Best Refining Reason Podcasts (2024)

1
The Power at Work Within Me 13:27

2h ago13:27

13:27

Growing up in the 80s and 90s, we didn’t really talk about the Holy Spirit much. It was all about Jesus. Not that it was a bad thing, but the Holy Spirit is important too. Join Janine for a conversation about the true power at work within us and the affects of lingering with Him. FROM TODAY'S EPISODE Scriptures 2 Corinthians 12:9 Ephesians 3:20-21 …

1
Improving Agent Design, JPEG-LM's Visual Breakthrough, TurboEdit's Real-Time Image Edits, Video Segmentation Advances, LLMs Learning Like Humans, RL Benchmarks 16:00

4h ago16:00

16:00

xGen-MM (BLIP-3): A Family of Open Large Multimodal ModelsJPEG-LM: LLMs as Image Generators with Canonical Codec RepresentationsAutomated Design of Agentic SystemsTurboEdit: Instant text-based image editingSurgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame PruningFine-tuning Large Language Models with Human-inspired Lea…

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

2h ago39:05

39:05

This week’s paper presents a comprehensive study of the performance of various LLMs acting as judges. The researchers leverage TriviaQA as a benchmark for assessing objective knowledge reasoning of LLMs and evaluate them alongside human annotations which they find to have a high inter-annotator agreement. The study includes nine judge models and ni…

1
Science & Clinical LLMs Leaps, Enhancing Small Model Reasoning, New Frontiers in Controlled Media Generation 14:24

5h ago14:24

14:24

The AI Scientist: Towards Fully Automated Open-Ended Scientific DiscoveryMed42-v2: A Suite of Clinical LLMsMutual Reasoning Makes Smaller LLMs Stronger Problem-SolversControlNeXt: Powerful and Efficient Control for Image and Video GenerationCogVideoX: Text-to-Video Diffusion Models with An Expert TransformerFruitNeRF: A Unified Neural Radiance Fiel…

1
Can Lingering Affect Our Anxiety? 21:10

7h ago21:10

21:10

Michelle writes… I struggle with anxiety…a lot. I believe in Jesus and I read his word but I still struggle. I want peace and I’m trying to linger but Can Jesus really help? I love this question because it gets to the heart of this podcast. Sure, we may know who Jesus is…and we may believe in Him and that He died for me and rose on the third day. B…

1
Multimodal Benchmarks, Visual Task Transfer, and 3D Object Generation 14:15

16d ago14:15

14:15

MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language ModelsLLaVA-OneVision: Easy Visual Task TransferAn Object is Worth 64x64 Pixels: Generating 3D Object via Image DiffusionMedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for MedicineIPAdapter-Instruct: Resolving Ambiguity in Image-based Co…

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

7d ago44:40

44:40

Meta just released Llama 3.1 405B–according to them, it’s “the first openly available model that rivals the top AI models when it comes to state-of-the-art capabilities in general knowledge, steerability, math, tool use, and multilingual translation.” Will the latest Llama herd ignite new applications and modeling paradigms like synthetic data gene…

1
Image and Video Segmentation with SAM 2, Gemma 2 for Efficient Language Models, Boosting Small Models with Contrastive Fine-Tuning, and MM-Vet v2 Challenges Large Multimodal Models 13:40

12d ago13:40

13:40

SAM 2: Segment Anything in Images and VideosGemma 2: Improving Open Language Models at a Practical SizeCoarse Correspondence Elicit 3D Spacetime Understanding in Multimodal Language ModelImproving Text Embeddings for Smaller Language Models Using Contrastive Fine-tuningOmniParser for Pure Vision Based GUI AgentSF3D: Stable Fast 3D Mesh Reconstructi…

1
Refined to Reflect 17:33

1M ago17:33

17:33

Silver is refined in an incredibly hot crucible. Isaiah 48:10 says we. are refined in our suffering. As figure skater growing up, I desperately wanted to give up many times. But my coach wouldn't let me. She knew the good...the reward of not giving up. When we persevere through our trials, the good waiting for us on the other side is perfectly refl…

1
Text-Guided Image Inpainting, AMEX for Mobile GUI Agents, AgentScope's Multi-Agent Simulation 14:29

28d ago14:29

14:29

Diffree: Text-Guided Shape Free Object Inpainting with Diffusion ModelLAMBDA: A Large Model Based Data AgentAMEX: Android Multi-annotation Expo Dataset for Mobile GUI AgentsBetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth EstimationVery Large-Scale Multi-Agent Simulation in AgentScopeData Mixture Inference: What do BPE Tok…

