I love reading research papers, but often find myself with pockets of time when I can’t sit down and read. This podcast bridges that gap, offering bite-sized explorations of individual papers.
Note
The voices are AI-generated. Think of this as your research reading assistant - quick, consistent, and focused on the key points.
Latest Episodes
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Artificial Intelligence
Reinforcement Learning
Language Models
Reasoning
Supervised Fine-Tuning
Distillation
DeepSeek-V3: Advancements in Open-Source Large Language Models
Deep Learning
Natural Language Processing
Neural Networks
Machine Learning
Titans: Learning to Memorize at Test Time
Machine Learning
Artificial Intelligence
Neural Networks
Memory Modules
Transformer2: Self-Adaptive Large Language Models
Artificial Intelligence
Natural Language Processing
Deep Learning
Machine Learning
Adaptive Systems
Learning to Learn Optimization Algorithms with LSTM Networks
Machine Learning
Meta-Learning
Optimization Algorithms
Recurrent Neural Networks
Trust Region Policy Optimization
Reinforcement Learning
Policy Optimization
Trust Region Methods
Artificial Intelligence
Efficient Deep Learning Parallelization using SOAP Search Space and FlexFlow Framework
Deep Learning
Parallelization
Distributed Computing
Neural Networks
Optimization
Deep Retrieval: Learning Efficient Structures for Large-Scale Recommendation Systems
Machine Learning
Recommendation Systems
Information Retrieval
Deep Learning
Scaling User Modeling for Personalized Advertising at Meta
Personalized Advertising
User Modeling
Deep Learning
Neural Networks
LiNR: Revolutionizing Large-Scale Retrieval for Recommendation Systems
Machine Learning
Information Retrieval
Recommender Systems
Deep Learning
GPU-based Systems
Comprehensive Guide to Real-Time Bidding (RTB): Challenges and Opportunities
Online Advertising
Real-Time Bidding
Digital Auctions
User Response Prediction
Bidding Strategies
Dynamic Pricing
Ad Fraud Detection
Efficient Inference for Large Language Models with LLM.int8()
Artificial Intelligence
Natural Language Processing
8-bit Quantization
Transformer Models
Enhancing Language Models with a Massive Datastore
Artificial Intelligence
Language Models
Data Retrieval
Natural Language Processing
In-Context Policy Iteration: Enhancing Reinforcement Learning with Large Language Models
Reinforcement Learning
Large Language Models
AI
Policy Iteration
Optimizing Quantization of Large Language Models for Efficiency and Accuracy
Machine Learning
Natural Language Processing
Quantization
Efficiency
Model Compression
AutoPruner: End-to-End Trainable Filter Pruning for Efficient Deep Neural Networks
Deep Learning
Neural Networks
Model Compression
SparseGPT: One-shot Pruning of Large Language Models
Artificial Intelligence
Natural Language Processing
Model Compression
Efficient Compression of Large Language Models using LLM-Pruner
Artificial Intelligence
Natural Language Processing
Model Compression
ScreenAgent: A Vision Language Model-driven Computer Control Agent
Artificial Intelligence
Computer Vision
Natural Language Processing
Artificial GUI Interaction
Supervised Pretraining for In-Context Reinforcement Learning with Transformers
Reinforcement Learning
Transformers
Meta-Learning
Deep Neural Networks
Decision-Pretrained Transformer: Bridging Supervised Learning and Reinforcement Learning
Reinforcement Learning
Transformer Models
Decision-Making
How Transformers Learn In-Context Beyond Simple Functions
Artificial Intelligence
Deep Learning
Transformers
In-Context Learning
Representation Learning
In-Context Learning Capabilities of Transformers
Machine Learning
Deep Learning
Transformer Models
In-Context Learning
Spider2-V: Automated Multimodal Agents for Data Science Workflows
Artificial Intelligence
Artificial GUI Interaction
Data Science
Generalization Patterns of Transformers in In-Weights Learning and In-Context Learning
Artificial Intelligence
Deep Learning
Machine Learning
Unmasking the Lottery Ticket Hypothesis
Deep Learning
Neural Networks
Network Pruning
Machine Learning
Rethinking Scale for In-Context Learning in Large Language Models
Natural Language Processing
Large Language Models
Transformer Architecture
In-Context Learning
Model Pruning
Ferret-UI: Multimodal Large Language Model for Mobile User Interface Understanding
Artificial Intelligence
Artificial GUI Interaction
Mobile Applications
Grounded SAM: A Novel Approach to Open-Set Segmentation
Computer Vision
Open-World Visual Perception
Segmentation Models
SAM 2: Segment Anything in Images and Videos
Computer Vision
Deep Learning
Video Segmentation
SAM 2
Visual Perception
RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning
Artificial Intelligence
Reinforcement Learning
Deep Learning
Evolutionary Optimization of Model Merging Recipes
Artificial Intelligence
Machine Learning
Natural Language Processing
Speculative Execution for Efficient Inference in Large Language Models on Consumer Devices
Artificial Intelligence
Large Language Models
Systems and Performance
In-context Learning and Induction Heads
Natural Language Processing
Deep Learning
Explainable AI
AI Safety
Geometric Properties of Data Representations in Deep Neural Networks
Deep Learning
Machine Learning
Explainable AI
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
3D Vision
Computer Vision
Deep Learning
Graph Isomorphism Networks: A Theoretical Framework and Architecture
