9:39Faster LLMs: Accelerate Inference with Speculative DecodingIBM Technology26.4K viewsView & Download
12:11LLM generates the ENTIRE output at once (world's first diffusion LLM)Matthew Berman196.6K viewsView & Download
31:06Diffusion Language Models - Turning ModernBERT into an instruct-tuned Diffusion LLMDataScienceCastnet4.4K viewsView & Download
9:47Make Diffusion LLMs 3X Faster - SIMPLE Trick By Top 0.1% AI ResearchersVuk Rosić374 viewsView & Download
7:40Speculative Decoding: 3× Faster LLM Inference with Zero Quality LossTales Of Tensors1.6K viewsView & Download
26:36LLM framework – Enhancing prompts output quality, while shortening their development cycleMachine & Deep Learning Israel352 viewsView & Download
6:12Diff2Flow: The AI Trick That Makes Diffusion Models FasterAI_with_Math_17291 viewsView & Download
9:093x Better DIFFUSION LLM - Loopholing Discrete Diffusion - Simple TrickVuk Rosić1.1K viewsView & Download