OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models Paper • 2604.10866 • Published 5 days ago • 58
SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs Paper • 2512.00722 • Published Nov 30, 2025 • 16
SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs Paper • 2512.00722 • Published Nov 30, 2025 • 16 • 2
Running Agents 25 Calculate Model Flops 🔥 25 Calculate FLOPs and parameters for transformer models
FlashDecoding++: Faster Large Language Model Inference on GPUs Paper • 2311.01282 • Published Nov 2, 2023 • 38