GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens Paper • 2604.15284 • Published 3 days ago • 18
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Paper • 2604.14268 • Published 4 days ago • 80
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe Paper • 2604.13016 • Published 5 days ago • 77
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation Paper • 2604.09132 • Published 9 days ago • 50
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published 23 days ago • 354
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published 17 days ago • 480
RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details Paper • 2604.06870 • Published 11 days ago • 40
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory Paper • 2604.08995 • Published 9 days ago • 46
FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios Paper • 2604.07413 • Published 11 days ago • 93
WildDet3D: Scaling Promptable 3D Detection in the Wild Paper • 2604.08626 • Published 10 days ago • 238
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published 10 days ago • 114
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published 10 days ago • 278
SEVerA: Verified Synthesis of Self-Evolving Agents Paper • 2603.25111 • Published 24 days ago • 31
INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling Paper • 2604.07209 • Published 11 days ago • 35
FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling Paper • 2604.06916 • Published 11 days ago • 34
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents Paper • 2604.06132 • Published 12 days ago • 114
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding Paper • 2604.05015 • Published 13 days ago • 233
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale Paper • 2604.04771 • Published 13 days ago • 120