Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs Paper • 2604.05643 • Published 3 days ago • 6
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models Paper • 2512.02556 • Published Dec 2, 2025 • 265
Asking like Socrates: Socrates helps VLMs understand remote sensing images Paper • 2511.22396 • Published Nov 27, 2025 • 5
Running on CPU Upgrade Featured 3.1k The Smol Training Playbook 📚 3.1k The secrets to building world-class LLMs
Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks Paper • 2510.08002 • Published Oct 9, 2025 • 24
Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering Paper • 2508.15213 • Published Aug 21, 2025 • 8