Les meilleurs podcasts Do Not Merge (2024)

1
[QA] A Hitchhiker's Guide to Scaling Law Estimation 10:08

5h ago10:08

10:08

The paper analyzes scaling laws in machine learning, providing best practices for estimating model performance using a large dataset of pretrained models and emphasizing the importance of intermediate training checkpoints. https://arxiv.org/abs//2410.11840 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Ap…

1
A Hitchhiker's Guide to Scaling Law Estimation 17:28

5h ago17:28

17:28

The paper analyzes scaling laws in machine learning, providing best practices for estimating model performance using a large dataset of pretrained models and emphasizing the importance of intermediate training checkpoints. https://arxiv.org/abs//2410.11840 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Ap…

1
[QA] Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations 7:39

5h ago7:39

7:39

This paper presents a novel method for image inversion and editing using rectified flow models, achieving superior performance in zero-shot tasks compared to existing diffusion model approaches. https://arxiv.org/abs//2410.10792 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcas…

1
Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations 10:29

5h ago10:29

10:29

This paper presents a novel method for image inversion and editing using rectified flow models, achieving superior performance in zero-shot tasks compared to existing diffusion model approaches. https://arxiv.org/abs//2410.10792 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcas…

1
972) WNBA Player Complains About Her Salary; Jim Forgot About Thanksgiving; Gretzky Retired 25 Years Ago? 48:31

21h ago48:31

48:31

We play our Friday song from the old TGOR show. Steve was once an actor in a drunk driving TV commercial. Jim didn't realize Thanksgiving had come and gone. It's maybe a little early for WNBA rookie Angel Reece to complain about her salary while living in an $8,000-a-month apartment. How the hell can Wayne Gretzky already be retired for 25 years? S…

1
[QA] Looking Inward: Language Models Can Learn About Themselves by Introspection 7:28

17h ago7:28

7:28

The paper explores whether large language models (LLMs) can introspect, finding that finetuned models can predict their own behavior, suggesting a form of internal knowledge access. https://arxiv.org/abs//2410.13787 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/…

1
Looking Inward: Language Models Can Learn About Themselves by Introspection 26:21

17h ago26:21

26:21

The paper explores whether large language models (LLMs) can introspect, finding that finetuned models can predict their own behavior, suggesting a form of internal knowledge access. https://arxiv.org/abs//2410.13787 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/…

1
[QA] Thinking LLMs: General Instruction Following with Thought Generation 7:25

17h ago7:25

7:25

The paper proposes a method to enhance LLMs' thinking abilities for better instruction following, improving performance across various tasks without additional human data through iterative search and optimization. https://arxiv.org/abs//2410.10630 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podca…

1
Thinking LLMs: General Instruction Following with Thought Generation 15:52

17h ago15:52

15:52

The paper proposes a method to enhance LLMs' thinking abilities for better instruction following, improving performance across various tasks without additional human data through iterative search and optimization. https://arxiv.org/abs//2410.10630 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podca…

1
[QA] Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs 7:44

1d ago7:44

7:44

The paper investigates extreme-token phenomena in transformer-based LLMs, revealing mechanisms behind attention sinks and proposing strategies to mitigate their impact during pretraining. https://arxiv.org/abs//2410.13835 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.appl…

1
Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs 17:44

1d ago17:44

17:44

The paper investigates extreme-token phenomena in transformer-based LLMs, revealing mechanisms behind attention sinks and proposing strategies to mitigate their impact during pretraining. https://arxiv.org/abs//2410.13835 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.appl…

1
[QA] MOVIE GEN: A Cast of Media Foundation Models 8:52

1d ago8:52

8:52

https://arxiv.org/abs//2410.13720 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016 Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers --- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/supp…

1
MOVIE GEN: A Cast of Media Foundation Models 1:53:06

1d ago1:53:06

1:53:06

https://arxiv.org/abs//2410.13720 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016 Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers --- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/supp…

1
Bank of Canada Takes Oversight of Payment Service Providers 15:33

2d ago15:33

15:33

In 2021, the Government of Canada passed the Retail Payments Activities Act, which required the Bank of Canada, the nation’s central bank, to begin overseeing payment service providers (PSPs). Under the legislation, Canadian PSPs—along with any entities involved in the electronic transfer or storage of funds—must register between November 1 and 15.…

1
[QA] One Step Diffusion via Shortcut Models 8:06

3d ago8:06

8:06

https://arxiv.org/abs//2410.12557 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016 Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers --- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/supp…

1
One Step Diffusion via Shortcut Models 17:39

3d ago17:39

17:39

https://arxiv.org/abs//2410.12557 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016 Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers --- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/supp…

1
[QA] Inference Scaling for Long-Context Retrieval Augmented Generation 7:17

3d ago7:17

7:17

https://arxiv.org/abs//2410.04343 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016 Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers --- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/supp…

1
Inference Scaling for Long-Context Retrieval Augmented Generation 22:02

3d ago22:02

22:02

https://arxiv.org/abs//2410.04343 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016 Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers --- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/supp…

