Best video Compression Podcasts (2024)

1
BlenderAlchemy Revolution, Stylus Adapter Magic, DressCode Digital Fashion 10:04

43m ago10:04

10:04

BlenderAlchemy: Editing 3D Graphics with Vision-Language ModelsStylus: Automatic Adapter Selection for Diffusion ModelsAg2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action RepresentationsDressCode: Autoregressively Sewing and Generating Garments from Text GuidancePLLaVA : Parameter-free LLaVA Extension from Images to V…

1
370: Interview with GloriousEggroll about Proton-GE, Nobara, and more 1:33:37

9h ago1:33:37

1:33:37

https://youtu.be/XjXXIvTMoKQ Download as MP3 Sponsored by LINBIT: Visit destinationlinux.net/linbit to learn how LINBIT’s OSS, based on DRBD® and LINSTOR®, can be used for Kubernetes, CloudStack, OpenNebula, and more. Support the show by becoming a patron at tuxdigital.com/membership or get some swag at tuxdigital.com/store Hosted by: Michael Tunne…

1
Real-Time Motion Control, Next-Gen Visual Captions, 3D Scene Reconstruction Innovations 11:30

5h ago11:30

11:30

MotionLCM: Real-time Controllable Motion Generation via Latent Consistency ModelVisual Fact Checker: Enabling High-Fidelity Detailed Caption GenerationGS-LRM: Large Reconstruction Model for 3D Gaussian SplattingSAGS: Structure-Aware 3D Gaussian SplattingInvisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting…

1
Kolmogorov-Arnold Networks, Iterative Reasoning Optimization, Extending Llama-3 Context Length 11:24

3d ago11:24

11:24

KAN: Kolmogorov-Arnold NetworksInstantFamily: Masked Attention for Zero-shot Multi-ID Image GenerationBetter & Faster Large Language Models via Multi-token PredictionIterative Reasoning Preference OptimizationExtending Llama-3's Context Ten-Fold Overnight

1
Innovative Image Editing, Advanced Autonomous Tracking, and the Evolution of Open-Source AI 12:10

1h ago12:10

12:10

Paint by Inpaint: Learning to Add Image Objects by Removing Them FirstSelf-Play Preference Optimization for Language Model AlignmentAutomatic Creative Selection with Cross-Modal MatchingSTT: Stateful Tracking with Transformers for Autonomous DrivingOctopus v4: Graph of language models

1
369: Fedora 40 vs Ubuntu 24.04 in the Distro BattleDome 1:36:24

9h ago1:36:24

1:36:24

https://youtu.be/jtFbALBRfGg Download as MP3 Sponsored by Kolide: If a device isn't secure, it can't access your apps. It's device trust for Okta. Visit https://destinationlinux.net/kolide to learn more and watch a demo. Sponsored by LINBIT: Visit destinationlinux.net/linbit to learn how LINBIT’s OSS, based on DRBD® and LINSTOR®, can be used for Ku…

1
GPT-4 Rival Models, Revolutionizing Open Source LM Evaluation, StoryDiffusion's Visual Narrative Breakthrough 11:31

3d ago11:31

11:31

Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language ModelsWildChat: 1M ChatGPT Interaction Logs in the WildStoryDiffusion: Consistent Self-Attention for Long-Range Image and Video GenerationLoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical ReportLLM-AD: Large Language Model based Audio Description System…

1
Model Editing Insights with Llama-3, Rethinking Large Language Models in Math, 3D Rendering and Audio Compression 11:52

4d ago11:52

11:52

Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3A Careful Examination of Large Language Model Performance on Grade School ArithmeticSpectrally Pruned Gaussian Fields with Neural CompensationSemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General SoundClover: Regressive Lightweight Speculative …

1
Episode 175: Bred For Dip 1:06:37

4d ago1:06:37

1:06:37

he fellas are joined once again by Miami comedian and purveyor of pour vous Sergio Mendez @Magiccitypacino on IG 🍄🐲SUBSCRIBE🐲🍄 https://www.youtube.com/channel/UC-vL4sWWxT8PwhRD9E1dBXA?sub_confirmation=1 Follow us on Instagram! @fromshrooms 📷 https://www.instagram.com/fromshrooms/ 🔵 https://www.facebook.com/fromshrooms And check out Shawn’s music- 👽…

