WorldSonus: Bringing Sound to Worlds
Paper • 2610.08760 • Published • 33
taesiri PRO
taesiri
AI & ML interests
AGI ... one linear layer at a time
Recent Activity
updated a dataset about 8 hours ago
taesiri/ArXivSignals-DeepSummaries updated a dataset about 10 hours ago
taesiri/ArXivSignals upvoted a paper about 20 hours ago
WorldSonus: Bringing Sound to WorldsOrganizations
upvoted 5
papers about 20 hours ago
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Paper • 2610.08621 • Published • 79
GRACE: Generation-aware latent compression for efficient video generation
Paper • 2610.10524 • Published • 63
Questioning the Questions: Sustaining Self-Evolution in Reasoning Models
Paper • 2610.04299 • Published • 64
nanoMuse: An Open-Source Personal Agent for Every Device You Own
Paper • 2610.08699 • Published • 82
upvoted 4
papers 1 day ago
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability
Paper • 2610.08448 • Published • 165
DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation
Paper • 2610.03543 • Published • 79
EVISKILL: Grounding Skill Evolution in Replayable Evidence
Paper • 2610.05030 • Published • 40
World Models' Last Exam in Physics
Paper • 2610.08791 • Published • 7
upvoted 3
papers 2 days ago
DistScene: Object-to-Scene Distillation for 3D Scene Generation
Paper • 2610.06960 • Published • 6
VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning
Paper • 2610.08761 • Published • 5
Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
Paper • 2610.01892 • Published • 16
upvoted 4
papers 3 days ago
OSWorld-Pro: Process-based Evaluation for Computer Use Agents
Paper • 2609.24890 • Published • 28
Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction
Paper • 2610.04137 • Published • 12
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
Paper • 2610.05608 • Published • 155
HelixWorld: A Real-time Interactive Audio-Visual World Model
Paper • 2609.38123 • Published • 36
upvoted 4
papers 4 days ago
Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation
Paper • 2610.02788 • Published • 17
Octrees as an Explicit 3D Language
Paper • 2610.02388 • Published • 15
Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite
Paper • 2610.02826 • Published • 102
EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling
Paper • 2610.02298 • Published • 57