Best Semi Limited Podcast Podcasts (2024)

1
Semi-Limited Podcast Ep: 0081 "Power Creeping Backwards?! 1:07:50

6d ago1:07:50

1:07:50

Boy oh boy do we have a jam packed episode for ya'll! Things get all kinds of spicy as Player X sits down with Goat himself, Mr. Jesse Kotton! They deep dive into everything from the impact of reprinting cards like from this year's megatins, his epic experience competing at Yugioh World Championships, and everyone's favorite segment, Peoples Choice…

1
[QA] Emu3: Next-Token Prediction is All You Need 7:43

4m ago7:43

7:43

Emu3 introduces a next-token prediction model for multimodal tasks, outperforming existing models and simplifying design by focusing on tokenization of images, text, and videos. https://arxiv.org/abs//2409.18869 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/p…

1
Emu3: Next-Token Prediction is All You Need 17:28

5m ago17:28

17:28

Emu3 introduces a next-token prediction model for multimodal tasks, outperforming existing models and simplifying design by focusing on tokenization of images, text, and videos. https://arxiv.org/abs//2409.18869 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/p…

1
[QA] MIO: A Foundation Model on Multimodal Tokens 8:38

9m ago8:38

8:38

MIO is a novel multimodal foundation model that excels in understanding and generating speech, text, images, and videos, outperforming existing models in any-to-any capabilities and diverse tasks. https://arxiv.org/abs//2409.17692 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podc…

1
MIO: A Foundation Model on Multimodal Tokens 19:09

9m ago19:09

19:09

MIO is a novel multimodal foundation model that excels in understanding and generating speech, text, images, and videos, outperforming existing models in any-to-any capabilities and diverse tasks. https://arxiv.org/abs//2409.17692 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podc…

1
[QA] A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor ? 7:52

6m ago7:52

7:52

The paper evaluates OpenAI's o1 model in medical scenarios, highlighting its enhanced reasoning and accuracy over GPT-4, while also identifying weaknesses and releasing data for further research. https://arxiv.org/abs//2409.15277 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podca…

1
A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor ? 8:52

7m ago8:52

8:52

The paper evaluates OpenAI's o1 model in medical scenarios, highlighting its enhanced reasoning and accuracy over GPT-4, while also identifying weaknesses and releasing data for further research. https://arxiv.org/abs//2409.15277 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podca…

1
[QA] Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models 8:44

11m ago8:44

8:44

The Logic-of-Thought (LoT) prompting method enhances logical reasoning in Large Language Models by integrating propositional logic, significantly improving performance across various reasoning tasks. https://arxiv.org/abs//2409.17539 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://p…

1
Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models 16:05

11m ago16:05

16:05

The Logic-of-Thought (LoT) prompting method enhances logical reasoning in Large Language Models by integrating propositional logic, significantly improving performance across various reasoning tasks. https://arxiv.org/abs//2409.17539 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://p…

1
TD197: Video Reviews: Garmin dēzl™ Headset 200 & Garmin dēzl™OTR810 15:11

11h ago15:11

15:11

So it’s been over a year since the last episode aired, so obviously I start out with a groveling apology, followed by a brief explanation of what happened. I also lay out a plan to wrap up the Trucker Dump Podcast once and for all. But for now, here are the links to those long overdue Garmin video reviews I’ve been talking about. And I also throw i…

1
[QA] Making Text Embedders Few-Shot Learners 7:45

17m ago7:45

7:45

We propose bge-en-icl, a model leveraging in-context learning in LLMs for high-quality text embeddings, achieving state-of-the-art performance on MTEB and AIR-Bench benchmarks. https://arxiv.org/abs//2409.15700 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/po…

1
Making Text Embedders Few-Shot Learners 16:11

17m ago16:11

16:11

We propose bge-en-icl, a model leveraging in-context learning in LLMs for high-quality text embeddings, achieving state-of-the-art performance on MTEB and AIR-Bench benchmarks. https://arxiv.org/abs//2409.15700 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/po…

