))
Neuroscience and artificial intelligence work better together. Brain inspired is a celebration and exploration of the ideas driving our progress to understand intelligence. I interview experts about their work at the interface of neuroscience, artificial intelligence, cognitive science, philosophy, psychology, and more: the symbiosis of these overlapping fields, how they inform each other, where they differ, what the past brought us, and what the future brings. Topics include computational n ...
…
continue reading
Paradromics Founder and CEO Matt Angle hosts an informal salon with some of the most influential figures in neurotechnology.
…
continue reading
Making artificial intelligence practical, productive & accessible to everyone. Practical AI is a show in which technology professionals, business people, students, enthusiasts, and expert guests engage in lively discussions about Artificial Intelligence and related topics (Machine Learning, Deep Learning, Neural Networks, GANs, MLOps, AIOps, LLMs & more). The focus is on productive implementations and real-world scenarios that are accessible to everyone. If you want to keep up with the lates ...
…
continue reading
1
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Sam Charrington
Machine learning and artificial intelligence are dramatically changing the way businesses operate and people live. The TWIML AI Podcast brings the top minds and ideas from the world of ML and AI to a broad and influential community of ML/AI researchers, data scientists, engineers and tech-savvy business and IT leaders. Hosted by Sam Charrington, a sought after industry analyst, speaker, commentator and thought leader. Technologies covered include machine learning, artificial intelligence, de ...
…
continue reading
Join us as we train our neural nets on the theme of the century: AI. Sonya Huang, Pat Grady and more Sequoia Capital partners host conversations with leading AI builders and researchers to ask critical questions and develop a deeper understanding of the evolving technologies—and their implications for technology, business and society. The content of this podcast does not constitute investment advice, an offer to provide investment advisory services, or an offer to sell or solicitation of an ...
…
continue reading
Getting beyond algorithms, petabytes, and neural nets, Data Difference covers softer side of data science that matters to executives, ata scientists, and organizations looking to capture full value of data and analytics.
…
continue reading
Welcome to Data Today with Dan Klein, a podcast from Zühlke. We're living in a world of opportunities. But to fully realise them, we have to reshape the way we innovate. We need to stop siloing data, ring-fencing knowledge, and thinking in traditional value chains. That's what this podcast is about. Every two weeks, we take a look at data outside the box. Join us to learn how inspiring individuals from diverse fields and industries are transforming the way they work with data to realise thei ...
…
continue reading
"The AI Canvas" delves into the remarkable potential of generative AI, and how it is impacting businesses and the arts in profound ways. Immerse yourself in enlightening fireside chats, captivating case studies, and revolutionary ideas as we unveil how AI is transforming industries, optimising operations, and redefining the creative realm with limitless possibilities.
…
continue reading
Linear Digressions is a podcast about machine learning and data science. Machine learning is being used to solve a ton of interesting problems, and to accomplish goals that were out of reach even a few short years ago.
…
continue reading
The O'Reilly Data Show Podcast explores the opportunities and techniques driving big data, data science, and AI.
…
continue reading
Are you a researcher or data scientist / analyst / ninja? Do you want to learn Bayesian inference, stay up to date or simply want to understand what Bayesian inference is? Then this podcast is for you! You'll hear from researchers and practitioners of all fields about how they use Bayesian statistics, and how in turn YOU can apply these methods in your modeling workflow. When I started learning Bayesian methods, I really wished there were a podcast out there that could introduce me to the me ...
…
continue reading
When will the world create an artificial intelligence that matches human level capabilities, better known as an artificial general intelligence (AGI)? What will that world look like & how can we ensure it's positive & beneficial for humanity as a whole? Tech entrepreneur & software engineer Soroush Pour (@soroushjp) sits down with AI experts to discuss AGI timelines, pathways, implications, opportunities & risks as we enter this pivotal new era for our planet and species. Hosted by Soroush P ...
