Show, Don't Tell: Detecting Novel Objects by Watching Human Videos
cs.CV, cs.LG, cs.RO
Submitted: 2026-03-13
Updated: 2026-11-09
Terminology
Sources
- Detect Anything via Next Point Prediction
- GPT-4o System Card
- Gemini: A Family of Highly Capable Multimodal Models
- Gemini Robotics: Bringing AI into the Physical World
- Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
- SAM 3: Segment Anything with Concepts
- SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory
- GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training
Related papers
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- 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
- From Formulas to Protocols: A Compositional View of Binary Target Segmentation Metrics
- Traffic Sign Recognition in Autonomous Driving: Dataset, Benchmark, and Field Experiment