DeltaWAM: Delta World Action Models for Bimanual Manipulation
Paper • 2609.28811 • Published • 3
samusenps PRO
samusenps
AI & ML interests
New & Foundational Architectures, World Models, Multi-Modality, Interpretability , High Quality Training Data, Reproducible Open Source
Recent Activity
upvoted a paper about 18 hours ago
DeltaWAM: Delta World Action Models for Bimanual Manipulation upvoted a paper about 18 hours ago
PUBG Ally: A Conversational Embodied Agent as an AI Teammate upvoted a paper about 18 hours ago
ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien WorldsOrganizations
upvoted 9
papers about 18 hours ago
PUBG Ally: A Conversational Embodied Agent as an AI Teammate
Paper • 2609.29837 • Published • 6
ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds
Paper • 2609.30199 • Published • 12
Coding Agents for Generalized Task and Motion Planning Problems
Paper • 2609.30233 • Published • 10
Agent-Editing World Model: Rethinking World Modeling for LLM Agents
Paper • 2609.28416 • Published • 19
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
Paper • 2609.29845 • Published • 74
Learning to Discover Interesting Mathematics
Paper • 2609.28603 • Published • 10
World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal
Paper • 2609.29964 • Published • 7
Training Object Permanence in World Models
Paper • 2609.28654 • Published • 203
liked a
Space 1 day ago
liked a
Space 4 days ago
upvoted a paper 7 days ago
upvoted 8
papers 15 days ago
WorldClaw: Agentic 3D Open-World Generation at Scale
Paper • 2608.05248 • Published • 86
Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs
Paper • 2609.11499 • Published • 33
Latent Action as Intention Enables Efficient Future Imagination for World Action Models
Paper • 2608.24882 • Published • 2
JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling
Paper • 2608.09381 • Published • 1
Foresight Without Seeing: Latent Futures for World Action Models
Paper • 2608.11605 • Published • 2
StageWAM: Joint-Embedding Stage Prediction for World-Action Models in Robot Manipulation
Paper • 2608.10780 • Published • 1
WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory
Paper • 2607.18840 • Published • 1
SenseNova-U1.5: Towards Native Unified Visual Intelligence
Paper • 2609.11929 • Published • 274