…
continue reading
A monthly podcast where we discuss recent research and developments in the world of Neural Search, LLMs, RAG and Natural Language Processing with our co-hosts Jakub Zavrel (AI veteran and founder at Zeta Alpha) and Dinos Papakostas (AI Researcher at Zeta Alpha).
…
continue reading
Stories gives meaning to our life. Story can be in form of words on paper or moving pictures on screen. Story can be in form of photo realistic video games or just sound in the ears. In my opinion, storytelling is the quintessential human thing. So, naturally I am attempting to teach a computer how to write stories. No, it's not Neural Network data driven magic and all that boring stuff. It's simple rule based abstract simulation that goes back and forth between macro and micro level underst ...
…
continue reading
Beyond the Prompt dives deep into the world of AI and its expanding impact on business and daily work. Hosted by Jeremy Utley of Stanford's d.school, alongside Henrik Werdelin, an entrepreneur known for starting BarkBox, prehype and other startups, each episode features conversations with innovators and leaders to uncover pragmatic stories of how organizations leverage AI to accelerate success. Learn creative strategies and actionable tactics you can apply right away as AI capabilities advan ...
…
continue reading
One person, one interview, one story. Join us as we explore the impact of AI on our world, one amazing person at a time -- from the wildlife biologist tracking endangered rhinos across the savannah here on Earth to astrophysicists analyzing 10 billion-year-old starlight in distant galaxies to the Walmart data scientist grappling with the hundreds of millions of parameters lurking in the retailer’s supply chain. Every two weeks, we’ll bring you another tale, another 25-minute interview, as we ...
…
continue reading
In this podcast we talk about data science and related topics
…
continue reading
The podcast for uncommon weird Artificial Intelligence applications and news.
…
continue reading
Exploring the people, the science and the challenges in neuroscience.
…
continue reading
Welcome to the DataCafé: a special-interest Data Science podcast with Dr Jason Byrne and Dr Jeremy Bradley, interviewing leading data science researchers and domain experts in all things business, stats, maths, science and tech.
…
continue reading
Too long didn’t read, brought to you by The Alan Turing Institute, the national institute for data science and AI. The monthly podcast that reads the week’s big AI stories so you don’t have to. With new developments in artificial intelligence happening at lightning speed, it can be hard to keep up. That’s where too long didn’t read comes in. We know you’re busy, so we’ll get right to the main points on how breakthroughs in machine learning, neural networks, and other AI systems could impact ...
…
continue reading
A4N — the Artificial Neural Network News Network — is a lighthearted podcast covering the latest developments in artificial intelligence, machine learning, and data science, in which we both introduce technical aspects of these advances, as well as their social implications. The intended audience is anyone interested in automation, A.I., or the future, with brief sections catering especially to professionals working in the fields of data science or software engineering.
…
continue reading
Technical discussions with deep learning researchers who study how to build intelligence. Made for researchers, by researchers.
…
continue reading
Step into the future, one day at a time, with Atometrix ByteSize! Your indispensable daily dose of the latest and greatest in AI, low-code, and all things tech. Each day, we whisk you through the most exciting updates, providing not just news, but insights, thought-provoking analysis, and of course, a sprinkle of humor. Every episode is a journey through the frontier of technology, exploring new developments in AI, the rapid evolution of low-code platforms, and the very tools that are rewrit ...
…
continue reading
CSIAC's Mission Mission Statement CSIAC is chartered to leverage the best practices and expertise from government, industry, and academia in order to promote technology domain awareness and solve the most critically challenging scientific and technical problems in the following areas: Cybersecurity and Information Assurance, Software Engineering, Modeling and Simulation, and Knowledge Management/Information Sharing.
…
continue reading
O'Reilly Media spreads the knowledge of innovators. At O’Reilly, a big part of our business is paying attention to what’s new and interesting in the world of technology. We have a pretty good record at having anticipated some of the big technology developments in recent history. For instance, we launched the first commercial Web site, GNN, in 1993; we organized the meeting at which the term “open source” was first adopted; we were early investors in Blogger, which helped launch the blogging ...
