view article Article NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction nvidia • 2 days ago • 56
ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport Paper • 2609.34899 • Published 4 days ago • 7
SmolDataEnvs Collection 5.5K+ RL tasks for hill-climbing small models in code and data science. Deterministic grading, no LLM judge. • 10 items • Updated about 5 hours ago • 8
view article Article Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL +2 aminediroHF, qgallouedec, kashif, sergiopaniego • 22 days ago • 53
⛵ Vela 1.0 Collection The model family for intelligent routing. • 15 items • Updated about 1 hour ago • 25
🎲 Decision 1.0 Collection Towards Open Decision Foundation Models • 7 items • Updated about 1 hour ago • 18
Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training Paper • 2608.29313 • Published Aug 29 • 3
EvoOntology: A Self-Evolving Ontology Layer for Data Agents Paper • 2609.15779 • Published 18 days ago • 159
Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards Paper • 2609.03181 • Published 30 days ago • 11
The Router Within: Eliciting Native Skill Routing from a Frozen LLM Paper • 2609.15982 • Published 18 days ago • 8
view article Article One sandbox per rollout, or how labs run RL for agents in 2026 sergiopaniego • 20 days ago • 10