1
Advancing LLMs with Multi-Token Prediction, Octopus v4 Revolution in Open-Source Language Models, Enhancing Reasoning with Iterative Preference Optimization 11:55

5d ago11:55

11:55

Octopus v4: Graph of language modelsInstantFamily: Masked Attention for Zero-shot Multi-ID Image GenerationBetter & Faster Large Language Models via Multi-token PredictionGS-LRM: Large Reconstruction Model for 3D Gaussian SplattingIterative Reasoning Preference Optimization

1
Evaluating LLMs with Diverse Models, Novel Robotic Skills Framework, Editing 3D Graphics with VLMs 11:02

6d ago11:02

11:02

Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse ModelsLEGENT: Open Platform for Embodied AgentsAg2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action RepresentationsKangaroo: Lossless Self-Speculative Decoding via Double Early ExitingBlenderAlchemy: Editing 3D Graphics with Vision-Languag…

1
368: Interviewing Framework at SCaLE & the Crocs Saga continues . . . 34:20

7d ago34:20

34:20

https://youtu.be/NltUqfuxT-M Download as MP3 Sponsored by LINBIT: Visit destinationlinux.net/linbit to learn how LINBIT’s OSS, based on DRBD® and LINSTOR®, can be used for Kubernetes, CloudStack, OpenNebula, and more. Support the show by becoming a patron at tuxdigital.com/membership or get some swag at tuxdigital.com/store Hosted by: Michael Tunne…

1
PLLaVA Breakthrough in Video-Language Modeling, Exploring Landmarks with HaLo-NeRF, and MaPa's Text-driven 3D Material Painting 9:19

7d ago9:19

9:19

AI Papers Podcast for 04/29/2024 PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense CaptioningAdvPrompter: Fast Adaptive Adversarial Prompting for LLMsHaLo-NeRF: Learning Geometry-Guided Semantics for Exploring Unconstrained Photo CollectionsMaPa: Text-driven Photorealistic Material Painting for 3D Shapes…

1
Bridging the Gap to GPT-4V, Interactive 3D Generation, Accelerating LLM Inference 12:13

10d ago12:13

12:13

AI Papers Podcast for 04/26/2024 How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source SuitesInteractive3D: Create What You Want by Interactive 3D GenerationLayer Skip: Enabling Early Exit Inference and Self-Speculative DecodingTele-FLM Technical ReportSEED-Bench-2-Plus: Benchmarking Multimodal Large Language Mo…

1
Hyper-SD Breakthrough, MAIA's Neural Understanding, SEED-X Multimodal Innovation 11:23

11d ago11:23

11:23

AI Papers Podcast for 04/25/2024 Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image SynthesisA Multimodal Automated Interpretability AgentSEED-X: Multimodal Models with Unified Multi-granularity Comprehension and GenerationMultiBooth: Towards Generating All Your Concepts in an Image from TextLearning H-Infinity Locomotion Control…

1
Episode 174: Chain Dangler Grain Wrangler 1:02:09

11d ago1:02:09

1:02:09

The fellas are joined by another of Carlos' cousins, Danny from Lost City Brewing in North Miami. 🍄🐲SUBSCRIBE🐲🍄 https://www.youtube.com/channel/UC-vL4sWWxT8PwhRD9E1dBXA?sub_confirmation=1 Follow us on Instagram! @fromshrooms 📷 https://www.instagram.com/fromshrooms/ 🔵 https://www.facebook.com/fromshrooms And check out Shawn’s music- 👽 https://soundc…

1
Enhancing AI with Multi-Head MoEs, Pegasus-1's Video Mastery, Optimizing Diffusion Models, 11:08

12d ago11:08

11:08

AI Papers Podcast for 04/24/2024 OpenELM: An Efficient Language Model Family with Open-source Training and Inference FrameworkMulti-Head Mixture-of-ExpertsPegasus-v1 Technical ReportAlign Your Steps: Optimizing Sampling Schedules in Diffusion ModelsSnapKV: LLM Knows What You are Looking for Before Generation…

1
Pack Controller Settings FAQs: “Parallel Compression and Ejectors 22:58

13d ago22:58

22:58

For today's final episode of the season, Controller Talk hosts Chris and Dave close out season 2 with another extended session of everybody's favorite podcast portion - "Stump Chris." Tune in for a fun and informative extended FAQ on controller settings. Dave grills Chris with more commonly asked questions surrounding parallel compression, includin…