…
continue reading
EE Times Current provides a deep dive into the most compelling stories in the electronics industry. Tune in to keep yourself current on what matters to design engineers and other tech industry professionals
…
continue reading
Welcome to "The AI Chronicles", the podcast that takes you on a journey into the fascinating world of Artificial Intelligence (AI), AGI, GPT-5, GPT-4, Deep Learning, and Machine Learning. In this era of rapid technological advancement, AI has emerged as a transformative force, revolutionizing industries and shaping the way we interact with technology. I'm your host, GPT-5, and I invite you to join me as we delve into the cutting-edge developments, breakthroughs, and ethical implications of A ...
…
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
Why isn't talking tech as simple, quick, and agile as its innovations promise to be? Technology Untangled is just that - a show that deciphers tech's rapid evolutions with one simple question in mind: what's really going to shape our future (and what's going to end up in the bargain bin with the floppy disc)? Join your host Michael Bird as he untangles innovation through a series of interviews, stories, and analyses with some of the industry's brightest brains. No marketing speak, no unneces ...
…
continue reading
Exploring tools and approaches that make us more effective engineers and make our systems safe and reliable. Join us for discussions on recent developments in topics such as best practices in reliability and security, applied formal methods, encryption, and safe and secure hardware.
…
continue reading
Minhaaj Podcast are Candid Conversations with Some of the Most Intelligent People. From Forbes and WSJ contributors, inventors, wall street bankers, Fintech experts, memory champions, neuroscientists, psychology veterans, FAANG employees and Youtube Educators, i have had the distinct pleasure to learn from these luminaries, for which i shall remain thankful, forever.
…
continue reading
Each episode of The Thesis Review is a conversation centered around a researcher's PhD thesis, giving insight into their history, revisiting older ideas, and providing a valuable perspective on how their research has evolved (or stayed the same) since.
…
continue reading
Understand what CQM Meditations are and how they help us access a new sense of self that, with work and practice help us access change in reality. Discover the healing power of Contemplative Intelligence Meditations or CQM’s as we call them for short. We have learned a lot over the last decades about the science of getting well. The more we learned and observed about healing the clearer the model became to us. We started to understand the similarities of depression to addiction and generalis ...
…
continue reading
1
[QA] LLM Pruning and Distillation in Practice: The Minitron Approach
7:23
7:23
Play later
Play later
Lists
Like
Liked
7:23
https://arxiv.org/abs//2408.11796 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
LLM Pruning and Distillation in Practice: The Minitron Approach
12:36
12:36
Play later
Play later
Lists
Like
Liked
12:36
https://arxiv.org/abs//2408.11796 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] Approaching Deep Learning through the Spectral Dynamics of Weights
7:26
7:26
Play later
Play later
Lists
Like
Liked
7:26
This paper explores spectral dynamics of weights in deep learning, revealing optimization biases, enhancing weight decay effects, and distinguishing between memorizing and generalizing networks across various tasks. https://arxiv.org/abs//2408.11804 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Pod…
…
continue reading
1
Approaching Deep Learning through the Spectral Dynamics of Weights
26:45
26:45
Play later
Play later
Lists
Like
Liked
26:45
This paper explores spectral dynamics of weights in deep learning, revealing optimization biases, enhancing weight decay effects, and distinguishing between memorizing and generalizing networks across various tasks. https://arxiv.org/abs//2408.11804 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Pod…
…
continue reading
1
NetBeans: A Comprehensive Integrated Development Environment
4:23
4:23
Play later
Play later
Lists
Like
Liked
4:23
NetBeans is a powerful, open-source integrated development environment (IDE) used by developers to create applications in various programming languages. Initially developed by Sun Microsystems and now maintained by the Apache Software Foundation, NetBeans provides a robust platform for building desktop, web, and mobile applications. It supports a w…
…
continue reading
1
Snowflake's Baris Gultekin on Unlocking the Value of Data With Large Language Models - Ep. 231
32:10
32:10
Play later
Play later
Lists
Like
Liked
32:10
