Byte-Sized Breakthroughs Podcast

I love Arxiv, 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.

A few things to note:

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!

Listen everywhere

The 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!

Optimizing Quantization of Large Language Models for Efficiency and Accuracy

Aug 12, 2024

AutoPruner: End-to-End Trainable Filter Pruning for Efficient Deep Neural Networks

Aug 11, 2024

Decision-Pretrained Transformer: Bridging Supervised Learning and Reinforcement Learning

Aug 10, 2024

How Transformers Learn In-Context Beyond Simple Functions

Aug 10, 2024

In-Context Learning Capabilities of Transformers

Aug 10, 2024

Spider2-V: Automated Multimodal Agents for Data Science Workflows

Aug 10, 2024

Generalization Patterns of Transformers in In-Weights Learning and In-Context Learning

Aug 10, 2024

Unmasking the Lottery Ticket Hypothesis

Aug 9, 2024

Rethinking Scale for In-Context Learning in Large Language Models

Aug 9, 2024

Ferret-UI: Multimodal Large Language Model for Mobile User Interface Understanding

Aug 8, 2024

Grounded SAM: A Novel Approach to Open-Set Segmentation

Aug 8, 2024

SAM 2: Segment Anything in Images and Videos

Aug 6, 2024

RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning

Aug 5, 2024

Evolutionary Optimization of Model Merging Recipes

Aug 5, 2024

Exploring Weight Agnostic Neural Networks

Categories

Listen everywhere

The Team

Optimizing Quantization of Large Language Models for Efficiency and Accuracy

AutoPruner: End-to-End Trainable Filter Pruning for Efficient Deep Neural Networks

SparseGPT: One-shot Pruning of Large Language Models

Efficient Compression of Large Language Models using LLM-Pruner

ScreenAgent: A Vision Language Model-driven Computer Control Agent

Supervised Pretraining for In-Context Reinforcement Learning with Transformers

Decision-Pretrained Transformer: Bridging Supervised Learning and Reinforcement Learning

How Transformers Learn In-Context Beyond Simple Functions

In-Context Learning Capabilities of Transformers

Spider2-V: Automated Multimodal Agents for Data Science Workflows

Generalization Patterns of Transformers in In-Weights Learning and In-Context Learning

Unmasking the Lottery Ticket Hypothesis

Rethinking Scale for In-Context Learning in Large Language Models

Ferret-UI: Multimodal Large Language Model for Mobile User Interface Understanding

Grounded SAM: A Novel Approach to Open-Set Segmentation

SAM 2: Segment Anything in Images and Videos

RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning

Evolutionary Optimization of Model Merging Recipes

Exploring Weight Agnostic Neural Networks

Speculative Execution for Efficient Inference in Large Language Models on Consumer Devices

In-context Learning and Induction Heads

On the Measure of Intelligence

Geometric Properties of Data Representations in Deep Neural Networks

The Case for Learned Index Structures

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

Constitutional AI: Harmlessness from AI Feedback

Proximal Policy Optimization Algorithms

Graph Isomorphism Networks: A Theoretical Framework and Architecture

Rethinking the Value of Network Pruning

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

Adding Conditional Control to Text-to-Image Diffusion Models

Denoising Diffusion Probabilistic Models

Practical Research Problems in AI Safety

Segment Anything: A Paradigm Shift in Image Segmentation

Learning Transferable Visual Models From Natural Language Supervision

Language Models are Few-Shot Learners

Training Deep Reinforcement Learning Systems with Human Preferences

Playing Atari with Deep Reinforcement Learning

Single Path One-Shot (SPOS): Efficient Neural Architecture Search with Simplified Supernet

Long-CLIP: Extending Text Length for Improved Vision-Language Modeling

𝑓VDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence

Unraveling the Connection between In-Context Learning and Gradient Descent in Transformers

Gradient Low-Rank Projection (GaLore): Revolutionizing Memory-Efficient LLM Training

Retrieval-Enhanced Transformers (RETRO): A Semi-Parametric Approach to Enhance Performance of Large Language Models

Foundation Models in Decision Making: Roles, Challenges, and Opportunities

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel

Hyper Networks: A Novel Approach to Learning Weights in Deep Neural Networks

DARTS: Differentiable Architecture Search

TiTok: A Transformer-based 1D Tokenization Approach for Image Generation

NerfBaselines: A Framework for Standardized Evaluation of Novel View Synthesis Methods in Computer Vision

Survey on reinforcement learning in reccomender systems

Models tell you what to discard

Training Large Language Models for Compiler Optimization

Metadata-based Color Harmonization for Multi-camera Surround View Systems

Extrapolated View Synthesis for Urban Scene Reconstruction

Planning-Oriented Autonomous Driving

SafePathNet: Learning a Distribution of Trajectories for Safe and Comfortable Autonomous Driving

Unsupervised Occupancy Fields for Perception and Forecasting

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

RT-DETR: Real-Time Object Detection with Transformer

Robustness Evaluation of HD Map Constructors under Sensor Corruptions for Autonomous Driving

DriveVLM: Vision-Language Models for Autonomous Driving in Urban Environments

No-Transaction Band Network A Neural Network Architecture for Efficient Deep Hedging

A Better Match for Drivers and Riders Reinforcement Learning at Lyft

The limits to learning a diffusion model

NeuralProphet Explainable Forecasting at Scale

TransAct Transformer-based Realtime User Action Model for Recommendation at Pinterest

AutoEmb Automated Embedding Dimensionality Searchg in Streaming Recommendations

ZeRO Memory Optimizations: Toward Training Trillion Parameter Models

Zero Bubble Pipeline Parallelism