PLAY PODCASTS
Daily Paper Cast

Daily Paper Cast

We update every weekday to discuss highest-voted papers from Huggingface Daily Paper (https://huggingface.co/papers).

Jingwen Liang, Gengyu Wang

2,516 episodesEN

Show overview

Daily Paper Cast has been publishing since 2024, and across the 2 years since has built a catalogue of 2,516 episodes. That works out to roughly 940 hours of audio in total. Releases follow a near-daily cadence.

Episodes typically run twenty to thirty-five minutes — most land between 21 min and 24 min — and the run-time is fairly consistent across the catalogue. None of the episodes are flagged explicit by the publisher. It is catalogued as a EN-language Science show.

The show is actively publishing — the most recent episode landed yesterday, with 975 episodes already out so far this year. The busiest year was 2025, with 1238 episodes published. Published by Jingwen Liang, Gengyu Wang.

Episodes
2,516
Running
2024–2026 · 2y
Median length
22 min
Cadence
Near-daily

From the publisher

We update every weekday to discuss highest-voted papers from Huggingface Daily Paper (https://huggingface.co/papers). Both the podcast scripts and audio are generated by AI. Feedback and suggestions are welcome! Email us: [email protected] Creator: Jingwen Liang, 3D ML, https://www.linkedin.com/in/jingwen-liang/ Gengyu Wang, LLM ML, http://wanggengyu.com Listen on: Spotify: https://open.spotify.com/show/21nrhmdaA8qoBiH8q03NXL Apple Podcast: https://podcasts.apple.com/us/podcast/daily-paper-cast/id1777620236 Cover Image by Kawen Kuang https://kawen.art

TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks

Nov 18, 202620 min

AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs

Nov 18, 202622 min

Weight-Space Programming Doesn't Need Transformers

Nov 18, 202621 min

ForceHarness: Turning Force into Action and Physics for Frozen Frontier Models

Nov 18, 202622 min

Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose

Nov 18, 202622 min

Multi-Branch Transformer

Nov 18, 202623 min

Self-Improvement Memory Enables Continual Recursive Self-Improvement

Nov 18, 202623 min

TCP4D: A Unified Tool-Center-Point Tracking and Generation Model for Robot Manipulation

Nov 18, 202620 min

AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data

Nov 17, 202621 min

InclusionMed: Benchmarking AI for Inclusive Healthcare

Nov 17, 202624 min

Sage S2.1 Flash Technical Report

Nov 17, 202622 min

SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection

Nov 17, 202620 min

SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations

Nov 17, 202624 min

SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models

Nov 13, 202622 min

BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model

Nov 13, 202623 min

G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation

Nov 13, 202620 min

Duo: A Reciprocal World Model for Full-Duplex Interaction

Nov 13, 202623 min

PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models

Nov 13, 202626 min

On the Design of Hyper-Connections: Simplification, Stability, and Scalability

Nov 13, 202621 min

Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents

Nov 13, 202618 min
© 2026 Jingwen Liang, Gengyu Wang