1
Moment #28: Go from Unknown to The Standout Expert in Your Industry 13:53

4d ago13:53

13:53

Ever wondered what it takes to become the go-to expert in your niche without needing millions of followers? In this moment, Samantha and Ron Reich dive into the secrets of becoming a micro-celebrity in your niche. From understanding who your true fans are to crafting your superhero persona, they reveal the exact steps to elevate your business and p…

1
[QA] What Matters in Transformers? Not All Attention is Needed 8:07

3d ago8:07

8:07

This study explores redundancy in Transformer architectures, revealing that many attention layers can be pruned with minimal performance loss, enhancing efficiency for large language models. https://arxiv.org/abs//2406.15786 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.a…

1
What Matters in Transformers? Not All Attention is Needed 16:20

3d ago16:20

16:20

This study explores redundancy in Transformer architectures, revealing that many attention layers can be pruned with minimal performance loss, enhancing efficiency for large language models. https://arxiv.org/abs//2406.15786 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.a…

1
[QA] Language Models Encode Numbers Using Digit Representations in Base 10 7:33

3d ago7:33

7:33

The paper investigates how large language models represent numbers, revealing they use digit-wise circular representations, which explains their frequent errors in numerical reasoning tasks. https://arxiv.org/abs//2410.11781 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.a…

1
Language Models Encode Numbers Using Digit Representations in Base 10 10:36

3d ago10:36

10:36

The paper investigates how large language models represent numbers, revealing they use digit-wise circular representations, which explains their frequent errors in numerical reasoning tasks. https://arxiv.org/abs//2410.11781 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.a…

1
Accountants View AI as an Ally, not a Competitor 21:01

4d ago21:01

21:01

Artificial intelligence has had a dramatic effect across industries in a short time. Accounting is no exception, but there has been speculation of whether AI would replace those working in the profession. In a recent PaymentsJournal podcast, Ted Callahan, Accountant Leader at Intuit, and Albert Bodine, Director of Commercial Payments at Javelin Str…

1
Merging Energetics, Psychology, and Strategy for Maximum Impact with Azra 33:26

6d ago33:26

33:26

Feeling stuck despite your efforts? Learn how Vedic astrology can transform your approach by blending energy, psychology, and strategy to elevate your business. In this episode, Samantha dives deep into the mystical world of Vedic astrology with Azra, a corporate strategist turned spiritual guide. Together, they explore how this ancient practice ca…

1
[QA] Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs 7:31

6d ago7:31

7:31

This paper explores using large language models to generate code transformations through a chain-of-thought approach, demonstrating improved precision and adaptability compared to direct code rewriting methods. https://arxiv.org/abs//2410.08806 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts…

1
Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs 6:15

6d ago6:15

6:15

This paper explores using large language models to generate code transformations through a chain-of-thought approach, demonstrating improved precision and adaptability compared to direct code rewriting methods. https://arxiv.org/abs//2410.08806 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts…

1
[QA] Do Unlearning Methods Remove Information from Language Model Weights? 8:03

6d ago8:03

8:03

The paper evaluates unlearning techniques in Large Language Models, revealing that current methods inadequately remove sensitive information, allowing attackers to recover significant pre-unlearning accuracy. https://arxiv.org/abs//2410.08827 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: …

1
Do Unlearning Methods Remove Information from Language Model Weights? 17:56

6d ago17:56

17:56

The paper evaluates unlearning techniques in Large Language Models, revealing that current methods inadequately remove sensitive information, allowing attackers to recover significant pre-unlearning accuracy. https://arxiv.org/abs//2410.08827 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: …

1
[QA] MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering 7:19

7d ago7:19

7:19

MLE-bench is a benchmark for evaluating AI agents in machine learning engineering, featuring 75 Kaggle competitions and establishing human baselines, with open-source code for future research. https://arxiv.org/abs//2410.07095 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts…

1
MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering 16:41

7d ago16:41

16:41

MLE-bench is a benchmark for evaluating AI agents in machine learning engineering, featuring 75 Kaggle competitions and establishing human baselines, with open-source code for future research. https://arxiv.org/abs//2410.07095 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts…

1
[QA] Pixtral 12B 7:34

7d ago7:34

7:34

https://arxiv.org/abs//2410.07073 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016 Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers --- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/supp…

1
Pixtral 12B 13:01

7d ago13:01

13:01

https://arxiv.org/abs//2410.07073 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016 Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers --- Support this podcast: https://podcasters.spotify.com/pod/show/arxiv-papers/supp…

1
[QA] Differential Transformer 7:20

8d ago7:20

7:20

DIFF Transformer enhances attention to relevant context while reducing noise, improving performance in language modeling, long-context tasks, and in-context learning, making it a promising architecture for large language models. https://arxiv.org/abs//2410.05258 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_pap…

1
Differential Transformer 13:09

8d ago13:09

13:09

DIFF Transformer enhances attention to relevant context while reducing noise, improving performance in language modeling, long-context tasks, and in-context learning, making it a promising architecture for large language models. https://arxiv.org/abs//2410.05258 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_pap…

