Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step
FINAL-Bench
• • 17
NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step
FINAL-Bench
• • 17Vividh-ASR: Diagnosing and Fixing Studio-Bias in Whisper for Indic Languages
adalat-ai
• • 11EMO: Pretraining mixture of experts for emergent modularity
allenai
• • 37Two Years of Local AI on a Laptop: When Open Models Outpaced Moore's Law
mishig
• • 22KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 333Uncensor any LLM with abliteration
mlabonne
• • 855How to Comply with SOC 2 and ISO 27001 with Hugging Face: A Practical Guide to AI Model Supply Chain Governance
jeffboudier
• • 5Software Forgets: Agent Traces Are the Memory
huggingface
• • 5Code a simple RAG from scratch
ngxson
• • 335Small Language Models (SLM): A Comprehensive Overview
jjokah
• • 153A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
karina-zadorozhny
• • 19NEO-unify: Building Native Multimodal Unified Models End to End
sensenova
• • 162Mastering Tensor Dimensions in Transformers
not-lain
• • 174Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
NormalUhr
• • 121Norm-Preserving Biprojected Abliteration
grimjim
• • 81Forge: Scalable Agent RL Framework and Algorithm
MiniMax-AI
• • 154LLM Architectures Explained: What Powers Today’s Top Models
PrunaAI
• • 11NVIDIA Isaac GR00T N1.7: Open Reasoning VLA Model for Humanoid Robots
nvidia
• • 16Talking to a 4-Year-Old: A Multilingual Benchmark for Children's AI Companions
batuhanaktas
• • 4SSE Retrieval MRL v2: Regularization of Representation Space and Performance Improvement via Hyperparameter Optimization
RikkaBotan
• • 2