LaLa-World: Scaling Latent World Models with Natural Language Actions Paper • 2610.27851 • Published 17 days ago • 41
Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V Paper • 2610.28416 • Published 18 days ago • 28
Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation Paper • 2610.30926 • Published 16 days ago • 29
A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning Paper • 2606.03335 • Published Oct 6 • 11
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training Paper • 2610.12468 • Published about 1 month ago • 40
U-Space: Uncovering When and Why Uncertainty Arises in Language Models Paper • 2610.09087 • Published Oct 6 • 44
REMORY: Learning Residual Memory for Context Compaction Paper • 2610.11287 • Published about 1 month ago • 49
TokenRouter: Efficient Serving System for Token-Level LLM Routing Paper • 2610.12242 • Published about 1 month ago • 119
WorldGuide: Goal-Directed Video World Model for Procedural Task Execution Paper • 2610.12459 • Published about 1 month ago • 13
RoboQuest: Generalist Physical Agents that Search, Inspect and Test Paper • 2610.10388 • Published Oct 7 • 4
Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks Paper • 2610.03858 • Published Oct 2 • 12
OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs Paper • 2610.12461 • Published about 1 month ago • 47
SuperNav: An Agentic Navigation System for Any Task in Any Scene Paper • 2610.12126 • Published about 1 month ago • 78
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published Sep 29 • 88
EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness? Paper • 2609.04280 • Published Sep 3 • 30
AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing Paper • 2609.08936 • Published Sep 8 • 137