CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents Paper • 2608.30147 • Published 7 days ago • 8
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published 21 days ago • 340
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill Paper • 2608.11924 • Published 26 days ago • 291
Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval Paper • 2608.06614 • Published Aug 6 • 7
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published 28 days ago • 342
DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation Paper • 2607.26811 • Published Jul 29 • 93
alphaedge-ai/siglip2-giant-opt-patch16-384-fin-32768 Zero-Shot Image Classification • 2B • Updated Jul 23 • 8 • 1
MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models Paper • 2607.07673 • Published Jul 8 • 14
LatentUMM: Dual Latent Alignment for Unified Multimodal Models Paper • 2605.17766 • Published May 18 • 9