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningNature, 2025
- RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete2025
- Magma: A Foundation Model for Multimodal AI Agents2025
- Universal Actions for Enhanced Embodied Foundation Models2025
- EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models2024
- MMMU: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI2024
- Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks2024
- Sigmoid Loss for Language Image Pre-Training2023
- HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World2023
- EVA: Exploring the Limits of Masked Visual Representation Learning at Scale2023