UX Magazine presents the Invisible Machines podcast. Conversational AI is going everywhere. Join great weekly conversations with experts in a podcast about conversational AI and hyperautomation, covering the intersection of UX, business, technology and design. Robb Wilson and Josh Tyson, authors of Age Of Invisible Machines, the first bestselling book about conversational AI, envisioned the moment we’re in with ChatGPT and the AI revolution. Join weekly as they continue their discussion with ...
…
continue reading
The Tech Savvy Professor, hosted by Dr. Marty Jencius (Kent State University) and Dr. Eric Perry (Keiser University), are two professors' love for all things technology. TSP will be brief weekly conversations regarding what technology they are currently enjoying. You'll get helpful ideas of great software, apps, and hardware as they can be used in your academic and non-academic life.
…
continue reading
Point-Free is a video series that explores advanced topics in the Swift programming language. Each episode covers a topic that may seem complex and academic at first, but turns out to be quite simple. At the end of each episode we’ll ask “what’s the point?!”, so that we can bring the concepts back down to earth and show how these ideas can improve the quality of your code today.
…
continue reading
Running out of time to catch up with new arXiv papers? We take the most impactful papers and present them as convenient podcasts. If you're a visual learner, we offer these papers in an engaging video format. Our service fills the gap between overly brief paper summaries and time-consuming full paper reads. You gain academic insights in a time-efficient, digestible format. Code behind this work: https://github.com/imelnyk/ArxivPapers Support this podcast: https://podcasters.spotify.com/pod/s ...
…
continue reading
Med Motivation is a Podcast for medical students. We discuss all things in Medicine, including evidence-based productivity tips to junior doctors and medical students and motivation to keep them going through their otherwise extremely exhausting and difficult academic journey
…
continue reading
Un podcast que explora el presente y el futuro de la educación digital y la tecnología en las universidades. Entrevistas con expertos y líderes en el campo de las TIC en la educación superior.
…
continue reading
1
CISSP Cyber Training Podcast - CISSP Training Program
Shon Gerber, vCISO, CISSP, Cybersecurity Consultant and Entrepreneur
Join Shon Gerber on his weekly CISSP Cyber Training podcast, where his extensive 22-year background in cybersecurity shines through. With a rich history spanning corporate sectors, government roles, and academic positions, Shon imparts the essential insights and advice necessary to conquer the CISSP exam. His expertise is not just theoretical; as a CISSP credential holder since 2009, Shon translates his deep understanding into actionable training. Each episode is packed with invaluable secur ...
…
continue reading
Welcome to Deeper learning, where we explore the world of autonomous driving from a safety technology perspective. Join us as we discuss various topics related to automotive safety, from the challenges and advancements in software-defined vehicles to deep learning and AI. Thank you for listening. Follow Zenseact on: LinkedIn: https://www.linkedin.com/company/zenseact/ https://www.instagram.com/zenseact/
…
continue reading
Peoples & Things is a podcast in which host Lee Vinsel interviews scholars, practitioners, and activists about human life with technology.
…
continue reading
The Industrial Research Podcast explores the tips, tricks and techniques used by software industry researchers to attempt to predict future trends, develop new ideas or concepts and validate them. This Podcast is aimed at fellow Industrial Researchers, anyone involved in corporate strategy or entrepreneurs who want to explore how technical and competitive landscapes can be understood. This mini-series will cover the basics of Industrial Research and how it differs from academic research, rig ...
…
continue reading
Podcast for developers, testers, SREs... and their managers. I explain complex and convoluted technologies in a clear way, avoiding buzzwords and hype. Never longer than 4 minutes and 16 seconds. Because software development does not require hours of lectures, dev advocates' slide decks and hand waving. For those of you, who want to combat FOMO, while brushing your teeth. 256 seconds is plenty of time. If I can't explain something within this time frame, it's either too complex, or I don't u ...
…
continue reading
The Road to Open Science Podcast is your guide on everything Open at Utrecht University and beyond. In our monthly podcast we discuss the latest developments in the fields of open acces, open data/software, public engagement and recognition and rewards.
