PPaperPicks

Tongzhou Mu

4 papers at tracked venues · 4 at CORE A* · active 2024–2025

DBLP profile ↗ORCID search ↗

Venues

ICLR ×2AAAI ×1ICML ×1

Frequent coauthors

Adrià López Escoriza
DBLP profile ↗ORCID search ↗
×1
Xiu Yuan
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
    ICML 2025 ·
    Adrià López Escoriza
    DBLP profile ↗ORCID search ↗
  2. Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
    ICLR 2025 ·
    Xiu Yuan
    DBLP profile ↗ORCID search ↗
  3. When Should We Prefer State-to-Visual DAgger over Visual Reinforcement Learning?
    AAAI 2025 · Tongzhou Mu
  4. DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks
    ICLR 2024 · Tongzhou Mu