Snowflake is using AI to help enterprises transform data into insights and applications. In this episode of NVIDIA’s AI Podcast, host Noah Kravitz and Baris Gultekin, head of AI at Snowflake, discuss how the company’s AI Data Cloud platform enables customers to access and manage data at scale. By separating the storage of data from compute, Snowfla…
…
continue reading
1
[QA] Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
8:04
8:04
Play later
Play later
Lists
Like
Liked
8:04
The paper challenges the Linear Representation Hypothesis, showing that gated recurrent neural networks encode token sequences using magnitude rather than direction, suggesting broader interpretability in neural network research. https://arxiv.org/abs//2408.10920 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_pa…
…
continue reading
1
Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
21:03
21:03
Play later
Play later
Lists
Like
Liked
21:03
The paper challenges the Linear Representation Hypothesis, showing that gated recurrent neural networks encode token sequences using magnitude rather than direction, suggesting broader interpretability in neural network research. https://arxiv.org/abs//2408.10920 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_pa…
…
continue reading
1
[QA] Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
7:53
7:53
Play later
Play later
Lists
Like
Liked
7:53
Transfusion is a multi-modal training method combining language modeling and diffusion, achieving superior performance in generating images and text with models up to 7B parameters. https://arxiv.org/abs//2408.11039 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/…
…
continue reading
1
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
24:23
24:23
Play later
Play later
Lists
Like
Liked
24:23
Transfusion is a multi-modal training method combining language modeling and diffusion, achieving superior performance in generating images and text with models up to 7B parameters. https://arxiv.org/abs//2408.11039 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/…
…
continue reading
1
Area Under the Curve (AUC): A Comprehensive Metric for Evaluating Classifier Performance
5:24
5:24
Play later
Play later
Lists
Like
Liked
5:24
The Area Under the Curve (AUC) is a widely used metric in the evaluation of binary classification models. It provides a single scalar value that summarizes the performance of a classifier across all possible threshold values, offering a clear and intuitive measure of how well the model distinguishes between positive and negative classes. The AUC is…
…
continue reading
1
Phaidra’s Jim Gao on Building the Fourth Industrial Revolution with Reinforcement Learning
50:33
50:33
Play later
Play later
Lists
Like
Liked
50:33
After AlphaGo beat Lee Sedol, a young mechanical engineer at Google thought of another game reinforcement learning could win: energy optimization at data centers. Jim Gao convinced his bosses at the Google data center team to let him work with the DeepMind team to try. The initial pilot resulted in a 40% energy savings and led he and his co-founder…
…
continue reading
1
[QA] Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
8:37
8:37
Play later
Play later
Lists
Like
Liked
8:37
The paper presents MOHAWK, a method for distilling Transformers into state space models, achieving strong performance with significantly less training data and computational resources. https://arxiv.org/abs//2408.10189 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.c…
…
continue reading
1
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
31:52
31:52
Play later
Play later
Lists
Like
Liked
31:52
The paper presents MOHAWK, a method for distilling Transformers into state space models, achieving strong performance with significantly less training data and computational resources. https://arxiv.org/abs//2408.10189 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.c…
…
continue reading
1
Non-Negative Matrix Factorization (NMF): Uncovering Hidden Patterns in Data
7:43
7:43
Play later
Play later
Lists
Like
Liked
7:43
Non-Negative Matrix Factorization (NMF) is a powerful technique in the field of data analysis and machine learning used to reduce the dimensionality of data and uncover hidden patterns. Unlike other matrix factorization methods, NMF imposes the constraint that the matrix elements must be non-negative. This constraint makes NMF particularly useful f…
…
continue reading
1
The Building Blocks of Agentic Systems with Harrison Chase - #698
59:17
59:17
Play later
Play later
Lists
Like
Liked
59:17
Today, we're joined by Harrison Chase, co-founder and CEO of LangChain to discuss LLM frameworks, agentic systems, RAG, evaluation, and more. We dig into the elements of a modern LLM framework, including the most productive developer experiences and appropriate levels of abstraction. We dive into agents and agentic systems as well, covering the “sp…