…
continue reading
Welcome to the givingBack Nepali Podcast! This podcast series is created especially for Nepali communities living around the world for academic and professional purposes. The givingBack Podcast® is dedicated to contributing to Nepali communities by bringing the rigorous topics/subjects ranging from Artificial Intelligence and Machine earning to Foreign policies and Economics into a comprehension of a common man. For video, visit https://www.youtube.com/channel/UCnHj8M4FkEe8yYgUEXx7tXQ Suppor ...
…
continue reading
Do you love apps and technology? Or are you a little intimidated by them? Your App Lady is here to help! This podcast delivers easy to digest, small chunks of tech information and incredibly usable apps that will improve your life. This podcast is archived. Please join me on my new podcast - For All Abilities. For All Abilities -The Podcast is meant to inform the world of the amazing people out there who are succeeding in HUGE ways with brains who don’t find into the imaginary norm. While de ...
…
continue reading
In the Real Life Superpowers podcast (ranked top 10% of global podcasts), Ronen Menipaz and Noa Eshed feature conversations with people they identify as peak performers. The podcast covers their uncut, no-fluff version of their journey to the top, the challenges, pitfalls, and obstacles – the real-life version of the arc of the hero. The idea is to help the listeners bridge the gap in social media where successful entrepreneurs are put on a pedestal and seem to be surfing on a rainbow, ringi ...
…
continue reading
Founders First explores how founders got started, what they did before starting their startups, and how you can go from an idea to a venture-backed company.
…
continue reading
The Corresponding Author podcast (https://twitter.com/CorrespondAuth) with Stephanie Hicks (https://twitter.com/stephaniehicks) and John Muschelli (https://twitter.com/StrictlyStat). We discuss academic data science and issues related to that, such as funding, promotion, hiring, and what that even means.
…
continue reading
Startup engineering is a podcast that goes behind the scenes at startups. Rob De Feo, startup advocate at AWS your host will talk to engineers, CTO’s, and founders that built the technology and products at some of the world's leading startups. Each episode we will learn the inside story of how they overcame their biggest technology challenges. From launch through to achieving mass scale, and all the bumps in between. Experts share their experiences, lessons learnt and best practices. If you ...
…
continue reading
1
[QA] AI-Assisted Generation of Difficult Math Questions
8:36
8:36
Play later
Play later
Lists
Like
Liked
8:36
The paper presents a framework combining LLMs and human input to generate diverse, challenging math questions, enhancing quality through iterative refinement and skill-based question generation. https://arxiv.org/abs//2407.21009 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcas…
…
continue reading
1
AI-Assisted Generation of Difficult Math Questions
31:27
31:27
Play later
Play later
Lists
Like
Liked
31:27
The paper presents a framework combining LLMs and human input to generate diverse, challenging math questions, enhancing quality through iterative refinement and skill-based question generation. https://arxiv.org/abs//2407.21009 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcas…
…
continue reading
1
[QA] SAM 2: Segment Anything in Images and Videos
7:25
7:25
Play later
Play later
Lists
Like
Liked
7:25
https://arxiv.org/abs//2408.00714 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…
…
continue reading
1
SAM 2: Segment Anything in Images and Videos
26:23
26:23
Play later
Play later
Lists
Like
Liked
26:23
https://arxiv.org/abs//2408.00714 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…
…
continue reading
1
S4E2 Ephemeral Applications and AGI
1:06:03
1:06:03
Play later
Play later
Lists
Like
Liked
1:06:03
We're entering an age when software will be written on-the-fly, by machines, to meet individual needs—an era of ephemeral applications. This will have a massive impact on the emergence of artificial general intelligence (also called AGI or singularity) and Ben Goertzel returns for a lively discussion about the scope of this dawning era. Ben helped …
…
continue reading
1
[QA] MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts
7:42
7:42
Play later
Play later
Lists
Like
Liked
7:42
https://arxiv.org/abs//2407.21770 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…
…
continue reading
1
MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts
41:46
41:46
Play later
Play later
Lists
Like
Liked
41:46
https://arxiv.org/abs//2407.21770 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…
…
continue reading
1
[QA] Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
7:49
7:49
Play later
Play later
Lists
Like
Liked
7:49
This paper explores scaling inference compute by increasing sample generation, demonstrating improved problem-solving coverage and performance across tasks, while highlighting challenges in selecting correct solutions from multiple samples. https://arxiv.org/abs//2407.21787 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.co…
…
continue reading
1
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
37:21
37:21
Play later
Play later
Lists
Like
Liked
37:21
This paper explores scaling inference compute by increasing sample generation, demonstrating improved problem-solving coverage and performance across tasks, while highlighting challenges in selecting correct solutions from multiple samples. https://arxiv.org/abs//2407.21787 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.co…
…
continue reading
1
CCT 163: Practice CISSP Questions - Data Roles and Regulations, Security Responsibilities (Domain 2)
17:01
17:01
Play later
Play later
Lists
Like
Liked
17:01
Send us a Text Message. Are you ready to ace your CISSP exam and propel your cybersecurity career to new heights? This episode of the CISSP Cyber Training Podcast promises to equip you with critical insights on data roles and regulations. From demystifying the responsibilities of data processors under GDPR to unpacking the PCI DSS framework essenti…
…
continue reading
1
E75 - Aviad Harell (Managing Partner Team8, co-Founder Sisense)
58:56
58:56
Play later
Play later
Lists
Like
Liked
58:56
In this episode, we speak with Aviad Harell - the Managing Partner at Team8, a global VC with deep domain expertise that builds and invests in companies specializing in enterprise technologies, cyber, AI, and fintech. He’s a seasoned angel investor and adviser to numerous startups, VCs, and executives. Before joining Team8, he co-founded Sisense, a…
…
continue reading
1
[QA] Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
7:40
7:40
Play later
Play later
Lists
Like
Liked
7:40
This paper examines vulnerabilities in Large Language Models, particularly in medical summarization, and proposes mitigation strategies to enhance their security and resilience against data leaks. https://arxiv.org/abs//2407.20529 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podc…
…
continue reading
1
Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
30:39
30:39
Play later
Play later
Lists
Like
Liked
30:39
This paper examines vulnerabilities in Large Language Models, particularly in medical summarization, and proposes mitigation strategies to enhance their security and resilience against data leaks. https://arxiv.org/abs//2407.20529 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podc…
…
continue reading
1
[QA] How to Measure the Intelligence of Large Language Models?
7:34
7:34
Play later
Play later
Lists
Like
Liked
7:34
https://arxiv.org/abs//2407.20828 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…
…
continue reading
1
How to Measure the Intelligence of Large Language Models?
8:05
8:05
Play later
Play later
Lists
Like
Liked
8:05
https://arxiv.org/abs//2407.20828 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…
…
continue reading
Marty and Eric speak about two kinds of monitor extenders they use for that second monitor while traveling. Marty's Single monitor - KYY Laptop extender - CIDETTY Eric's Single monitor - Viewsonic Laptop extender - Kefeya
…
continue reading
1
CCT 162: Decoding Data Roles in CISSP and Navigating NIST Guidelines for Cybersecurity Governance (Domain 2)
34:39
34:39
Play later
Play later
Lists
Like
Liked
34:39
Send us a Text Message. Unlock the secrets to mastering Domain 2 of the CISSP exam and navigate the paradox of the booming yet financially strained cybersecurity field. Despite the staggering 4 million global job openings, recent budget cuts and layoffs are reshaping the landscape. Learn how economic challenges are clashing with the rising demand f…
…
continue reading
1
Kate McDonald on Asian Mobility History as Labor History
1:13:33
1:13:33
Play later
Play later
Lists
Like
Liked
1:13:33
Peoples & Things host, Lee Vinsel, talks to Kate McDonald, Associate Professor of History at University of California, Santa Barbara, about her fascinating research on the history of mobility in Asia and how it looks different when we approach it as a history of work and labor. The pair traverse McDonald’s career from her current project, The Ricks…
