187 подписчиков
119 видео
DeepSeek-V3 Technical Report
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
OmniParser for Pure Vision Based GUI Agent
The Ultimate Guide to Fine Tuning LLMs from Basics to Breakthroughs
StructRAG
LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
OpenAI o1 System Card
Sparse Crosscoders for Cross Layer Features and Model Diffing
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
Were RNNs All We Needed?
Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for LLMs
Simplifying, Stabilizing and Scaling Continuous Time Consistency Models
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning