LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR Paper • 2601.14251 • Published 5 days ago • 22
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback Paper • 2601.10156 • Published 11 days ago • 25
RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation Paper • 2601.08430 • Published 13 days ago • 57
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization Paper • 2601.05432 • Published 17 days ago • 161
EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis Paper • 2601.05808 • Published 17 days ago • 36
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss Paper • 2512.23447 • Published 28 days ago • 95
Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space Paper • 2512.24617 • Published 26 days ago • 61
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling Paper • 2512.23959 • Published 27 days ago • 109
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data Paper • 2510.02294 • Published Oct 2, 2025 • 46
C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling Paper • 2512.21332 • Published Dec 24, 2025 • 16