Best Guise Of Science Podcasts (2024)

1
UtGoS Ep. 55 : Thought Experiments / Please, Hammer. Don't Hurt 'Em. 1:41:52

4h ago1:41:52

1:41:52

Thought Experiments are a helpful tool for scientists, philosophers, and two dopes who very much enjoy getting sidetracked and derailing conversations. This one's long and all over the place!By Under The Guise Of Science

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

1h 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
Wake the Bear Radio - Show 149 - The Making of a Coup-mala 1:19:25

1d ago1:19:25

1:19:25

In a week's time we see a democrat coup placing Kamala as the top nomination without a single vote, Venezuela had another stolen election and the opener for the Paris Olympics turns satanic.By WTBR

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

1d 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
The Heart as Cosmic Creator: Hindu Scriptures Translated through the Lens of Ibn al-ʿArabī 23:16

3d ago23:16

23:16

Shankar Nair specializes in Muslim-Hindu interactions in South Asia, Sufism and Islamic philosophy, Qur'anic exegesis, Hindu philosophy and theology, and South Asian religious literatures, primarily in the context of the early modern period, but also including the medieval periodBy Shankar Nair

1
Wake the Bear Radio - Show 148 - Buckle up for the Cover up 1:35:50

4h ago1:35:50

1:35:50

We talk about a week of coverups as Secret Service protection of President Trump is questioned, the missing Biden and democrat coup, and the very interesting outage caused by CrowdStrike.By WTBR

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

6h 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
Philosophical Sufism in the Sokoto Caliphate: Two Poems of Shaykh Dan Tafa 23:20

6d ago23:20

23:20

Oludamini Ogunnaike is an assistant professor of Religious Studies at the University of Virginia. He teaches courses on African and African Diasporic Religions as well as Islam, Islamic Philosophy, Spirituality, and Art. He holds a PhD in African Studies and the Study of Religion from Harvard University, and spent a year as a postdoctoral fellow at…

1
Baked Potatoes Ep. 6 - Bray Wyatt 1:14:48

5h ago1:14:48

1:14:48

"THIS ONE'S SOMBER, SO IT'S ALRIGHT TO CRY!" THIS WEEK, the 'Taters talk about Bray Wyatt and his career that was cut too short. There's jokes though, it's not a total bummer!By Under The Guise Of Science

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

4h 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
Wake the Bear Radio - Show 147 - Angels and Angles 1:24:12

6h ago1:24:12

1:24:12

The shot heard around the world as President Trump is spared from assassination.By WTBR

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

14d 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
Challenger, and Space Barbie 48:41

20d ago48:41

48:41

Was the Space Shuttle fundamentally flawed? Richard Hollingham talks to Adam Higginbotham, author of a new book on the Space Shuttle to discuss the design, the dream, and the wishful thinking that led to the Challenger and Columbia disasters. Sue Nelson visits London's Design Museum to visit a new Barbie exhibition and talk "Space Barbie". Also, di…

1
Challenger, and Space Barbie 48:41

12d ago48:41

48:41

Was the Space Shuttle fundamentally flawed? Richard Hollingham talks to Adam Higginbotham, author of a new book on the Space Shuttle to discuss the design, the dream, and the wishful thinking that led to the Challenger and Columbia disasters. Sue Nelson visits London's Design Museum to visit a new Barbie exhibition and talk "Space Barbie". Also, di…

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

3d 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
Wake the Bear Radio - Show 146 - Panic at the DisCo 1:20:45

4d ago1:20:45

1:20:45

The swamp rat DC politicians are scrambling in confusion as they try to reassemble themselves for a "better" candidate to run against Trump, OR this is all kabuki theater.By WTBR

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

10d 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

24d 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

10d 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
Wake the Bear Radio - Show 145 - Who's in Charge Here? 1:08:13

12d ago1:08:13

1:08:13

We discuss the reactions to the Presidential debate and the major cases decided in SCOTUS.By WTBR

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

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

29d 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

16d 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

17d 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
Wake the Bear Radio - Show 144 - The Coming Clashes between Podiums and Projectiles 1:26:29

23d ago1:26:29

1:26:29

As we prepare to watch the upcoming Presidential debates later in the week, we expect there to be clashes of ideals, agendas, world views in the room, much like the buildup of opposite agendas with major nations on the world stage.By WTBR

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

23d 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

24d 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
Wake the Bear Radio - Show 143 - Fathering a Nation in 2024 1:23:10

1M ago1:23:10

1:23:10

We discuss the latest news items of the week through the lens of fatherhood as we celebrate Father's Day in the midst of political upheavals.By WTBR

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

28d 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
Revolutionizing Image Synthesis with TiTok, Multilingual Code Benchmark, Exploring GenAI Prompting Techniques, 10:53

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

1M 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
Mixture-of-Agents, Benchmarking LLMs, and GenAI Arena Evaluation 11:06

