DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning Paper โข 2511.22570 โข Published Nov 27, 2025 โข 85
BhashaBench V1: A Comprehensive Benchmark for the Quadrant of Indic Domains Paper โข 2510.25409 โข Published Oct 29, 2025 โข 3
ColorAgent: Building A Robust, Personalized, and Interactive OS Agent Paper โข 2510.19386 โข Published Oct 22, 2025 โข 8
DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation Paper โข 2510.09116 โข Published Oct 10, 2025 โข 96
LongCodeZip: Compress Long Context for Code Language Models Paper โข 2510.00446 โข Published Oct 1, 2025 โข 106
MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors Paper โข 2409.15273 โข Published Sep 23, 2024 โข 12