1
OpenDevin & AI Software Development, Enhancing Visual Language Models, , DDK: Refining Large Language Model Efficiency through Domain Knowledge 13:45

28d ago13:45

13:45

OpenDevin: An Open Platform for AI Software Developers as Generalist AgentsVILA^2: VILA Augmented VILAHumanVid: Demystifying Training Data for Camera-controllable Human Image AnimationPERSONA: A Reproducible Testbed for Pluralistic AlignmentSV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View ConsistencyScalify: scale propagation for…

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

21d ago33:57

33:57

Chaining language model (LM) calls as composable modules is fueling a new way of programming, but ensuring LMs adhere to important constraints requires heuristic “prompt engineering.” The paper this week introduces LM Assertions, a programming construct for expressing computational constraints that LMs should satisfy. The researchers integrated the…

1
Vocabulary Expansion for Large Models, Big Data Enhancing LMs, 4D Reconstruction Progress, AI Cityscape Generation, DPO Policy Analysis, Expanding Code Models, Multimodal LM Trust Evaluation 14:55

22d ago14:55

14:55

Scaling Laws with Vocabulary: Larger Models Deserve Larger VocabulariesScaling Retrieval-Based Language Models with a Trillion-Token DatastoreShape of Motion: 4D Reconstruction from a Single VideoStreetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video DiffusionUnderstanding Reference Policies in Direct Preference Opti…

1
Qwen2 Language Model, Mitigating Privacy Risks in LLMs, Exploring Non-Determinism, Increased Efficiency with Q-Sparse, GRUtopia for Embodied AI 10:38

1M ago10:38

10:38

Qwen2 Technical ReportLearning to Refuse: Towards Mitigating Privacy Risks in LLMsThe Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-DeterminismQ-Sparse: All Large Language Models can be Fully Sparsely-ActivatedGRUtopia: Dream General Robots in a City at Scale

1
Skywork-Math's Reasoning, Video Diffusion Model Innovations, Multimodal Learning, Q-GaLore's Memory Efficiency, MAVIS: Visual Math Instruction 12:11

2M ago12:11

12:11

Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes OnVideo Diffusion Alignment via Reward GradientsMultimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language ModelQ-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank GradientsMAVIS: Math…

1
Beyond Encoders in Vision-Language Models, Revolutionizing Human-LLM Interaction, and Advancing Knowledge Graphs 12:05

1M ago12:05

12:05

Unveiling Encoder-Free Vision-Language ModelsFunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMsAriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM AgentsRULE: Reliable Multimodal RAG for Factuality in Medical Vision Language ModelsChartGemma: Visual Instruction-…

1
Diffusion Forcing to Expert Tuning, Structured Planning, Vision-Language Models, and Tabular ML Benchmarks 11:34

1M ago11:34

11:34

Diffusion Forcing: Next-token Prediction Meets Full-Sequence DiffusionLet the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language ModelsPlanetarium: A Rigorous Benchmark for Translating Text to Structured Planning LanguagesInternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Co…

1
Advancing AI's Mathematical Reasoning: WE-MATH, ROS-LLM Framework, Autoregressive Image Generation 10:36

2M ago10:36

10:36

We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoningMMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient EvaluationLiteSearch: Efficacious Tree Search for LLMWavelets Are All You Need for Autoregressive Image…

1
Persona-Driven Data Synthesis, Enhancing Medical MLLMs, Robot Learning, Knowledge Distillation in LLMs, Text to 3D Gaussian Revolution 11:24

2M ago11:24

11:24

Scaling Synthetic Data Creation with 1,000,000,000 PersonasHuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at ScaleLLaRA: Supercharging Robot Learning Data for Vision-Language PolicyDirect Preference Knowledge Distillation for Large Language ModelsGaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enh…

1
OMG-LLaVA: Unifying Vision and Language Understanding, Step-DPO for LLMs Mathematical Reasoning, MUMU's Multimodal Image Generation 12:15

2M ago12:15

12:15

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and UnderstandingStep-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMsMUMU: Bootstrapping Multimodal Image Generation from Text-to-Image DataSimulating Classroom Education with LLM-Empowered AgentsSeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval …

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

2M ago44:01

44:01

Where adapting LLMs to specialized domains is essential (e.g., recent news, enterprise private documents), we discuss a paper that asks how we adapt pre-trained LLMs for RAG in specialized domains. SallyAnn DeLucia is joined by Sai Kolasani, researcher at UC Berkeley’s RISE Lab (and Arize AI Intern), to talk about his work on RAFT: Adapting Languag…

