view article Article Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains JetBrains • 25 days ago • 32
view article Article ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM ibm-research • about 1 month ago • 17
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding Paper • 2604.26779 • Published Apr 29 • 14
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression Paper • 2604.04921 • Published Apr 6 • 116
Synthetic Sandbox for Training Machine Learning Engineering Agents Paper • 2604.04872 • Published Apr 6 • 14
Does Your Reasoning Model Implicitly Know When to Stop Thinking? Paper • 2602.08354 • Published Feb 9 • 266
view article Article OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environments +3 christian-washington, ajasuja, santosh-iima, lewtun, burtenshaw • Feb 12 • 35
view article Article Optimizing GLM4-MoE for Production: 65% Faster TTFT with SGLang novita • Jan 22 • 10
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning Paper • 2601.09708 • Published Jan 14 • 56
Mistral Large 3 Collection A state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. • 4 items • Updated Dec 2, 2025 • 100
view article Article Continuous batching from first principles +1 ror, ArthurZ, mcpotato • Nov 25, 2025 • 411