WAMJET: A Harness for World Action Model Acceleration
cs.CV, cs.AI, cs.RO
Submitted: 2026-10-01
Updated: 2026-10-07
Comments: 8 pages, 3 figures, project page: https://liulixinkerry.github.io/WAMJET/index.html
Code: https://github.com/liulixinkerry/WAMJET
Project page: https://liulixinkerry.github.io/WAMJET/index.html
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Meta-Harness: End-to-End Optimization of Model Harnesses
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- OpenVLA: An Open-Source Vision-Language-Action Model
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- Unified Video Action Model
- World Action Models are Zero-shot Policies
- Progressive Distillation for Fast Sampling of Diffusion Models
- Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
- C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache
- AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents
- CUDA-LLM: LLMs Can Write Efficient CUDA Kernels
- CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization
- HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning
- Nautilus: From One Prompt to Plug-and-Play Robot Learning
- Show-Harness: Just a VLM Agent Can Play Robots
- Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation
- Causal World Modeling for Robot Control
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models