…
continue reading
1
[QA] JPEG-LM: LLMs as Image Generators with Canonical Codec Representations
7:47
7:47
Play later
Play later
Lists
Like
Liked
7:47
This paper proposes using canonical codecs for image and video generation in autoregressive models, demonstrating improved efficiency and effectiveness over traditional pixel-based and vector quantization methods. https://arxiv.org/abs//2408.08459 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podca…
…
continue reading
1
JPEG-LM: LLMs as Image Generators with Canonical Codec Representations
20:04
20:04
Play later
Play later
Lists
Like
Liked
20:04
This paper proposes using canonical codecs for image and video generation in autoregressive models, demonstrating improved efficiency and effectiveness over traditional pixel-based and vector quantization methods. https://arxiv.org/abs//2408.08459 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podca…
…
continue reading
1
[QA] TextCAVs: Debugging vision models using text
7:19
7:19
Play later
Play later
Lists
Like
Liked
7:19
TextCAVs is a novel method for generating concept activation vectors using text descriptions, reducing the need for labeled image data in deep learning model interpretability, particularly in medical applications. https://arxiv.org/abs//2408.08652 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podca…
…
continue reading
1
TextCAVs: Debugging vision models using text
9:33
9:33
Play later
Play later
Lists
Like
Liked
9:33
TextCAVs is a novel method for generating concept activation vectors using text descriptions, reducing the need for labeled image data in deep learning model interpretability, particularly in medical applications. https://arxiv.org/abs//2408.08652 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podca…
…
continue reading
1
Signal Detection Theory (SDT): Understanding Decision-Making in the Presence of Uncertainty
4:51
4:51
Play later
Play later
Lists
Like
Liked
4:51
Signal Detection Theory (SDT) is a framework used to analyze and understand decision-making processes in situations where there is uncertainty. Originating in the fields of radar and telecommunications during World War II, SDT has since been applied across various domains, including psychology, neuroscience, medical diagnostics, and market research…
…
continue reading
1
[QA] Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
9:08
9:08
Play later
Play later
Lists
Like
Liked
9:08
The paper presents rStar, a self-play mutual reasoning method that enhances small language models' reasoning abilities without fine-tuning, achieving significant accuracy improvements across various reasoning tasks. https://arxiv.org/abs//2408.06195 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Pod…
…
continue reading
1
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
16:46
16:46
Play later
Play later
Lists
Like
Liked
16:46
The paper presents rStar, a self-play mutual reasoning method that enhances small language models' reasoning abilities without fine-tuning, achieving significant accuracy improvements across various reasoning tasks. https://arxiv.org/abs//2408.06195 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Pod…
…
continue reading
1
AngularJS: Revolutionizing Web Development with Dynamic Applications
5:57
5:57
Play later
Play later
Lists
Like
Liked
5:57
AngularJS is a powerful JavaScript-based open-source front-end web framework developed by Google. Introduced in 2010, AngularJS was designed to simplify the development and testing of single-page applications (SPAs) by providing a robust framework for client-side model–view–controller (MVC) architecture. It has significantly transformed the way dev…
…
continue reading
1
[QA] Towards flexible perception with visual memory
7:18
7:18
Play later
Play later
Lists
Like
Liked
7:18
https://arxiv.org/abs//2408.08172 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
Towards flexible perception with visual memory
17:09
17:09
Play later
Play later
Lists
Like
Liked
17:09
https://arxiv.org/abs//2408.08172 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] I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm
7:45
7:45
Play later
Play later
Lists
Like
Liked
7:45
The paper introduces I-SHEEP, a continuous self-alignment paradigm for LLMs, significantly improving performance on various benchmarks compared to traditional one-time alignment methods. https://arxiv.org/abs//2408.08072 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple…
…
continue reading
1
I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm
17:47
17:47
Play later
Play later
Lists
Like
Liked
17:47