1
Model Efficiency, Instruction Prioritization, and Workflow Automation 11:51

20d ago11:51

11:51

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions FlowMind: Automatic Workflow Generation with LLMs Music Consistency Models How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study

1
367: Augmented Reality finally coming? Meta seems to think so 1:16:13

14d ago1:16:13

1:16:13

https://youtu.be/lRX1_4KjQWY Download as MP3 Sponsored by LINBIT: Visit destinationlinux.net/linbit to learn how LINBIT’s OSS, based on DRBD® and LINSTOR®, can be used for Kubernetes, CloudStack, OpenNebula, and more. Support the show by becoming a patron at tuxdigital.com/membership or get some swag at tuxdigital.com/store Hosted by: Michael Tunne…

1
Physics-Based Video, Text-Centric Visuals, Gaussian Splatting, Program Repair, Progressive Web Crawling 11:47

14d ago11:47

11:47

AI Papers Podcast for 04/23/2024 PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation TextSquare: Scaling up Text-Centric Visual Instruction Tuning Does Gaussian Splatting need SFM Initialization? How Far Can We Go with Practical Function-Level Program Repair? AutoCrawler: A Progressive Understanding Web Agent for Web Crawler…

1
Adapting Diverse Controls: Ctrl-Adapter, HQ-Edit, Tango 2 11:48

23d ago11:48

11:48

AI Papers Podcast for 04/21/2024Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion ModelHQ-Edit: A High-Quality Dataset for Instruction-based Image EditingTango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference OptimizationTextHawk: Exploring Efficient Fine-Grained Percept…

1
Dynamic Typography, Mesh Reconstruction, and Personalized Image Generation 11:27

16d ago11:27

11:27

AI Papers Podcast for 04/20/2024 Dynamic Typography: Bringing Words to Life Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing MeshLRM: Large Reconstruction Model for High-Quality Mesh MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation EdgeFusion: On-Device Text-to-Image Generatio…

1
AI Papers for 04/19/2024: Multimodal Advancements, AI Animation, Speculative Decoding 12:00

17d ago12:00

12:00

AI Papers Podcast for 04/19/2024 BLINK: Multimodal Large Language Models Can See but Not Perceive Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models AniClipart: Clipart Animation with Text-to-Video Priors TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding OpenBezoar: Small, Co…

1
AI Papers Special Release: Llama 3 1:48

18d ago1:48

1:48

AI Papers Podcast for 04/19/2024 Meta releases Llama 3, claims it's among the best open models availableBy PocketPod

1
AI Papers for 04/18/2024: "Generating Full-Length Music with Latent Diffusion" 5:49

18d ago5:49

5:49

AI Papers Podcast for 04/18/2024Long-form music generation with latent diffusionScaling Instructable Agents Across Many Simulated WorldsBy PocketPod

1
Episode 173: The Legend of Shartboi and Guava Gurl 54:24

19d ago54:24

54:24

The fellas talk about the new A24 film 'Civil War" 🍄🐲SUBSCRIBE on YouTube🐲🍄 https://www.youtube.com/channel/UC-vL4sWWxT8PwhRD9E1dBXA?sub_confirmation=1 Follow us on Instagram! @fromshrooms 📷 https://www.instagram.com/fromshrooms/ 🔵 https://www.facebook.com/fromshrooms And check out Shawn’s music- 👽 https://soundcloud.com/moselyy Just incase you wan…

1
AI Papers for 04/17/2024: Efficient Methods for Model Alignment and Compression 11:43

19d ago11:43

11:43

AI Papers Podcast for 04/17/2024Learn Your Reference Model for Real Good AlignmentMegalodon: Efficient LLM Pretraining and Inference with Unlimited Context LengthTransformerFAM: Feedback attention is working memoryCompression Represents Intelligence LinearlyVideo2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Sing…

1
The Future of Compiler Explorer

22d ago

—

Matt ponders the future of his accidentally eponymous hobby project. Ben offers thoughtful consideration while waiting for the right opportunity to crack a joke. No lawyers were harmed in the making of this podcast.