1
FineWeb Datasets, YouDream's 3D Animals, PDE-Solving Breakthrough, Noise-Conditioned Perception Alignment, Language Models' Continual Learning 11:02

2M ago11:02

11:02

The FineWeb Datasets: Decanting the Web for the Finest Text Data at ScaleYouDream: Generating Anatomically Controllable Consistent Text-to-3D AnimalsDiffusionPDE: Generative PDE-Solving Under Partial ObservationAligning Diffusion Models with Noise-Conditioned PerceptionUnlocking Continual Learning Abilities in Language Models…

1
BigCodeBench Challenges, Cambrian-1 Leap, D-MERIT's Evaluation, Long Context Breakthrough in Vision 11:06

2M ago11:06

11:06

DreamBench++: A Human-Aligned Benchmark for Personalized Image GenerationBigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex InstructionsCambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMsEvaluating D-MERIT of Partial-annotation on Information RetrievalLong Context Transfer from Language to Vision…

1
LongRAG Breakthrough, LLMs as Judges, Transformer Memory Insights, Video Library AI, Democratizing Art Styles 10:14

2M ago10:14

10:14

LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMsJudging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-JudgesComplexity of Symbolic Representation in Working Memory of Transformer Correlates with the Complexity of a TaskTowards Retrieval Augmented Generation over Large Video LibrariesStylebreeder: Exploring …

1
Scaling In-Context Reinforcement Learning, ChartMimic's AI Benchmark, Multimodal Document Comprehension, Long Context Reasoning Challenges 10:36

2M ago10:36

10:36

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement LearningMake It Count: Text-to-Image Generation with an Accurate Number of ObjectsChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code GenerationNeedle In A Multimodal HaystackBABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Hay…

1
Revolutionizing Vision and Language Models: Depth Prediction Breakthroughs, Pixel-Level Transformers, and Robotic Skill Learning 13:20

2M ago13:20

13:20

Depth Anything V2An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual PixelsTransformers meet Neural Algorithmic ReasonersSamba: Simple Hybrid State Space Models for Efficient Unlimited Context Language ModelingOpenVLA: An Open-Source Vision-Language-Action ModelAlleviating Distortion in Image Generation via Multi-Resolut…

1
The FASTEST and EASIEST way to confirm that your financial advisor is NOT running a scam 3:50

3M ago3:50

3:50

Sean recounts a thread in one of his Facebook groups where a member was dealing with a case of fraud, and didn't know where some of his money was. Sean recommends asking two questions: Who holds my money? and Who prints my statements?By Sean Kernan

1
If your financial advisor only recommends annuities, they aren't a financial planner or advisor 9:45

3M ago9:45

9:45

Sean explains why someone who specializes in pushing annuities could be dangerous for your financial well-being — and the three red flags you need to be aware of.By Sean Kernan

1
Why you would want a CFP financial advisor — and 3 reasons it may not matter as much as you think 8:39

3M ago8:39

8:39

Sean talks about why you may or may not want to work with a Certified Financial Planner as your financial advisor. A CFP license holder might be the best advisor for you. But does it really make a difference?By Sean Kernan

1
How to check a financial advisor's public disciplinary history 16:39

3M ago16:39

16:39

Sean wants you to know how to check up on your potential financial advisor — because you need to know as much as possible about the individual — using a tool called BrokerCheck.By Sean Kernan

1
When you should definitely NOT invest in an annuity! 4:55

3M ago4:55

4:55

If you want to invest in an annuity, you need to have a solid reason to use this long-term financial vehicle. And you should definitely have a financial advisor helping you determine if the annuity is your best option, or if another type of investment might better suit your needs.By Sean Kernan

1
What if I am wrong? 25:48

3M ago25:48

25:48

Sean and Ben often ask themselves if they're actually helping their clients, or if they may have made a mistake. Ben had a client who was certain he could handle his estate planning needs on his own, without Ben. Spoiler alert: He didn't.By Sean Kernan

1
Pros & Cons of working with a newer financial advisor 7:59

3M ago7:59

7:59

Sean gives you the ups and downs of hiring a less-experienced financial advisor.By Sean Kernan

1
What does "I am a fiduciary" even mean? 8:51

3M ago8:51

8:51

Sean defines "fiduciary" with a little help from the Eternal Source of Truth - Wikipedia. Then he talks about financial advisors who are or aren't fiduciaries, and what that means for you.By Sean Kernan

1
When you would NOT want a fee-only financial advisor 10:58

3M ago10:58

10:58

Sean discusses the situations when you want a financial advisor who's paid on commission, and why fee-only shouldn't be a hard, fast limit for you.By Sean Kernan