The paper introduces I-SHEEP, a continuous self-alignment paradigm for LLMs, significantly improving performance on various benchmarks compared to traditional one-time alignment methods. https://arxiv.org/abs//2408.08072 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple…
…
continue reading
1
Expectation-Maximization Algorithm (EM): A Powerful Tool for Data Analysis
4:24
4:24
Play later
Play later
Lists
Like
Liked
4:24
The Expectation-Maximization (EM) algorithm is a widely-used statistical technique for finding maximum likelihood estimates in the presence of latent variables. Developed by Arthur Dempster, Nan Laird, and Donald Rubin in 1977, the EM algorithm provides an iterative method to handle incomplete data or missing values, making it a cornerstone in fiel…
…
continue reading
1
Using LLMs in Information Retrieval (w/ Ronak Pradeep)
22:15
22:15
Play later
Play later
Lists
Like
Liked
22:15
In this episode of Neural Search Talks, we're chatting with Ronak Pradeep, a PhD student from the University of Waterloo, about his experience using LLMs in Information Retrieval, both as a backbone of ranking systems and for their end-to-end evaluation. Ronak analyzes the impact of the advancements in language models on the way we think about IR s…
…
continue reading
1
[QA] BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
7:43
7:43
Play later
Play later
Lists
Like
Liked
7:43
BAM enhances Mixture of Experts by fully utilizing dense model parameters, improving efficiency and performance in large language models, surpassing baselines in perplexity and downstream tasks. https://arxiv.org/abs//2408.08274 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcas…
…
continue reading
1
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
20:07
20:07
Play later
Play later
Lists
Like
Liked
20:07
BAM enhances Mixture of Experts by fully utilizing dense model parameters, improving efficiency and performance in large language models, surpassing baselines in perplexity and downstream tasks. https://arxiv.org/abs//2408.08274 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcas…
…
continue reading
1
[QA] Can Large Language Models Understand Symbolic Graphics Programs?
7:14
7:14
Play later
Play later
Lists
Like
Liked
7:14
This paper evaluates large language models' understanding of symbolic graphics programs, introducing a benchmark and a method, Symbolic Instruction Tuning, to enhance their visual reasoning capabilities. https://arxiv.org/abs//2408.08313 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https…
…
continue reading
1
Can Large Language Models Understand Symbolic Graphics Programs?
23:48
23:48
Play later
Play later
Lists
Like
Liked
23:48
This paper evaluates large language models' understanding of symbolic graphics programs, introducing a benchmark and a method, Symbolic Instruction Tuning, to enhance their visual reasoning capabilities. https://arxiv.org/abs//2408.08313 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https…
…
continue reading
1
Kotlin: A Modern Programming Language for the JVM and Beyond
7:05
7:05
Play later
Play later
Lists
Like
Liked
7:05
Kotlin is a contemporary programming language developed by JetBrains, designed to be fully interoperable with Java while offering a more concise and expressive syntax. Introduced in 2011 and officially released in 2016, Kotlin has rapidly gained popularity among developers for its modern features, safety enhancements, and seamless integration with …
…
continue reading
1
BI 191 Damian Kelty-Stephen: Fractal Turbulent Cascading Intelligence
1:27:51
1:27:51
Play later
Play later
Lists
Like
Liked
1:27:51
Support the show to get full episodes and join the Discord community. Damian Kelty-Stephen is an experimental psychologist at State University of New York at New Paltz. Last episode with Luis Favela, we discussed many of the ideas from ecological psychology, and how Louie is trying to reconcile those principles with those of neuroscience. In this e…
…
continue reading
1
[QA] Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
7:55
7:55
Play later
Play later
Lists
Like
Liked
7:55
This paper presents a Monte-Carlo Tree Search approach to enhance LLMs' performance in multi-step reasoning tasks, achieving significant improvements in web navigation and decision-making capabilities. https://arxiv.org/abs//2408.07199 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https:/…
…
continue reading
1
Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
29:15
29:15
Play later
Play later
Lists
Like
Liked
29:15
This paper presents a Monte-Carlo Tree Search approach to enhance LLMs' performance in multi-step reasoning tasks, achieving significant improvements in web navigation and decision-making capabilities. https://arxiv.org/abs//2408.07199 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https:/…
