Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning Paper • 2606.24428 • Published 4 days ago • 49
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision Paper • 2606.17162 • Published 12 days ago • 140
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams Paper • 2606.21337 • Published 8 days ago • 71
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published 11 days ago • 206
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining Paper • 2606.20521 • Published 9 days ago • 13
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance Paper • 2606.19195 • Published 10 days ago • 136
Learning from the Self-future: On-policy Self-distillation for dLLMs Paper • 2606.18195 • Published 11 days ago • 75
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters Paper • 2606.02437 • Published 26 days ago • 234
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published about 1 month ago • 249
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding Paper • 2605.29707 • Published about 1 month ago • 149
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval Paper • 2605.29271 • Published about 1 month ago • 9
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published May 22 • 81