DISCO distilled tree search named CoRL 2026 best-paper finalist, top 6 of 687
yining_hong · x · 2026-11-04
DISCO (Distilled Tree Search over Continuous Actions) is a CoRL 2026 best-paper finalist, top 6 of 687 submissions. It combines learned policies with Monte-Carlo Tree Search over continuous actions for long-horizon manipulation tasks, with a detailed technical thread from the authors.
Related event: DISCO Distilled Tree Search Named CoRL 2026 Best Paper Finalist(2 posts)→
More from Embodied
- Chris Paxton: interactive robot sim is the future but glaringly data-limited — Scobleizer · 2026-11-04
- DreamX: video diffusion models as universal latent action learners for robots — kaist-ai · 2026-11-04
- RoboTryOn turns human videos into robot demos, lifting success rate from 2% to 60% — kaist-ai · 2026-11-04
- INMO Future glasses: dual 1080p displays, 125g, $799 early-bird on Kickstarter Dec 10 — Scobleizer · 2026-11-04
- Tsinghua wires a fruit fly connectome into robots, boosting maze success by 30 points — 量子位 · 2026-11-04
- CMRI's Lion-ER-35B-A3B: open embodied reasoning MoE lifts all 10 benchmarks at ~3B active params — 量子位 · 2026-11-04