Where to Generate Touch: Do Image Latents Preserve Material Recognition?
cs.CV, cs.RO
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- FlowTouch: View-Invariant Visuo-Tactile Prediction
- Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
- Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
- Towards Generalization of Tactile Image Generation: Reference-Free Evaluation in a Leakage-Free Setting
- HT-Bench: Benchmarking and Learning Dexterous Full-Hand Tactile Representations with Egocentric Vision
- Achieving Time Series Reasoning Requires Rethinking Model Design, Tasks Formulation, and Evaluation
- VQ-Touch: A Data-Efficient Tactile Generation Framework Across Sensors and Scenarios
- Cosmos World Foundation Model Platform for Physical AI
- Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
- TacGen: Touch Is a Necessary Dimension of Physical-World Representation -- Addressing Tactile Data Scarcity with Scalable Vision-to-Touch Alignment and Generation
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