AI Paper Podcasts

Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling (Jan 2025)

Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction (Apr 2024)

Recursive Language Models (Dec 2025)

uGMM-NN: Univariate Gaussian Mixture Model Neural Network (Sep 2025)

Code as Agent Harness (May 2026)

$δ$-mem: Efficient Online Memory for Large Language Models (May 2026)

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning (June 2025)

Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining (Apr 202

Benchmarking Vision-Language Models on OCR in Dynamic Video Environments (Feb 2025)

Back to Basics: Let Denoising Generative Models Denoise (Nov 2025)

Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent (Aug 2025)

FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space (May 2025)

LLMD: A Large Language Model for Interpreting Longitudinal Medical Records (Oct 2024)

Benchmarking On-Device Machine Learning on Apple Silicon with MLX (Oct 2025)

MEMO: Memory as a Model (May 2026)

Scalable watermarking for identifying large language model outputs (Oct 2024)

FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines (Jun 2026)

Simplifying DINO via Coding Rate Regularization (February 2025)

Learn to Guide Your Diffusion Model (Oct 2025)

Kwai Keye-VL-2.0 Technical Report (Jun 2026)

U.S. Policies Unintentionally Accelerated China's Open AI Ecosystems (Jun 2026)

You Don't Need to Run Every Eval (Jun 2026)

Apple Neural Engine: Architecture, Programming, and Performance (Jun 2026)

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments (Jun 2026)

PixelFlow: Pixel-Space Generative Models with Flow (Apr 2025)

Generative Modeling with Bayesian Sample Inference (Feb 2025)