ModernVBERT: Towards Smaller Visual Document Retrievers
By
and 4 others
•
•
35
ModernVBERT: Towards Smaller Visual Document Retrievers
By
and 4 others
•
•
35Visualizing How VLMs Work
By
and 1 other
•
•
14CU-1 for Autonomous UI Agent Systems: An Open Alternative to Proprietary Solutions
By
•
•
14How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons
By
•
•
16There is no such thing as a tokenizer-free lunch
By
•
•
73Code a simple RAG from scratch
By
•
•
214Gaia2 Leaderboard Update: New Models and New Observations
By
and 3 others
•
•
7Small Language Models (SLM): A Comprehensive Overview
By
•
•
81Cactus: High-Performance AI Inference on Any Smartphone
By
•
•
6Uncensor any LLM with abliteration
By
•
•
688How to Train an Antibody Developability Model
By
and 1 other
•
•
16Model Quality: Hugging Face Is All You Need
By
•
•
21Vocabulary is the most important element of Sparse Retrieval
By
•
•
5KV Caching Explained: Optimizing Transformer Inference Efficiency
By
•
•
141Nemotron-Personas-Japan: Synthesized Data for Sovereign AI
By
and 6 others
•
•
25Preserving Agency: Why AI Safety Needs Community, Not Corporate Control
By
•
•
10The Past and Present of Sparse Retrieval
By
•
•
4Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face
By
•
•
74DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
By
•
•
228Prefill and Decode for Concurrent Requests - Optimizing LLM Performance
By
•
•
46