1
AI Papers for 04/16/2024: Advancing Language Models for Multimodal and Long-context Learning 11:35

22d ago11:35

11:35

AI Papers Podcast for 04/16/2024Octopus v2: On-device language model for super agentAdvancing LLM Reasoning Generalists with Preference TreesLong-context LLMs Struggle with Long In-context LearningLLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language ModelBigger is not Always Better: Scaling Properties of Latent Diffusion M…

1
366: Interview with Jon "maddog" Hall, a true LEGEND of Linux 1:13:39

21d ago1:13:39

1:13:39

https://youtu.be/90N6oWIkDZI Download as MP3 Sponsored by LINBIT: Visit destinationlinux.net/linbit to learn how LINBIT’s OSS, based on DRBD® and LINSTOR®, can be used for Kubernetes, CloudStack, OpenNebula, and more. Support the show by becoming a patron at tuxdigital.com/membership or get some swag at tuxdigital.com/store Hosted by: Michael Tunne…

1
AI Papers for 04/15/2024: Modernizing Segmentation, Analyzing CLIP, and Probing 3D Awareness in Vision Models 11:08

21d ago11:08

11:08

AI Papers Podcast for 04/15/2024 COCONut: Modernizing COCO Segmentation Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation Pre-training Small Base LMs with Fewer Tokens Probing the 3D Awareness of Visual Founda…

1
AI Papers Podcast for 04/14/2024 11:24

22d ago11:24

11:24

AI Papers Podcast for 04/14/2024 Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences: https://arxiv.org/abs/2404.03715 No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance: https://arxiv.org/abs/2404.04125 AutoWebGLM: Bootstrap And Reinforce A Large La…

1
AI Papers Podcast for 04/13/2024 12:41

23d ago12:41

12:41

AI Papers Podcast for 04/13/2024 OmniFusion Technical Report: https://arxiv.org/abs/2404.06212 LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders: https://arxiv.org/abs/2404.05961 InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD: https://arxiv.org/abs/2404.06512 Eagle a…

1
AI Papers Podcast for 04/12/2024 11:10

24d ago11:10

11:10

AI Papers Podcast 04/12/2024 RecurrentGemma: Moving Past Transformers for Efficient Open Language Models: https://arxiv.org/abs/2404.07839 WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents: https://arxiv.org/abs/2404.05902 Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models: https://arxiv.org…

1
AI Papers Podcast for 04/11/2024 11:28

24d ago11:28

11:28

AI Papers Podcast for 04/12/2024 ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback: https://arxiv.org/abs/2404.07987 OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments: https://arxiv.org/abs/2404.07972 Rho-1: Not All Tokens Are What You Need: https://arxiv.org/abs/2404.07965 Jet…

1
Episode 172: Boosting Engagement 1:02:52

26d ago1:02:52

1:02:52

Shawn makes music with AI 🍄🐲SUBSCRIBE on YouTube🐲🍄 https://www.youtube.com/channel/UC-vL4sWWxT8PwhRD9E1dBXA?sub_confirmation=1 Follow us on Instagram! @fromshrooms 📷 https://www.instagram.com/fromshrooms/ 🔵 https://www.facebook.com/fromshrooms And check out Shawn’s music- 👽 https://soundcloud.com/moselyy Just incase you wanted more links we put the…

1
“Pack Controller Settings FAQs: “Receiver Control” 13:31

28d ago13:31

13:31

In today's episode, our Danfoss controller experts, Chris and Dave, delve into some commonly asked questions about controller settings, showcasing their extensive knowledge and experience in the field. Tune in for a fun and informative extended portion of everybody's favorite podcast portion - "Stump Chris," while Dave grills Chris with some FAQ, i…

1
365: The XZorcist: a Compression Project Possessed by Evil 1:25:19

30d ago1:25:19

1:25:19

https://youtu.be/K6YnpBx1IEI Download as MP3 Sponsored by Kolide: If a device isn't secure, it can't access your apps. It's device trust for Okta. Visit https://destinationlinux.net/kolide to learn more and watch a demo. Sponsored by LINBIT: Visit destinationlinux.net/linbit to learn how LINBIT’s OSS, based on DRBD® and LINSTOR®, can be used for Ku…

Podcasts Worth a Listen

Video Compression Podcasts

Podcasts Worth a Listen

Quick Reference Guide