Learning to Live: A Step Toward Lifelong Embodied Intelligence
cs.RO, cs.CV
Submitted: 2026-10-30
Updated: 2026-11-12
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose
- AHA -- Predicting What Matters Next: Online Highlight Detection Without Looking Ahead
- Don't Pause! Every prediction matters in a streaming video
- ReSight: Task-Driven Self-Improving Memory for Embodied Agents
- Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection
- Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
- Rescaling Egocentric Vision
- Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
- Oops! Predicting Unintentional Action in Video
- TALL: Temporal Activity Localization via Language Query
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- Worth Remembering: Surprise-Gated Robot Episodic Memory
- Ego4D: Around the World in 3,000 Hours of Egocentric Video
- ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning
- LoRA: Low-Rank Adaptation of Large Language Models
- RAVEN: Long-Horizon Reasoning & Navigation with a Visuo-Spatio-Temporal Memory
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation