VLDA From HIT and Baidu Reframes Robot Control as Compact Transition Delta Modeling
LoongForge · hf · 2026-10-20
Harbin Institute of Technology (Shenzhen) and Baidu propose Vision-Language-Delta-Action (VLDA), which reformulates robotic manipulation as compact transition modeling via a Delta variable bridging vision-language understanding and action generation, targeting task-specified state changes rather than direct observation-to-action mapping, improving long-horizon consistency and generalization.
More from Embodied
- MIT CSAIL's X-Hinges 3D-Prints Everyday Objects With Built-In Sensing Across Three Motion Axes — MIT News AI · 2026-10-23
- Formic raises $50M Series B to scale physical AI across 100+ US factories — garrytan · 2026-10-23
- fal starts fine-tuning a physical robot to draw, results next week — OdinLovis · 2026-10-23
- PEARL demo: an LLM agent that checks experiment results, revises plans, and re-tests — KevinKaichuang · 2026-10-23
- CU Boulder's ATLAS Institute Opens Tenure-Track Robotics Professorship — ryosuzk · 2026-10-23
- MiTaS multi-resolution tactile imitation learning hits 80% success vs 35.5% vision-only baseline — Jan_R_Peters · 2026-10-23