EgoCS-400K: An Egocentric Gameplay Dataset for World Models
Paper • 2606.18180 • Published • 15 •
2
Noah
noahml
AI & ML interests
None yet
Recent Activity
commentedon a paper about 1 hour ago
EgoCS-400K: An Egocentric Gameplay Dataset for World Models commentedon a paper about 2 hours ago
Kairos: A Native World Model Stack for Physical AI commentedon a paper about 2 hours ago
Native Active Perception as Reasoning for Omni-Modal UnderstandingOrganizations
None yet
commented a
paper about 1 hour ago
commented 4
papers about 2 hours ago
Kairos: A Native World Model Stack for Physical AI
Paper • 2606.16533 • Published • 34 •
4
Native Active Perception as Reasoning for Omni-Modal Understanding
Paper • 2606.19341 • Published • 14 •
3
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
Paper • 2606.19162 • Published • 19 •
2
Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States
Paper • 2606.19334 • Published • 6 •
2
commented 10
papers 1 day ago
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
Paper • 2606.20515 • Published • 35 •
3
DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis
Paper • 2604.13416 • Published • 28 •
5
ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
Paper • 2606.19980 • Published • 10 •
1
FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines
Paper • 2606.19605 • Published • 10 •
2
Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe
Paper • 2606.20381 • Published • 6 •
2
ReSyn: A Generalized Recursive Regular Expression Synthesis Framework
Paper • 2603.24624 • Published • 2 •
4
The Data Manifold under the Microscope
Paper • 2606.15760 • Published • 3 •
7
Context-Aware RL for Agentic and Multimodal LLMs
Paper • 2606.17053 • Published • 10 •
3
LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI
Paper • 2606.18021 • Published • 5 •
2
Duration Aware Scheduling for ASR Serving Under Workload Drift
Paper • 2603.11273 • Published • 3 •
3
commented 5
papers 2 days ago
Playful Agentic Robot Learning
Paper • 2606.19419 • Published • 43 •
2
JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising
Paper • 2606.20563 • Published • 19 •
2
No Resource, No Benchmarks, No Problem? Evaluating and Improving LLMs for Code Generation in No-Resource Languages
Paper • 2606.16827 • Published • 3 •
3
Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation
Paper • 2606.16429 • Published • 5 •
5
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
Paper • 2606.20521 • Published • 6 •
2