…
continue reading
This paper presents a framework for creating desired images by compositing user-selected parts from generated images, enhancing flexibility and quality in image generation through a novel blending technique. https://arxiv.org/abs//2408.07116 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: h…
…
continue reading
This paper presents a framework for creating desired images by compositing user-selected parts from generated images, enhancing flexibility and quality in image generation through a novel blending technique. https://arxiv.org/abs//2408.07116 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: h…
…
continue reading
1
Dynamic Topic Models (DTM): Capturing the Evolution of Themes Over Time
5:00
5:00
Play later
Play later
Lists
Like
Liked
5:00
Dynamic Topic Models (DTM) are an advanced extension of topic modeling techniques designed to analyze and understand how topics in a collection of documents evolve over time. Developed to address the limitations of static topic models like Latent Dirichlet Allocation (LDA), DTMs allow researchers and analysts to track the progression and transforma…
…
continue reading
You might have heard that “AI is only as good as the data.” What does that mean and what data are we talking about? Chris and Daniel dig into that topic in the episode exploring the categories of data that you might encounter working in AI (for training, testing, fine-tuning, benchmarks, etc.). They also discuss the latest developments in AI regula…
…
continue reading
1
[QA] Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models
7:26
7:26
Play later
Play later
Lists
Like
Liked
7:26
The paper identifies "semantic leakage" in language models, revealing how irrelevant prompt information influences outputs, and proposes methods for detection and evaluation across multiple languages and scenarios. https://arxiv.org/abs//2408.06518 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podc…
…
continue reading
1
Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models
16:13
16:13
Play later
Play later
Lists
Like
Liked
16:13
The paper identifies "semantic leakage" in language models, revealing how irrelevant prompt information influences outputs, and proposes methods for detection and evaluation across multiple languages and scenarios. https://arxiv.org/abs//2408.06518 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podc…
…
continue reading
1
[QA] Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction
8:28
8:28
Play later
Play later
Lists
Like
Liked
8:28
The Learned Ranking Function (LRF) optimizes recommendations for long-term user satisfaction using short-term behavior predictions, employing a novel constraint optimization algorithm, and is tested on YouTube. https://arxiv.org/abs//2408.06512 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts…
…
continue reading
1
Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction
15:10
15:10
Play later
Play later
Lists
Like
Liked
15:10
The Learned Ranking Function (LRF) optimizes recommendations for long-term user satisfaction using short-term behavior predictions, employing a novel constraint optimization algorithm, and is tested on YouTube. https://arxiv.org/abs//2408.06512 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts…
…
continue reading
1
False Positive Rate (FPR): A Critical Metric for Evaluating Classification Accuracy
6:14
6:14
Play later
Play later
Lists
Like
Liked
6:14
The False Positive Rate (FPR) is a crucial metric used to evaluate the performance of binary classification models. It measures the proportion of negative instances that are incorrectly classified as positive by the model. Understanding FPR is essential for assessing how well a model distinguishes between classes, particularly in applications where…
…
continue reading
1
[QA] The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
8:34
8:34
Play later
Play later
Lists
Like
Liked
8:34
The paper introduces THE AI SCIENTIST, a framework enabling LLMs to autonomously conduct scientific research, generate ideas, write papers, and evaluate findings, significantly advancing scientific discovery and democratizing research. https://arxiv.org/abs//2408.06292 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@ar…
…
continue reading
1
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
30:36
30:36
Play later
Play later
Lists
Like
Liked
30:36
The paper introduces THE AI SCIENTIST, a framework enabling LLMs to autonomously conduct scientific research, generate ideas, write papers, and evaluate findings, significantly advancing scientific discovery and democratizing research. https://arxiv.org/abs//2408.06292 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@ar…
…
continue reading