1
[QA] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale 6:45

27m ago6:45

6:45

The paper introduces PROX, a framework enabling small language models to refine data effectively, outperforming human-crafted methods and enhancing efficiency in LLM pre-training across various benchmarks. https://arxiv.org/abs//2409.17115 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: htt…

1
Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale 8:57

28m ago8:57

8:57

The paper introduces PROX, a framework enabling small language models to refine data effectively, outperforming human-crafted methods and enhancing efficiency in LLM pre-training across various benchmarks. https://arxiv.org/abs//2409.17115 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: htt…

1
[QA] Infer Human's Intentions Before Following Natural Language Instruction 8:18

3m ago8:18

8:18

The FISER framework enhances AI's ability to follow ambiguous human instructions by inferring intentions, outperforming traditional methods in collaborative tasks, particularly on the HandMeThat benchmark. https://arxiv.org/abs//2409.18073 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: htt…

1
Infer Human's Intentions Before Following Natural Language Instruction 27:36

4m ago27:36

27:36

The FISER framework enhances AI's ability to follow ambiguous human instructions by inferring intentions, outperforming traditional methods in collaborative tasks, particularly on the HandMeThat benchmark. https://arxiv.org/abs//2409.18073 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: htt…

1
[QA] MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models 7:05

9m ago7:05

7:05

This paper presents a learnable pruning method for Large Language Models, achieving efficient N:M sparsity, improved mask quality, and transferability across tasks, outperforming existing techniques in empirical evaluations. https://arxiv.org/abs//2409.17481 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers …

1
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models 15:10

9m ago15:10

15:10

This paper presents a learnable pruning method for Large Language Models, achieving efficient N:M sparsity, improved mask quality, and transferability across tasks, outperforming existing techniques in empirical evaluations. https://arxiv.org/abs//2409.17481 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers …

1
[QA] Counterfactual Token Generation in Large Language Models 7:53

10m ago7:53

7:53

This paper presents a method to enable large language models to perform counterfactual token generation, enhancing their capabilities without fine-tuning, and applying it for bias detection. https://arxiv.org/abs//2409.17027 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.a…

1
Counterfactual Token Generation in Large Language Models 14:52

11m ago14:52

14:52

This paper presents a method to enable large language models to perform counterfactual token generation, enhancing their capabilities without fine-tuning, and applying it for bias detection. https://arxiv.org/abs//2409.17027 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.a…

1
[QA] Characterizing stable regions in the residual stream of LLMs 7:45

15m ago7:45

7:45

The paper identifies stable regions in Transformers' residual streams, showing insensitivity to small changes but high sensitivity at boundaries, aligning with semantic distinctions and clustering similar prompts. https://arxiv.org/abs//2409.17113 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podca…

1
Characterizing stable regions in the residual stream of LLMs 5:26

15m ago5:26

5:26

The paper identifies stable regions in Transformers' residual streams, showing insensitivity to small changes but high sensitivity at boundaries, aligning with semantic distinctions and clustering similar prompts. https://arxiv.org/abs//2409.17113 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podca…

1
[QA] Watch Your Steps: Observable and Modular Chains of Thought 7:30

28m ago7:30

7:30

We introduce Program Trace Prompting, enhancing chain of thought explanations with formal syntax, improving observability, and enabling analysis of reasoning errors across diverse tasks in the BIG-Bench Hard benchmark. https://arxiv.org/abs//2409.15359 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple …

1
Watch Your Steps: Observable and Modular Chains of Thought 29:35

2h ago29:35

29:35

We introduce Program Trace Prompting, enhancing chain of thought explanations with formal syntax, improving observability, and enabling analysis of reasoning errors across diverse tasks in the BIG-Bench Hard benchmark. https://arxiv.org/abs//2409.15359 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple …

