Melhores podcasts sobre Refining Reason (2024)

1
Composable Interventions for Language Models 42:35

4d ago42:35

42:35

This week, we're excited to be joined by Kyle O'Brien, Applied Scientist at Microsoft, to discuss his most recent paper, Composable Interventions for Language Models. Kyle and his team present a new framework, composable interventions, that allows for the study of multiple interventions applied sequentially to the same language model. The discussio…

1
#208: 3 Reasons You Should Be Buying Online Courses as a Digital Course Creator 20:21

5d ago20:21

20:21

You are an expert in what you do, so why would you buy courses that are related to your course topic? There are 3 reasons you should be buying online courses as a Digital Course Creator. The reality is that we all have our own perspectives, our own perspectives, and our own preferences, but our students might benefit from a wider range of approache…

1
#207: Online Course Bonuses: Do they make a difference? 20:55

12d ago20:55

20:55

Should you include bonuses with your digital or online course? So often we get the advice that bonuses should be even better than your course, they should make people buy your course just to get the bonus, and they should overcome objections. But do they really help? Yes and no. But the real question is should you include them for your online cours…

1
The Power at Work Within Me 13:27

19d 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
#206: Entrepreneurial Costs: What is Normal? 17:38

19d ago17:38

17:38

What is one thing that you didn’t necessarily think about when you decided to become an entrepreneur, when you decided that you’d like to have a digital course? What is one thing that you rarely hear people talking about out in the open? Money and the debt that being an entrepreneur can bring with it. That debt adds up fast, but still it is somethi…

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

25d 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
#205: How to Make the Most of Social Media Groups (Hint: Use Google Search More) 22:10

26d ago22:10

22:10

I've noticed a trend in course creation groups: asking for instructions on how to do a tech task. Sure you pay to be in these groups, they are filled with people who are on the same pathway you are, creating, launching, and serving a digital course, but the big, important questions can sometimes get buried under the smaller, simpler questions that …

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

30d 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

1M 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

1M 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
#204: Does Weekly Content Really Build Demand for your Course? 29:29

1M ago29:29

29:29

The best way to build demand for your online course is with weekly content, or is it? So often we are told that we need to build an audience so that when we launch a course, there will be eager buyers ready with their credit cards. To build an audience the direction often given is to create weekly content. Why then, after creating and sharing weekl…

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

1M 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

1M 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
#203: When is the Right Time to Launch Your Course 22:33

1M ago22:33

22:33

When is the right time to launch your digital course? Is it in the summer, the fall, January 1, or April 28? This is a reasonable question. You put so much effort into the creation of a truly fantastic and meaningful course that the last thing you want is to scuttle your efforts with a poorly chosen course launch date. Why, then, if this is somethi…

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

1M 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

2M 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

2M 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
#202: Online Course Creation Launch Success: Revenue vs. Profit 23:23

2M ago23:23

23:23

What is your business making? Should you be measuring your revenue or your profit when launching the online course you painstakingly created? A lot of times you’ll see people talking about how they had a 5 figure launch or a 6 figure launch, but that doesn’t tell the whole story. It’s frustrating because when someone lists a number, you don’t know …

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

2M 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

2M 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
#201: Digital Course Creation Toughness (Mental Toughness) 21:11

2M ago21:11

21:11

Course creation is a marathon not a sprint. Course creation is a long game. We can apply any number of inspirational quotes or mantras to our digital course creation business, but that isn’t going to keep you warm at night. The reality is that knowing course creation and the subsequent success will take time doesn’t protect us from the challenges t…

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

2M 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

2M 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
#200: Entrepreneurship is About Persistence 19:32

2M ago19:32

19:32

“State of running a business with considerable initiative and risk”. That is the definition of entrepreneurship (dictionary.com). This definition is accurate. You have to show initiative, you have to assume the risk of creating something new, finding an audience who wants to purchase what you’ve created, and then deliver on what you’ve promised. Wh…

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

2M 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
#199: The Easiest Way to Record your Online Course Videos (Maximum Impact) 17:08

2M ago17:08

17:08

You have carefully planned out your digital course. You’ve mapped out the modules, the outcomes, the examples, and the resources. Which leaves you with the actual recording of your online course. All too often this is where the dramatic music that you hear in horror films starts to play because course creators want their course to have an impact. B…

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

2M 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

3M 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
#198: Creating a Digital Course that Engages: Regardless of Attention Span 21:56

3M ago21:56

21:56

Today’s topic is a little controversial and completely practical all in one nice serving. So what makes today’s topic practical? We all want our students and clients to finish the digital course that we have painstakingly created, assembled, and sold. We want them to succeed and eventually become a case study for our business in addition to experie…

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

3M 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

3M 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

3M 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

3M 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
#197: What makes sense? One-to-One Coaching vs. Group Program vs. Digital Course 13:12

3M ago13:12

13:12

What makes the most sense for your business? Building a One-to-One Coaching Offer, a Group Program, or a Digital Course? This is probably something that you’ve been wondering and have seen suggestions telling you why each one of these is THE way to go. But which one makes the most sense for you? After all, our businesses are not a one size fits all…

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

3M 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…

Podcasts que valem a pena ouvir

Podcasts sobre Refining Reason

Podcasts que valem a pena ouvir

Guia rápido de referências