1M ago11:06

11:06

Mixture-of-Agents Enhances Large Language Model CapabilitiesWildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the WildCRAG -- Comprehensive RAG BenchmarkGenAI Arena: An Open Evaluation Platform for Generative ModelsLarge Language Model Confidence Estimation via Black-Box Access

1
Wake the Bear Radio - Show 142 - The Throne of Lies Deep and Wide 1:20:00

1M ago1:20:00

1:20:00

We see lies being exposed around the world and are realizing that this has been going on for a long time, and that time is running out!By WTBR

1
Enhancing AI Video and Image Generation, BitsFusion Quantization, Step-aware Optimization, Thought-Augmented Reasoning, and Single Forward Video Generation 11:39

1M ago11:39

11:39

ShareGPT4Video: Improving Video Understanding and Generation with Better CaptionsBitsFusion: 1.99 bits Weight Quantization of Diffusion ModelStep-aware Preference Optimization: Aligning Preference with Denoising Performance at Each StepBuffer of Thoughts: Thought-Augmented Reasoning with Large Language ModelsSF-V: Single Forward Video Generation Mo…

1
AI Papers Podcast Special Edition: Apple Intelligence & Ferret-UI 1:52

1M ago1:52

1:52

Apple announced new Siri features and Apple Intelligence today, Interestingly, Apple already released a paper, titled "Ferret-UI," on how it all works - a multimodal vision-language model capable of understanding widgets, icons, and text on an iOS mobile screen, and reasoning about their spatial relationships and functional meanings. https://arxiv.…

1
Block Transformers: Faster Inference, Mobile Device AI Agents, 3D-Image Generation, Low Latency TTS 10:41

1M ago10:41

10:41

Block Transformer: Global-to-Local Language Modeling for Fast InferenceParrot: Multilingual Visual Instruction TuningMobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent CollaborationOuroboros3D: Image-to-3D Generation via 3D-aware Recursive DiffusionLiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autore…

1
Seed-TTS, Decoding LLMs, Innovations in Text-to-Video, Self-Improving AI Preferences, and Refining Diffusion Models 11:10

2M ago11:10

11:10

Seed-TTS: A Family of High-Quality Versatile Speech Generation ModelsTo Believe or Not to Believe Your LLMI4VGen: Image as Stepping Stone for Text-to-Video GenerationSelf-Improving Robust Preference OptimizationGuiding a Diffusion Model with a Bad Version of Itself

1
Ep. 54 - Total Eclipse LIVE! 1:05:58

2M ago1:05:58

1:05:58

THERE WAS A SOLAR ECLIPSE!!!!The Guise were in the same place, The Sun and Moon appeared to be in the same place, there's people in the room with the Guise including friend of the show and Patreon subscriber Sherruldt! There's a lot of yelling, there was a lot of drinking, there's a bunch of talking off mic. Recorded live at the Burlington Vermont …

1
MMLU-Pro: Next-Level Language Understanding, Tailored LLMs, High FPS Video Generation Innovation 11:30

1M ago11:30

11:30

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding BenchmarkLearning Temporally Consistent Video Depth from Video Diffusion PriorsShow, Don't Tell: Aligning Language Models with Demonstrated FeedbackArtificial Generational Intelligence: Cultural Accumulation in Reinforcement LearningZeroSmooth: Training-free Diffuser Adaptati…

1
Ibn al-ʿArabī in Japan: The Life and Legacy of Toshihiko Izutsu (1914-1993) 20:56

1M ago20:56

20:56

Atif Khalil is on the faculty of Religious Studies at the University of Lethbridge. Khalil's primary area of research lies in Sufism, with secondary interests in Islamic philosophy and theology, comparative mysticism, interfaith relations, Jewish-Muslim relations, medieval philosophy, non-duality, and more recently, mysticism and the Near Death Exp…

1
Transformers and State-Space Models Unite, Multi-modal LLM Benchmark, Perplexity in Data Pruning, Advancing 4D Content Generation 10:23

2M ago10:23

10:23

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space DualityVideo-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video AnalysisPerplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference ModelsKaleido Diffusion: Improving Conditional Diffusion Models with Au…

1
DITTO-2 Speeds Up Music AI, GECO's Quick 3D Generation, PLA4D's 4D Advances, DevEval's Real-World Code Benchmark, Parrot's LLM Application Efficiency 10:47

2M ago10:47

10:47

AI Papers Podcast for 06/04/2024 DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music GenerationGECO: Generative Image-to-3D within a SECOndPLA4D: Pixel-Level Alignments for Text-to-4D Gaussian SplattingDevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code RepositoriesParrot: Efficient Serving of LLM-b…

1
Wake the Bear Radio - Show 141 - Will the First Arrest Shock the World? 1:24:44

2M ago1:24:44

1:24:44

Details of the sham hush money case against President Trump and what it means in the big picture.By WTBR

Podcasts Worth a Listen

Guise Of Science Podcasts

Podcasts Worth a Listen

Quick Reference Guide