1
[QA] Seeing Faces in Things: A Model and Dataset for Pareidolia 7:38

11h ago7:38

7:38

This paper explores face pareidolia in computer vision, presenting a dataset of annotated images and analyzing the differences in face detection between humans and machines. https://arxiv.org/abs//2409.16143 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podca…

1
Seeing Faces in Things: A Model and Dataset for Pareidolia 10:54

2h ago10:54

10:54

This paper explores face pareidolia in computer vision, presenting a dataset of annotated images and analyzing the differences in face detection between humans and machines. https://arxiv.org/abs//2409.16143 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podca…

1
[QA] Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts 8:20

33m ago8:20

8:20

The paper investigates out-of-distribution behavior in autoregressive LLMs through rule extrapolation in formal languages, analyzing various architectures and proposing a normative theory inspired by algorithmic information theory. https://arxiv.org/abs//2409.13728 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_…

1
Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts 29:04

1h ago29:04

29:04

The paper investigates out-of-distribution behavior in autoregressive LLMs through rule extrapolation in formal languages, analyzing various architectures and proposing a normative theory inspired by algorithmic information theory. https://arxiv.org/abs//2409.13728 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_…

1
[QA] Style over Substance: Failure Modes of LLM Judges in Alignment Benchmarking 7:40

8m ago7:40

7:40

This study evaluates the effectiveness of LLM-judge preferences in improving alignment, finding no correlation with concrete metrics and highlighting biases in LLM judgments. https://arxiv.org/abs//2409.15268 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podc…

1
Style over Substance: Failure Modes of LLM Judges in Alignment Benchmarking 11:39

9m ago11:39

11:39

This study evaluates the effectiveness of LLM-judge preferences in improving alignment, finding no correlation with concrete metrics and highlighting biases in LLM judgments. https://arxiv.org/abs//2409.15268 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podc…

1
[QA] LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models 7:46

32m ago7:46

7:46

This paper introduces LLM Surgery, a framework for efficiently modifying large language models to unlearn outdated information and integrate new knowledge without complete retraining, demonstrating significant performance improvements. https://arxiv.org/abs//2409.13054 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@ar…

1
LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models 13:56

33m ago13:56

13:56

This paper introduces LLM Surgery, a framework for efficiently modifying large language models to unlearn outdated information and integrate new knowledge without complete retraining, demonstrating significant performance improvements. https://arxiv.org/abs//2409.13054 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@ar…

1
[QA] Embedding Geometries of Contrastive Language-Image Pre-Training 7:35

7m ago7:35

7:35

This paper explores alternative geometries and softmax logits for language-image pre-training, finding that Euclidean CLIP (EuCLIP) performs as well as or better than the original CLIP. https://arxiv.org/abs//2409.13079 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.…

1
Embedding Geometries of Contrastive Language-Image Pre-Training 15:25

2d ago15:25

15:25

This paper explores alternative geometries and softmax logits for language-image pre-training, finding that Euclidean CLIP (EuCLIP) performs as well as or better than the original CLIP. https://arxiv.org/abs//2409.13079 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.…

1
[QA] Kolmogorov–Arnold Transformer 8:14

40m ago8:14

8:14

The Kolmogorov–Arnold Transformer (KAT) enhances transformer performance by replacing MLP layers with Kolmogorov-Arnold Network layers, addressing key challenges and demonstrating superior results in various tasks. https://arxiv.org/abs//2409.10594 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podc…

1
Kolmogorov–Arnold Transformer 15:05

41m ago15:05

15:05

The Kolmogorov–Arnold Transformer (KAT) enhances transformer performance by replacing MLP layers with Kolmogorov-Arnold Network layers, addressing key challenges and demonstrating superior results in various tasks. https://arxiv.org/abs//2409.10594 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podc…

1
[QA] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think 6:42

1h ago6:42

6:42

This paper reveals a flaw in the inference pipeline of diffusion models for depth estimation, leading to a 2002#2 speed improvement and superior performance through end-to-end fine-tuning. https://arxiv.org/abs//2409.11355 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.app…