…
continue reading
Subscriber-Only: Today's episode is available only to subscribers. If you are a Point-Free subscriber you can access your private podcast feed by visiting https://www.pointfree.co/account.---While we rebuilt SwiftUI bindings in UIKit to power state-driven navigation, that's not all SwiftUI uses them for! Let's see what it takes to power `UIControl`…
…
continue reading
1
[QA] CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis
8:19
8:19
Play later
Play later
Lists
Like
Liked
8:19
This study presents Chain-of-Diagnosis (CoD) to enhance interpretability in LLM-based medical diagnostics, enabling transparent reasoning and improved performance in diagnosing 9,604 diseases with DiagnosisGPT. https://arxiv.org/abs//2407.13301 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts…
…
continue reading
1
CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis
23:15
23:15
Play later
Play later
Lists
Like
Liked
23:15
This study presents Chain-of-Diagnosis (CoD) to enhance interpretability in LLM-based medical diagnostics, enabling transparent reasoning and improved performance in diagnosing 9,604 diseases with DiagnosisGPT. https://arxiv.org/abs//2407.13301 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts…
…
continue reading
1
[QA] Recursive Introspection: Teaching Language Model Agents How to Self-Improve
7:44
7:44
Play later
Play later
Lists
Like
Liked
7:44
https://arxiv.org/abs//2407.18219 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…
…
continue reading
1
Recursive Introspection: Teaching Language Model Agents How to Self-Improve
39:01
39:01
Play later
Play later
Lists
Like
Liked
39:01
https://arxiv.org/abs//2407.18219 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…
…
continue reading
1
[QA] Course-Correction: Safety Alignment Using Synthetic Preferences
7:24
7:24
Play later
Play later
Lists
Like
Liked
7:24
This paper evaluates and enhances large language models' ability to autonomously correct harmful content, introducing the C-EVAL benchmark and a synthetic dataset for effective preference learning. https://arxiv.org/abs//2407.16637 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://pod…
…
continue reading
1
Course-Correction: Safety Alignment Using Synthetic Preferences
20:57
20:57
Play later
Play later
Lists
Like
Liked
20:57
This paper evaluates and enhances large language models' ability to autonomously correct harmful content, introducing the C-EVAL benchmark and a synthetic dataset for effective preference learning. https://arxiv.org/abs//2407.16637 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://pod…
…
continue reading
1
[QA] Solving The Travelling Salesman Problem Using A Single Qubit
8:03
8:03
Play later
Play later
Lists
Like
Liked
8:03
This paper presents a resource-efficient quantum algorithm for solving the travelling salesman problem using a single qubit, achieving optimal solutions for small city samples with potential polynomial speed-up. https://arxiv.org/abs//2407.17207 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcast…
…
continue reading
1
Solving The Travelling Salesman Problem Using A Single Qubit
21:52
21:52
Play later
Play later
Lists
Like
Liked
21:52
This paper presents a resource-efficient quantum algorithm for solving the travelling salesman problem using a single qubit, achieving optimal solutions for small city samples with potential polynomial speed-up. https://arxiv.org/abs//2407.17207 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcast…
…
continue reading
1
[QA] Exploring Scaling Trends in LLM Robustness
7:35
7:35
Play later
Play later
Lists
Like
Liked
7:35
Larger language models show improved responses to adversarial training, but scaling alone does not enhance robustness against adversarial prompts without explicit defenses. https://arxiv.org/abs//2407.18213 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcas…
…
continue reading
1
Exploring Scaling Trends in LLM Robustness
16:03
16:03
Play later
Play later
Lists
Like
Liked
16:03
Larger language models show improved responses to adversarial training, but scaling alone does not enhance robustness against adversarial prompts without explicit defenses. https://arxiv.org/abs//2407.18213 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcas…
…
continue reading
Eric gives Marty a good explanation of home/office WiFi and things you should consider when setting up your system.
