Disentangling Task-Relevant Latent Dynamics for Reward Modeling
cs.RO, cs.CV
Submitted: 2026-10-09
Updated: 2026-10-09
Project page: https://ditarr.github.io
Terminology
Sources
- Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- Mastering Diverse Domains through World Models
- RoboReward: General-Purpose Vision-Language Reward Models for Robotics
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
- Wan: Open and Advanced Large-Scale Video Generative Models
- A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
- CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies