Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI Paper • 2609.24815 • Published 11 days ago • 10
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling Paper • 2609.34981 • Published 5 days ago • 126
WorldAttention: An Efficient Attention Architecture for Interactive Video World Models Paper • 2609.34606 • Published 6 days ago • 44
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 8 days ago • 313
Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models Paper • 2609.34972 • Published 6 days ago • 30
Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching Paper • 2608.09444 • Published 9 days ago • 13
LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay Paper • 2609.25053 • Published 27 days ago • 17
RULER: Instance-aware Rubric Rewards for SVG Generation Paper • 2609.25270 • Published 13 days ago • 102
All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts Paper • 2609.24058 • Published 13 days ago • 55
ImIR: Image-Instruction Tuning for All-in-One Image Restoration Paper • 2609.25267 • Published 13 days ago • 14