PERK: Long-Context Reasoning as Parameter-Efficient Test-Time Learning Paper • 2507.06415 • Published Jul 8, 2025 • 9
LEGO-Anything: Coding Agents for 3D Scene Reconstruction Paper • 2609.36380 • Published 5 days ago • 122
TradingAgents: Multi-Agents LLM Financial Trading Framework Paper • 2412.20138 • Published Dec 28, 2024 • 148
Efficient Memory Management for Large Language Model Serving with PagedAttention Paper • 2309.06180 • Published Sep 12, 2023 • 75
Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning Paper • 2608.27549 • Published Aug 27 • 49
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City Paper • 2608.27456 • Published Aug 27 • 88
4DAnyone: Create Anyone in 4D from a Casual Monocular Video Paper • 2608.20335 • Published Aug 20 • 86
Articulated Object Reconstruction from Rest-State Observation Paper • 2607.27749 • Published Jul 30 • 52
Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction Paper • 2608.12209 • Published Aug 12 • 5
MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling Paper • 2608.14783 • Published Aug 14 • 20
GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation Paper • 2608.17988 • Published Aug 18 • 5
World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible Paper • 2606.13652 • Published Jun 11 • 17
Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time Paper • 2606.15631 • Published Jun 14 • 17
Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models Paper • 2606.16281 • Published Jun 15 • 33