Predictive Representation Learning for Manipulation via Streaming Egocentric 3D Hand Forecasting
cs.CV
Submitted: 2025-11-22
Updated: 2026-11-06
Terminology
Sources
- What Makes Pre-Trained Visual Representations Successful for Robust Manipulation?
- In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data
- Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
- On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
- The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation
- EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs
- EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
- InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
- RealDex: Towards Human-like Grasping for Robotic Dexterous Hand
- Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
- MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos
- Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos
- VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
- InsTALL: Context-aware Instructional Task Assistance with Multi-modal Large Language Models
- EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
- Embodied Hands: Modeling and Capturing Hands and Bodies Together
- EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation
- Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling
- TimeGazer: Temporal Modeling of Predictive Gaze Stabilization for AR Interaction
- EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos
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