4:30Thinking Before Constraining: A Unified Decoding Framework for Large Language Models | ResearchPodResearchPod1 viewsView & Download
9:39Faster LLMs: Accelerate Inference with Speculative DecodingIBM Technology26.3K viewsView & Download
59:11Between the Layers– Interpreting Large Language Models - Michelle Frost - NDC AI 2025NDC Conferences889 viewsView & Download
5:24Constrained Generation for Better LLM Prompting ResultsEspoAI — AI + Life500 viewsView & Download
11:53Greedy? Min-p? Beam Search? How LLMs Actually Pick Words – Decoding Strategies ExplainedAI Coffee Break with Letitia7.0K viewsView & Download
7:48Guiding LLM Post-training Data Engineering with Model Internals from Sparse AutoencodersResearchPod16 viewsView & Download
43:40Towards Monosemanticity: Decomposing Language Models Into Understandable ComponentsArize AI3.4K viewsView & Download
5:07Convex Low-resource Accent-Robust Language Detection in Speech Recognition | ResearchPodResearchPod0 viewsView & Download
6:00The Probability Bottleneck in Diffusion LLMs: Why Parallel Decoding Is Not FreeXiaol.x51 viewsView & Download
4:54Locally Coherent Parallel Decoding in Diffusion Language Models - ICML2026Michael Hersche1 viewsView & Download
4:53What is Speculative Decoding? making LLMs fasterData Science in your pocket59 viewsView & Download
7:47Headroom: The Context Optimization Layer for LLM ApplicationsResearch Paper Review65 viewsView & Download