CLARA: A Cognitively-Driven Clarification Framework for Grounding Ambiguous Requests
cs.RO, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/Zeqiang-Lai/Mini-DALLE3
Terminology
Sources
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Large Language Models for Robotics: A Survey
- InstructPix2Pix: Learning to Follow Image Editing Instructions
- DialogPaint: A Dialog-based Image Editing Model
- Instruction-Guided Editing Controls for Images and Multimedia: A Survey in LLM era
- ChatterBox: Multi-round Multimodal Referring and Grounding
- GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- The Llama 3 Herd of Models
- Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
- Segment Anything
- Resolution-robust Large Mask Inpainting with Fourier Convolutions
- Gemini: A Family of Highly Capable Multimodal Models
- Learning Transferable Visual Models From Natural Language Supervision
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