1
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think 11:52

1h ago11:52

11:52

This paper reveals a flaw in the inference pipeline of diffusion models for depth estimation, leading to a 2002#2 speed improvement and superior performance through end-to-end fine-tuning. https://arxiv.org/abs//2409.11355 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.app…

1
The Emerging Legal Landscape around Intimate Photos and the Internet 26:30

4h ago26:30

26:30

Back in the pre-digital days, you’d bring film into a drugstore to be developed. If the film contained nude photos, the only person you had to worry about was “that creepy guy behind the counter.” “That was when we were talking about paper photos. They can actually get that photo back. It's done, right? Different day now,” Stan Gipe explains in thi…

1
[QA] Re-Introducing LayerNorm: Geometric Meaning, Irreversibility and a Comparative Study with RMSNorm 7:03

40m ago7:03

7:03

This paper explores the geometric implications of LayerNorm in transformers, revealing its irreversibility and redundancy, and advocates for RMSNorm as a more efficient alternative with similar performance. https://arxiv.org/abs//2409.12951 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: ht…

1
Re-Introducing LayerNorm: Geometric Meaning, Irreversibility and a Comparative Study with RMSNorm 12:28

7d ago12:28

12:28

This paper explores the geometric implications of LayerNorm in transformers, revealing its irreversibility and redundancy, and advocates for RMSNorm as a more efficient alternative with similar performance. https://arxiv.org/abs//2409.12951 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: ht…

1
[QA] Is Tokenization Needed for Masked Particle Modelling? 7:52

1d ago7:52

7:52

This paper enhances masked particle modeling (MPM) for high-energy physics, improving performance through better implementation and a powerful decoder, outperforming previous methods in various jet physics tasks. https://arxiv.org/abs//2409.12589 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcas…

1
Is Tokenization Needed for Masked Particle Modelling? 20:39

7d ago20:39

20:39

This paper enhances masked particle modeling (MPM) for high-energy physics, improving performance through better implementation and a powerful decoder, outperforming previous methods in various jet physics tasks. https://arxiv.org/abs//2409.12589 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcas…

1
[QA] Finetuning Language Models to Emit Linguistic Expressions of Uncertainty 6:49

9h ago6:49

6:49

https://arxiv.org/abs//2409.12180 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
Finetuning Language Models to Emit Linguistic Expressions of Uncertainty 12:41

9h ago12:41

12:41

https://arxiv.org/abs//2409.12180 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] To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning 7:23

9h ago7:23

7:23

Chain-of-thought prompting enhances reasoning in large language models, particularly for math and logic tasks, but shows limited benefits for other tasks, suggesting a need for new computational paradigms. https://arxiv.org/abs//2409.12183 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: htt…

1
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning 26:23

9h ago26:23

26:23

Chain-of-thought prompting enhances reasoning in large language models, particularly for math and logic tasks, but shows limited benefits for other tasks, suggesting a need for new computational paradigms. https://arxiv.org/abs//2409.12183 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: htt…

1
[QA] On the limits of agency in agent-based models 8:12

15m ago8:12

8:12

AgentTorch is a framework that enhances agent-based modeling by using large language models to simulate millions of agents, demonstrating its utility in analyzing complex systems like the COVID-19 pandemic. https://arxiv.org/abs//2409.10568 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: ht…

1
On the limits of agency in agent-based models 19:50

16m ago19:50

19:50

AgentTorch is a framework that enhances agent-based modeling by using large language models to simulate millions of agents, demonstrating its utility in analyzing complex systems like the COVID-19 pandemic. https://arxiv.org/abs//2409.10568 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: ht…

1
[QA] Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models 7:14

21h ago7:14

7:14

Promptriever is a novel retrieval model that follows instructions, achieving state-of-the-art performance and improved robustness, demonstrating the potential of prompting in information retrieval. https://arxiv.org/abs//2409.11136 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://pod…

Podcasts Worth a Listen

Semi Limited Podcast

Podcasts Worth a Listen

Quick Reference Guide