RoboCoach: World Models as Active Coaches for Compositional Robot Skills
Paper • 2609.39685 • Published • 14
Dohyun Kim
dohyun-k
·
AI & ML interests
Video generation, video diffusion models, temporal consistency, motion modeling
Recent Activity
upvoted a paper about 2 hours ago
RoboCoach: World Models as Active Coaches for Compositional Robot Skills upvoted a paper about 2 hours ago
Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model upvoted a paper about 2 hours ago
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video GenerationOrganizations
None yet
upvoted 5
papers about 2 hours ago
Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model
Paper • 2609.40358 • Published • 14
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
Paper • 2609.28923 • Published • 11
EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
Paper • 2609.38334 • Published • 71
BiasReducer: Adaptive Bias Mitigation for Reward Models
Paper • 2609.32720 • Published • 24
upvoted 5
papers 1 day ago
CompoWorld: Compositional Environment Scaling for General Agents
Paper • 2609.33665 • Published • 42
Agent-Editing World Model: Rethinking World Modeling for LLM Agents
Paper • 2609.28416 • Published • 43
Training Object Permanence in World Models
Paper • 2609.28654 • Published • 243
Precise Editing and Flexible Referencing for Interactable Worlds
Paper • 2609.34470 • Published • 20
Think Before You Score: Thinking Reward Model for Visual Generation
Paper • 2609.37372 • Published • 101
upvoted a paper 2 days ago
upvoted 4
papers 3 days ago
Anisotropic Representations Improve Planning in JEPA World Models
Paper • 2609.37441 • Published • 32
WorldAttention: An Efficient Attention Architecture for Interactive Video World Models
Paper • 2609.34606 • Published • 49
LongLive-Plug: Once-for-All Distillation for Video Generation
Paper • 2609.38154 • Published • 41
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Paper • 2609.34981 • Published • 136
upvoted 3
papers 4 days ago
In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion
Paper • 2609.32540 • Published • 33
WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon
Paper • 2609.35560 • Published • 31
Selecting Diverse SFT Traces Improves Post-RL Generalization
Paper • 2609.33780 • Published • 38
upvoted a paper 5 days ago
upvoted a paper 6 days ago