1
[QA] GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models 7:45

8d ago7:45

7:45

This study introduces GSM-Symbolic, a benchmark revealing LLMs' inconsistent mathematical reasoning, highlighting performance drops with altered questions and increased complexity, questioning their genuine logical reasoning abilities. https://arxiv.org/abs//2410.05229 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@ar…

1
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models 12:39

8d ago12:39

12:39

This study introduces GSM-Symbolic, a benchmark revealing LLMs' inconsistent mathematical reasoning, highlighting performance drops with altered questions and increased complexity, questioning their genuine logical reasoning abilities. https://arxiv.org/abs//2410.05229 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@ar…

1
[QA] Efficient Dictionary Learning with Switch Sparse Autoencoders 7:43

9d ago7:43

7:43

Switch Sparse Autoencoders efficiently scale feature extraction in neural networks by routing activations through smaller expert models, improving reconstruction and sparsity while reducing computational costs. https://arxiv.org/abs//2410.08201 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts…

1
Efficient Dictionary Learning with Switch Sparse Autoencoders 15:44

9d ago15:44

15:44

Switch Sparse Autoencoders efficiently scale feature extraction in neural networks by routing activations through smaller expert models, improving reconstruction and sparsity while reducing computational costs. https://arxiv.org/abs//2410.08201 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts…

1
[QA] Visual Scratchpads: Enabling Global Reasoning in Vision 7:22

9d ago7:22

7:22

This paper introduces global visual benchmarks, highlighting modern vision models' struggles with global reasoning and proposing 'visual scratchpads' to enhance learning efficiency and generalization. https://arxiv.org/abs//2410.08165 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://…

1
Visual Scratchpads: Enabling Global Reasoning in Vision 26:26

9d ago26:26

26:26

This paper introduces global visual benchmarks, highlighting modern vision models' struggles with global reasoning and proposing 'visual scratchpads' to enhance learning efficiency and generalization. https://arxiv.org/abs//2410.08165 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://…

1
971) Shesterkin's Crazy Contract Demand, NY Jets Coach Robert Saleh Fired By...Aaron Rodgers? 33:41

9d ago33:41

33:41

Shesterkin's Crazy Contract Demand, NY Jets Coach Robert Saleh Fired By His QB? And will Mike Tyson be the one to stop the cocky You Tubers from thinking they're great boxers?

1
Prepaid Cards Are Essential Components of Rewards and Incentives Programs 19:22

9d ago19:22

19:22

When the topic is prepaid cards, the store-branded or general-purpose gift cards at grocery stores and retailers might come to mind. However, a substantial number of businesses and organizations continually use prepaid cards for a range of cases, including employee incentives and customer rebates. In a recent PaymentsJournal podcast, Sheryl Shewman…

1
[QA] RL, but don't do anything I wouldn't do 7:43

10d ago7:43

7:43

The paper critiques KL regularization in reinforcement learning, showing it fails with Bayesian predictive models, and proposes a new principle to better control advanced RL agent behavior. https://arxiv.org/abs//2410.06213 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.ap…

1
RL, but don't do anything I wouldn't do 16:19

10d ago16:19

16:19

The paper critiques KL regularization in reinforcement learning, showing it fails with Bayesian predictive models, and proposes a new principle to better control advanced RL agent behavior. https://arxiv.org/abs//2410.06213 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.ap…

1
[QA] Restructuring Vector Quantization with the Rotation Trick 7:43

10d ago7:43

7:43

This paper proposes a method to propagate gradients through VQ-VAEs' vector quantization layer, improving reconstruction metrics, codebook utilization, and quantization error across various training paradigms. https://arxiv.org/abs//2410.06424 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts:…

1
Restructuring Vector Quantization with the Rotation Trick 23:23

10d ago23:23

23:23

This paper proposes a method to propagate gradients through VQ-VAEs' vector quantization layer, improving reconstruction metrics, codebook utilization, and quantization error across various training paradigms. https://arxiv.org/abs//2410.06424 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts:…

1
Moment #27: Why Your Marketing Isn’t Working (And What to Do About It) 6:28

11d ago6:28

6:28

Are you chasing shiny objects instead of optimising what already works? In this moment, Samantha challenges you to take a hard look at your marketing and sales efforts. Would you be earning a raise or facing a performance improvement plan if you were employing yourself as the Chief Marketing Officer of your company? Dive into the magic of the “Thre…

1
[QA] EnsemW2S: Can an Ensemble of LLMs be Leveraged to Obtain a Stronger LLM? 7:42

12d ago7:42

7:42

This research proposes an innovative ensemble method for weak-to-strong generalization in AI, enhancing LLM performance through collaborative supervision, achieving significant improvements on challenging tasks. https://arxiv.org/abs//2410.04571 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcast…

1
EnsemW2S: Can an Ensemble of LLMs be Leveraged to Obtain a Stronger LLM? 18:39

12d ago18:39

18:39

This research proposes an innovative ensemble method for weak-to-strong generalization in AI, enhancing LLM performance through collaborative supervision, achieving significant improvements on challenging tasks. https://arxiv.org/abs//2410.04571 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcast…

Podcasts qui valent la peine d'être écoutés

Do Not Merge Podcasts

Podcasts qui valent la peine d'être écoutés

Guide de référence rapide