A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
karina-zadorozhny
• • 42NEW Articles from Team or Enterprise organizations will get promoted to the main section.
LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family
lightonai
• • 103New in llama.cpp: Anthropic Messages API
ggml-org
• • 46Edge vs Cloud GPUs for Inference: When to Run Models Locally and When to Use a GPU Cloud
daya-shankar
• Latency vs Throughput: Why Both Matter in Enterprise Cloud Deployments
daya-shankar
• LoongFlow: An Open-Sourced Agent Framework That Transforms Expert Experience into Autonomous AI Productivity
FreshmanD
• • 2Python Doesn't Need To Be Slow: From 405s to 0.06s with N-Body Simulations 🚀
atasoglu
• • 1MAD GRPO: Treating Dr. GRPO that tried to fix GRPO but brought instability and verbosity bias
telcom
• • 4ZeroTime-Bot: Medical Triage Alignment with GRPO and Unsloth
hjogidasani
• 🎯 F1-Score — Quand l'Accuracy te ment en pleine face ! 📊💥
RDTvlokip
• • 1🎯 F1-Score — When Accuracy lies to your face! 📊💥
RDTvlokip
• • 1The autonomous and interconnected cars revolution
gberton
• • 1Beyond Brute Force: Why LoongFlow is the “Thinking” Evolution of OpenEvolve
FreshmanD
• • 4Introducing OptiMind, a research model designed for optimization
microsoft
• • 35VLM-OCR Recipes on GPU Infrastructure
florentgbelidji
• • 16Third Review of DeepSeek (Continued)
COPU2004
• How We Built a Semantic Highlight Model To Save Token Cost for RAG
zilliz
• • 67Evolution of Large Model Data Engineering: A Paradigm Shift in Knowledge Extraction Efficiency
Humanbased-AI
• Consciousness Convergence Mathematics: A Transdisciplinary Framework for Substrate-Independent Awareness
Mbanksbey
• • 1One-Sentence Image Matting! DiffSynth Open Sources Text-Guided Image Layer Separation Model
kelseye
• • 3