Media Summary: Sean Welleck (Carnegie Mellon University) ... This guest lecture by Sean Welleck for CMU CS 11-711, Advanced NLP (Fall 2024) covers a survey of inference-time Ethan Meyers, Hampshire College / MIT BMM Summer Course 2018.

Beyond Decoding Meta Generation Algorithms - Detailed Analysis & Overview

Sean Welleck (Carnegie Mellon University) ... This guest lecture by Sean Welleck for CMU CS 11-711, Advanced NLP (Fall 2024) covers a survey of inference-time Ethan Meyers, Hampshire College / MIT BMM Summer Course 2018. Today Daniel Melcer joined us to present Constrained April 29, 2025 High-level overview of reasoning in large language models, focusing on motivations, core ideas, and current ... Ever wondered how Large Language Models (LLMs) like ChatGPT generate text? It's one word at a time. Discover the secret ...

How do large language models like ChatGPT actually decide which word comes next? In this video, we break down the core ... We are excited to invite you to our exclusive livestream on NVIDIA NIM™ inference microservices for learning how to leverage ... Ready to become a certified watsonx AI Assistant Engineer? Register now and use code IBMTechYT20 for 20% off of your exam ... In an era where we rely on massive, fallible AI models to check our code, how can we be sure our tools aren't hallucinating?

Photo Gallery

Beyond Decoding: Meta-Generation Algorithms for Large Language Models (Remote Talk)
CMU Advanced NLP Fall 2024 (22): From Decoding to Meta Generation  Inference Time Algorithms for LMs
Explore Meta-Generator Algorithms for LLMs
Tutorial: Using Decoding to Understand Neural Algorithms
Constrained Decoding for LMs via Lef/Right Quotienting of Context-Sensitive Grammars - Daniel Melcer
Stanford CS25: V5 I Large Language Model Reasoning, Denny Zhou of Google Deepmind
GenAI: LLM Decoding Strategies Explained | Greedy, Beam, Top-k, Top-p, Temperature, Contrastive
Greedy? Min-p? Beam Search? How LLMs Actually Pick Words – Decoding Strategies Explained
Beyond the Algorithm with NVIDIA: Generating Reasoning Enhanced Podcasts with Open Source AI Agents
Beyond Speculative Decoding: Jacobi Forcing in LLMs
Faster LLMs: Accelerate Inference with Speculative Decoding
Mathematically Proving Software Sanity: Beyond AI and LLMs
View Detailed Profile
Beyond Decoding: Meta-Generation Algorithms for Large Language Models (Remote Talk)

Beyond Decoding: Meta-Generation Algorithms for Large Language Models (Remote Talk)

Sean Welleck (Carnegie Mellon University) ...

CMU Advanced NLP Fall 2024 (22): From Decoding to Meta Generation  Inference Time Algorithms for LMs

CMU Advanced NLP Fall 2024 (22): From Decoding to Meta Generation Inference Time Algorithms for LMs

This guest lecture by Sean Welleck for CMU CS 11-711, Advanced NLP (Fall 2024) covers a survey of inference-time

Explore Meta-Generator Algorithms for LLMs

Explore Meta-Generator Algorithms for LLMs

... Thanh Tình Tutorial:

Tutorial: Using Decoding to Understand Neural Algorithms

Tutorial: Using Decoding to Understand Neural Algorithms

Ethan Meyers, Hampshire College / MIT BMM Summer Course 2018.

Constrained Decoding for LMs via Lef/Right Quotienting of Context-Sensitive Grammars - Daniel Melcer

Constrained Decoding for LMs via Lef/Right Quotienting of Context-Sensitive Grammars - Daniel Melcer

Today Daniel Melcer joined us to present Constrained

Stanford CS25: V5 I Large Language Model Reasoning, Denny Zhou of Google Deepmind

Stanford CS25: V5 I Large Language Model Reasoning, Denny Zhou of Google Deepmind

April 29, 2025 High-level overview of reasoning in large language models, focusing on motivations, core ideas, and current ...

GenAI: LLM Decoding Strategies Explained | Greedy, Beam, Top-k, Top-p, Temperature, Contrastive

GenAI: LLM Decoding Strategies Explained | Greedy, Beam, Top-k, Top-p, Temperature, Contrastive

Ever wondered how Large Language Models (LLMs) like ChatGPT generate text? It's one word at a time. Discover the secret ...

Greedy? Min-p? Beam Search? How LLMs Actually Pick Words – Decoding Strategies Explained

Greedy? Min-p? Beam Search? How LLMs Actually Pick Words – Decoding Strategies Explained

How do large language models like ChatGPT actually decide which word comes next? In this video, we break down the core ...

Beyond the Algorithm with NVIDIA: Generating Reasoning Enhanced Podcasts with Open Source AI Agents

Beyond the Algorithm with NVIDIA: Generating Reasoning Enhanced Podcasts with Open Source AI Agents

We are excited to invite you to our exclusive livestream on NVIDIA NIM™ inference microservices for learning how to leverage ...

Beyond Speculative Decoding: Jacobi Forcing in LLMs

Beyond Speculative Decoding: Jacobi Forcing in LLMs

Previous Video on Speculative

Faster LLMs: Accelerate Inference with Speculative Decoding

Faster LLMs: Accelerate Inference with Speculative Decoding

Ready to become a certified watsonx AI Assistant Engineer? Register now and use code IBMTechYT20 for 20% off of your exam ...

Mathematically Proving Software Sanity: Beyond AI and LLMs

Mathematically Proving Software Sanity: Beyond AI and LLMs

In an era where we rely on massive, fallible AI models to check our code, how can we be sure our tools aren't hallucinating?