MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild Paper • 2603.17187 • Published 2 days ago • 88
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published 2 days ago • 284
WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation Paper • 2603.16871 • Published 2 days ago • 51
Grounding World Simulation Models in a Real-World Metropolis Paper • 2603.15583 • Published 3 days ago • 127
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion Paper • 2603.06577 • Published 13 days ago • 48
Heterogeneous Agent Collaborative Reinforcement Learning Paper • 2603.02604 • Published 17 days ago • 185
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation Paper • 2602.24286 • Published 20 days ago • 95
OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens Paper • 2603.02138 • Published 17 days ago • 147
EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents Paper • 2602.23205 • Published 21 days ago • 11
DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference Paper • 2602.21548 • Published 23 days ago • 46
SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models Paper • 2602.07616 • Published Feb 7 • 2
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Paper • 2602.08222 • Published Feb 9 • 283
PaperBanana: Automating Academic Illustration for AI Scientists Paper • 2601.23265 • Published Jan 30 • 219
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration Paper • 2602.05400 • Published Feb 5 • 349