…
continue reading
This paper presents VILA, a visual language model that enhances data quality and performance through self-augmentation and specialist-augmentation, achieving state-of-the-art results on various tasks. https://arxiv.org/abs//2407.17453 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://…
…
continue reading
This paper presents VILA, a visual language model that enhances data quality and performance through self-augmentation and specialist-augmentation, achieving state-of-the-art results on various tasks. https://arxiv.org/abs//2407.17453 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://…
…
continue reading
1
[QA] OpenDevin: An Open Platform for AI Software Developers as Generalist Agents
7:17
7:17
Play later
Play later
Lists
Like
Liked
7:17
OpenDevin is a platform for developing AI agents that write code, interact with command lines, and browse the web, evaluated on 15 challenging tasks, fostering community contributions. https://arxiv.org/abs//2407.16741 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.c…
…
continue reading
1
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents
31:22
31:22
Play later
Play later
Lists
Like
Liked
31:22
OpenDevin is a platform for developing AI agents that write code, interact with command lines, and browse the web, evaluated on 15 challenging tasks, fostering community contributions. https://arxiv.org/abs//2407.16741 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.c…
…
continue reading
How do AI agents fit into a strategy for increasing a business' longevity? Imagine having a conversational operating system for your organization that was always learning. The advanced orchestration of AI agents can create a broader technology ecosystem that sets a trajectory for organizational AGI. Whereas artificial general intelligence, or AGI, …
…
continue reading
1
CCT 161: Practice CISSP Questions - Understanding Key Cybersecurity Legislation and Career Coaching Insight
14:19
14:19
Play later
Play later
Lists
Like
Liked
14:19
Send us a Text Message. Ever wondered what the GDPR and the Economic Espionage Act of 1996 have in common? On this episode of CISSP Cyber Training Podcast, I break down the complexities of essential cybersecurity legislation, both in the U.S. and Europe. We'll uncover what you need to know about the Identity Theft and Assumption Deterrence Act, the…
…
continue reading
1
[QA] MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences
7:30
7:30
Play later
Play later
Lists
Like
Liked
7:30
MovieDreamer is a novel framework combining autoregressive models and diffusion rendering for generating long-duration videos with complex narratives, high visual fidelity, and enhanced character consistency. https://arxiv.org/abs//2407.16655 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: …
…
continue reading
1
MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences
24:34
24:34
Play later
Play later
Lists
Like
Liked
24:34
MovieDreamer is a novel framework combining autoregressive models and diffusion rendering for generating long-duration videos with complex narratives, high visual fidelity, and enhanced character consistency. https://arxiv.org/abs//2407.16655 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: …
…
continue reading
This paper compares KAN and MLP models across various tasks, finding MLP generally outperforms KAN, except in symbolic formula representation, where B-spline activation enhances performance. https://arxiv.org/abs//2407.16674 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.a…
…
continue reading
This paper compares KAN and MLP models across various tasks, finding MLP generally outperforms KAN, except in symbolic formula representation, where B-spline activation enhances performance. https://arxiv.org/abs//2407.16674 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.a…
…
continue reading
1
[QA] Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning
8:25
8:25
Play later
Play later
Lists
Like
Liked
8:25
https://arxiv.org/abs//2407.15762 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…
…
continue reading
1
Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning
31:53
31:53
Play later
Play later
Lists
Like
Liked
31:53
https://arxiv.org/abs//2407.15762 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…
…
continue reading
1
[QA] BOND: Aligning LLMs with Best-of-N Distillation
7:24
7:24
Play later
Play later
Lists
Like
Liked
7:24
https://arxiv.org/abs//2407.14622 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…
…
continue reading
1
BOND: Aligning LLMs with Best-of-N Distillation
25:45
25:45
Play later
Play later
Lists
Like
Liked
25:45
https://arxiv.org/abs//2407.14622 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…
…
continue reading
1
[QA] Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
7:09
7:09
Play later
Play later
Lists
Like
Liked
7:09
https://arxiv.org/abs//2407.14435 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…
…
continue reading
1
Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
28:06
28:06
Play later
Play later
Lists
Like
Liked
28:06
https://arxiv.org/abs//2407.14435 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…
…
continue reading
1
[QA] LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
7:25
7:25
Play later
Play later
Lists
Like
Liked
7:25
LazyLLM accelerates transformer-based language model inference by dynamically selecting essential tokens for KV cache computation, improving generation speed without fine-tuning while maintaining accuracy across various tasks. https://arxiv.org/abs//2407.14057 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_paper…
…
continue reading
1
LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
23:05
23:05
Play later
Play later
Lists
Like
Liked
23:05
LazyLLM accelerates transformer-based language model inference by dynamically selecting essential tokens for KV cache computation, improving generation speed without fine-tuning while maintaining accuracy across various tasks. https://arxiv.org/abs//2407.14057 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_paper…
…
continue reading
Subscriber-Only: Today's episode is available only to subscribers. If you are a Point-Free subscriber you can access your private podcast feed by visiting https://www.pointfree.co/account.---We round out our stack navigation tools with support for an `@Environment`-like feature for holding onto the stack's path, a `NavigationLink`-like feature for …
…
continue reading
1
[QA] Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies
8:22
8:22
Play later
Play later
Lists
Like
Liked
8:22
This study highlights the importance of vocabulary size in scaling large language models, proposing optimal sizes that enhance performance, particularly for models like Llama2-70B. https://arxiv.org/abs//2407.13623 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/u…
…
continue reading