1
How to Think About Costs 40:08

3M ago40:08

40:08

Sean and Ben chat about a simple question with a complicated answer: How much does it cost to do a Roth conversion? There are many ways to answer "How much will this cost?" and they can become overwhelming .By Sean Kernan

1
NaRCan Revolutionizes Video Editing, Training-Free Video Generation, Recaptioning Web Images with LLaMA-3, Novel Data Synthesis Approach, Smartphone LLM Inference 11:33

2M ago11:33

11:33

NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video EditingMotionClone: Training-Free Motion Cloning for Controllable Video GenerationWhat If We Recaption Billions of Web Images with LLaMA-3?Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with NothingPowerInfer-2: Fast Large Language Model I…

1
Refined Concert at HICC: My Personal Experience. 6:54

2M ago6:54

6:54

Hello everyone, I hope you're doing well! In this podcast, I'm sharing my exciting experience at the HICC Redefining concert. From amazing performances to unforgettable moments, I'm taking you through my journey. Sit back, relax, and enjoy my story!

1
Revolutionizing Image Synthesis with TiTok, Multilingual Code Benchmark, Exploring GenAI Prompting Techniques, 10:53

2M ago10:53

10:53

An Image is Worth 32 Tokens for Reconstruction and GenerationMcEval: Massively Multilingual Code EvaluationZero-shot Image Editing with Reference ImitationThe Prompt Report: A Systematic Survey of Prompting TechniquesTextGrad: Automatic "Differentiation" via Text

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

3M ago44:00

44:00

It’s been an exciting couple weeks for GenAI! Join us as we discuss the latest research from OpenAI and Anthropic. We’re excited to chat about this significant step forward in understanding how LLMs work and the implications it has for deeper understanding of the neural activity of language models. We take a closer look at some recent research from…

1
LlamaGen's Image Revolution, Husky: The Multi-Step Reasoner, Vript's Video Breakthrough, VALL-E 2 Achieves Human Parity 10:46

3M ago10:46

10:46

Autoregressive Model Beats Diffusion: Llama for Scalable Image GenerationHusky: A Unified, Open-Source Language Agent for Multi-Step ReasoningVript: A Video Is Worth Thousands of WordsLighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View SynthesisVALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text …

1
Dirty little secrets of financial advisor compensation models 17:38

3M ago17:38

17:38

Sean shares five secrets some financial advisors don't want you to know about in regards to their fees.By Sean Kernan

1
How to upgrade your financial advisor — at half the cost and twice the value 8:10

3M ago8:10

8:10

Sean discusses why you may be unhappy with your financial advisor and what to do in that situation. He's happy to help you navigate finding a new advisor who's a better fit for you.By Sean Kernan

1
How to get 18 potential fit financial advisors in 24 hours 4:15

3M ago4:15

4:15

Sean brings up a case study of a relatively young couple looking for financial advisors. He can help you find financial advisors who could be a good fit for you. Don't hesitate to reach out!By Sean Kernan

1
Beware of must-have lists for your financial advisor 12:13

3M ago12:13

12:13

Sean addresses common must-have ideas around hiring a financial advisor, and why they can make you miss out on your ideal advisor.By Sean Kernan

1
The 80/20 rule 23:38

3M ago23:38

23:38

Sean and Ben discuss the 80/20 rule, or the Pareto Principle. Italian economist Vilfredo Pareto observed in 1906 that 80% of the land in Italy was owned by 20% of the population. He looked at other nations and saw that the ratio was the same.By Sean Kernan

1
Financial Advisor Fees - a surprisingly simple question to see if you're a good fit for an advisor 7:52

3M ago7:52

7:52

Sean discusses the simple question to ask potential financial advisors, to see if they might be a good fit for you.By Sean Kernan

1
The WRONG questions to ask a potential financial advisor 4:44

3M ago4:44

4:44

Sean talks about questions that you absolutely do not want potential financial advisors to answer without asking a dozen questions back at you.By Sean Kernan

1
The secret of interviewing a potential financial advisor 9:45

3M ago9:45

9:45

Sean discusses the super secret question you should ask any potential financial advisor. In fact, it's so secret, he mentions it 20 seconds into the episode!By Sean Kernan

1
Compared to what? 34:13

3M ago34:13

34:13

Sean and Ben talk about the dangers of asking "Compared to what?" In Dallas in summer, it's hot. "Compared to what?" Compared to Alaska? Jupiter? your normal temperature? A refrigerator? The heart of a volcano?By Sean Kernan

Podcasts Worth a Listen

Refining Reason Podcasts

Podcasts Worth a Listen

Quick Reference Guide