ReferClaw: Disambiguating User Intent for Egocentric Assistance
cs.CV, cs.AI, cs.MA
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification
- MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering
- EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence
- Companion-style QA Assistance in Ego-Vision
- Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- VisualClaw: A Real-Time, Personalized Agent for the Physical World
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
- Qwen3 Technical Report
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs