29 subscribers
Mettez-vous hors ligne avec l'application Player FM !
Podcasts qui valent la peine d'être écoutés
SPONSORISÉ


1 The 3 N’s - Negotiation, Networking & No with Kathryn Valentine | 327 37:43
Deep Papers
Manage series 3448051
Deep Papers is a podcast series featuring deep dives on today’s most important AI papers and research. Hosted by Arize AI founders and engineers, each episode profiles the people and techniques behind cutting-edge breakthroughs in machine learning.
53 episodes
Manage series 3448051
Deep Papers is a podcast series featuring deep dives on today’s most important AI papers and research. Hosted by Arize AI founders and engineers, each episode profiles the people and techniques behind cutting-edge breakthroughs in machine learning.
53 episodes
Tous les épisodes
×
1 Watermarking for LLMs and Image Models 42:56

1 Self-Adapting Language Models: Paper Authors Discuss Implications 31:26

1 The Illusion of Thinking: What the Apple AI Paper Says About LLM Reasoning 30:35

1 Accurate KV Cache Quantization with Outlier Tokens Tracing 25:11

1 Scalable Chain of Thoughts via Elastic Reasoning 28:54

1 Sleep-time Compute: Beyond Inference Scaling at Test-time 30:24

1 LibreEval: The Largest Open Source Benchmark for RAG Hallucination Detection 27:19

1 AI Benchmark Deep Dive: Gemini 2.5 and Humanity's Last Exam 26:11


1 AI Roundup: DeepSeek’s Big Moves, Claude 3.7, and the Latest Breakthroughs 30:23

1 How DeepSeek is Pushing the Boundaries of AI Development 29:54

1 Multiagent Finetuning: A Conversation with Researcher Yilun Du 30:03

1 Training Large Language Models to Reason in Continuous Latent Space 24:58

1 LLMs as Judges: A Comprehensive Survey on LLM-Based Evaluation Methods 28:57

1 Merge, Ensemble, and Cooperate! A Survey on Collaborative LLM Strategies 28:47

1 Agent-as-a-Judge: Evaluate Agents with Agents 24:54

1 Introduction to OpenAI's Realtime API 29:56

1 Swarm: OpenAI's Experimental Approach to Multi-Agent Systems 46:46

1 Google's NotebookLM and the Future of AI-Generated Audio 43:28

1 Exploring OpenAI's o1-preview and o1-mini 42:02

1 Breaking Down Reflection Tuning: Enhancing LLM Performance with Self-Learning 26:54

1 Composable Interventions for Language Models 42:35

1 Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges 39:05

1 Breaking Down Meta's Llama 3 Herd of Models 44:40

1 DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines 33:57

1 RAFT: Adapting Language Model to Domain Specific RAG 44:01

1 LLM Interpretability and Sparse Autoencoders: Research from OpenAI and Anthropic 44:00

1 Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models' Alignment 48:07

1 Breaking Down EvalGen: Who Validates the Validators? 44:47

1 Keys To Understanding ReAct: Synergizing Reasoning and Acting in Language Models 45:07

1 Demystifying Chronos: Learning the Language of Time Series 44:40


1 Reinforcement Learning in the Era of LLMs 44:49

1 Sora: OpenAI’s Text-to-Video Generation Model 45:08


1 HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels 36:22

1 A Deep Dive Into Generative's Newest Models: Gemini vs Mistral (Mixtral-8x7B)–Part I 47:50

1 How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings 44:59

1 The Geometry of Truth: Emergent Linear Structure in LLM Representation of True/False Datasets 41:02

1 Towards Monosemanticity: Decomposing Language Models With Dictionary Learning 44:50

1 RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models 43:49

1 Explaining Grokking Through Circuit Efficiency 36:12

1 Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior 42:14

1 Skeleton of Thought: LLMs Can Do Parallel Decoding 43:39

1 Llama 2: Open Foundation and Fine-Tuned Chat Models 30:26

1 Lost in the Middle: How Language Models Use Long Contexts 42:28

1 Orca: Progressive Learning from Complex Explanation Traces of GPT-4 42:03

1 Toolformer: Training LLMs To Use Tools 34:06


1 ChatGPT and InstructGPT: Aligning Language Models to Human Intention 47:39
Bienvenue sur Lecteur FM!
Lecteur FM recherche sur Internet des podcasts de haute qualité que vous pourrez apprécier dès maintenant. C'est la meilleure application de podcast et fonctionne sur Android, iPhone et le Web. Inscrivez-vous pour synchroniser les abonnements sur tous les appareils.