InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation
Paper • 2610.26853 • Published • 34
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 5 days ago
InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation upvoted a paper 5 days ago
SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum upvoted a paper 5 days ago
OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal MemoryOrganizations
upvoted 7
papers 5 days ago
SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum
Paper • 2610.26824 • Published • 89
OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory
Paper • 2610.26860 • Published • 118
Scaling Parameter-Efficient Fine-Tuning for Brain Encoding
Paper • 2610.26802 • Published • 247
Execution Before Memory: Diagnosing Memory Failures in Video World Models
Paper • 2610.23542 • Published • 34
LEV: Thinking Fast and Deep with Looped Decision Models
Paper • 2610.20951 • Published • 106
Learning to Think and Explore in 3D World
Paper • 2610.21783 • Published • 141
liked a
model 5 days ago
upvoted 9
papers 28 days ago
DeltaWAM: Delta World Action Models for Bimanual Manipulation
Paper • 2609.28811 • Published • 22
PUBG Ally: A Conversational Embodied Agent as an AI Teammate
Paper • 2609.29837 • Published • 25
ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds
Paper • 2609.30199 • Published • 31
Coding Agents for Generalized Task and Motion Planning Problems
Paper • 2609.30233 • Published • 28
Agent-Editing World Model: Rethinking World Modeling for LLM Agents
Paper • 2609.28416 • Published • 45
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
Paper • 2609.29845 • Published • 105
Learning to Discover Interesting Mathematics
Paper • 2609.28603 • Published • 16
World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal
Paper • 2609.29964 • Published • 15
Training Object Permanence in World Models
Paper • 2609.28654 • Published • 123
liked a
Space 29 days ago
liked a
Space about 1 month ago
upvoted a paper about 1 month ago