Graph Neural Networks
Machine Learning
Deep Learning
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Deep Learning
Machine Learning
Optimization
Adding Conditional Control to Text-to-Image Diffusion Models
Generative Models
Computer Vision
Deep Learning
Multimodal AI
Segment Anything: A Paradigm Shift in Image Segmentation
Computer Vision
Deep Learning
Machine Learning
Learning Transferable Visual Models From Natural Language Supervision
Computer Vision
Natural Language Processing
Multimodal AI
Language Models are Few-Shot Learners
Natural Language Processing
Few-Shot/Meta-Learning
Deep Learning
Training Deep Reinforcement Learning Systems with Human Preferences
Reinforcement Learning
Deep Learning
AI Safety
Playing Atari with Deep Reinforcement Learning
Deep Learning
Reinforcement Learning
Artificial Intelligence
Single Path One-Shot (SPOS): Efficient Neural Architecture Search with Simplified Supernet
Deep Learning
Optimization
Machine Learning
Long-CLIP: Extending Text Length for Improved Vision-Language Modeling
Multimodal AI
Natural Language Processing
Computer Vision
𝑓VDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence
3D Vision
Deep Learning
Systems and Performance
Unraveling the Connection between In-Context Learning and Gradient Descent in Transformers
Natural Language Processing
Deep Learning
Explainable AI
Gradient Low-Rank Projection (GaLore): Revolutionizing Memory-Efficient LLM Training
Natural Language Processing
Optimization
Systems and Performance
Retrieval-Enhanced Transformers (RETRO): A Semi-Parametric Approach to Enhance Performance of Large Language Models
Natural Language Processing
Deep Learning
Systems and Performance
Foundation Models in Decision Making: Roles, Challenges, and Opportunities
Artificial Intelligence
Machine Learning
Explainable AI
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Deep Learning
Transformers
Systems and Performance
PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel
Systems and Performance
Deep Learning
Machine Learning
Hyper Networks: A Novel Approach to Learning Weights in Deep Neural Networks
Deep Learning
Machine Learning
Neural Networks
TiTok: A Transformer-based 1D Tokenization Approach for Image Generation
Generative Models
Computer Vision
Transformers
NerfBaselines: A Framework for Standardized Evaluation of Novel View Synthesis Methods in Computer Vision
3D Vision
Computer Vision
Systems and Performance
Survey on reinforcement learning in reccomender systems
Reinforcement Learning
Recommender Systems
Machine Learning
Training Large Language Models for Compiler Optimization
Natural Language Processing
Systems and Performance
AI for Science
Metadata-based Color Harmonization for Multi-camera Surround View Systems
Computer Vision
Autonomous Driving
Extrapolated View Synthesis for Urban Scene Reconstruction
3D Vision
Computer Vision
Generative Models
SafePathNet: Learning a Distribution of Trajectories for Safe and Comfortable Autonomous Driving
Autonomous Driving
AI Safety
Machine Learning
Unsupervised Occupancy Fields for Perception and Forecasting
Computer Vision
Machine Learning
Autonomous Driving
UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
Autonomous Driving
Deep Learning
Computer Vision
Robustness Evaluation of HD Map Constructors under Sensor Corruptions for Autonomous Driving
Autonomous Driving
Computer Vision
AI Safety
DriveVLM: Vision-Language Models for Autonomous Driving in Urban Environments
Autonomous Driving
Computer Vision
Multimodal AI
TransAct Transformer-based Realtime User Action Model for Recommendation at Pinterest
Recommender Systems
Transformers
Systems and Performance
ZeRO Memory Optimizations: Toward Training Trillion Parameter Models
Systems and Performance
Deep Learning
Natural Language Processing
A Better Match for Drivers and Riders Reinforcement Learning at Lyft
Reinforcement Learning
Recommender Systems
Machine Learning
No-Transaction Band Network A Neural Network Architecture for Efficient Deep Hedging
Deep Learning
AI for Science
Machine Learning
AutoEmb Automated Embedding Dimensionality Searchg in Streaming Recommendations
Deep Learning
Recommender Systems
Optimization
No matching items
About
- The voices you’ll hear are AI-generated, not real people (though names from papers might appear).
- While we strive for accuracy, these are complex topics. Our current AI systems aren’t perfect, so approach with a critical mind.
- Consider this a starting point. For deeper understanding, always refer to the original paper.
- The papers featured are ones I’m personally interested in or have been wanting to read. It’s a curated selection based on my interests.
This podcast aims to spark curiosity and make cutting-edge research more accessible. It’s perfect for those moments when you want to learn but can’t dive into a full paper.
Enjoy the exploration of ideas, and let it fuel your interest in further reading!
The (AI) Team
- Alex Askwell: Our curious and knowledgeable moderator, always ready with the right questions to guide our exploration.
- Dr. Paige Turner: Our lead researcher and paper expert, diving deep into the methods and results.
- Prof. Wyd Spectrum: Our field expert, providing broader context and critical insights.
Join them as they break down complex research into byte-sized breakthroughs!
Request a paper
If you have a paper you’d like to see discussed, please fill this form