Ministral 3 Collection A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated Dec 2, 2025 • 148
AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents Paper • 2512.23343 • Published 20 days ago • 27
Lost in the Noise: How Reasoning Models Fail with Contextual Distractors Paper • 2601.07226 • Published 6 days ago • 28
Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning Paper • 2601.09088 • Published 5 days ago • 53
Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits Paper • 2512.20578 • Published 26 days ago • 77
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling Paper • 2512.23959 • Published 20 days ago • 103
Controlled Self-Evolution for Algorithmic Code Optimization Paper • 2601.07348 • Published 6 days ago • 106
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning Paper • 2601.06943 • Published 7 days ago • 201
Fast Inference from Transformers via Speculative Decoding Paper • 2211.17192 • Published Nov 30, 2022 • 10
RelayLLM: Efficient Reasoning via Collaborative Decoding Paper • 2601.05167 • Published 10 days ago • 28
view article Article Tokenization in Transformers v5: Simpler, Clearer, and More Modular +4 Dec 18, 2025 • 114
💧 LFM2.5 Collection Collection of Instruct, Base, and Japanese LFM2.5-1.2B models. • 19 items • Updated 6 days ago • 73