Skip to content

AI models and papers trending on September 28, 2026

Archive · Monday, September 28, 2026 · week 40

The edition of this day as it was recorded: the most upvoted papers of the daily list.

On Monday, September 28, 2026 the most upvoted paper was "FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders" from USC Physical Superintelligence (PSI) Lab, with 158 votes. 11 of the 15 leading papers had a code repository attached. No model list exists for this day: Hugging Face does not publish past trending lists, and our collector had not started yet.

Papers only · rebuilt on 2026-10-03 09:16 UTC from the Hugging Face daily papers archive

Papers

Daily list of September 28, 2026

  1. 158

    FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

    USC Physical Superintelligence (PSI) LabarXiv 2609.31620 (opens in a new tab)Code (opens in a new tab)

  2. 90

    Disaggregated Quantization: Specializing LLM Prefill and Decode

    IST Austria Distributed Algorithms and Systems LabarXiv 2609.26333 (opens in a new tab)Code (opens in a new tab)

  3. 54

    RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation

    Peking UniversityarXiv 2609.18703 (opens in a new tab)Code (opens in a new tab)

  4. 32

    TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent

    Visa IncarXiv 2609.27277 (opens in a new tab)Code (opens in a new tab)

  5. 30

    Block Sparse Attention with Log-Linear Complexity

    ByteDance SeedarXiv 2609.31093 (opens in a new tab)

  6. 29

    InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data

    arXiv 2609.31394 (opens in a new tab)

  7. 28

    LastOPD: Taming Collapse in Latent On-Policy Distillation

    Visa IncarXiv 2609.28845 (opens in a new tab)Code (opens in a new tab)

  8. 23

    Tactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors

    arXiv 2609.24385 (opens in a new tab)Code (opens in a new tab)

  9. 22

    FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance

    Seoul National UniversityarXiv 2609.25716 (opens in a new tab)Code (opens in a new tab)

  10. 21

    IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking

    National Payments Corporation of IndiaarXiv 2609.29167 (opens in a new tab)Code (opens in a new tab)

  11. 17

    D-JEPA: A Decision-Aligned Latent World Model

    NEBULIS LabarXiv 2609.24749 (opens in a new tab)Code (opens in a new tab)

  12. 15

    Jev in the Wild: A Data-Driven Analysis of the Jev Model's Functionality, Applications and Ecosystem

    The Chinese University of Hong KongarXiv 2609.30216 (opens in a new tab)Code (opens in a new tab)

  13. 15

    Morphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy

    UC BerkeleyarXiv 2609.28660 (opens in a new tab)Code (opens in a new tab)

  14. 14

    Enhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal Conditioning

    ThalesarXiv 2609.31199 (opens in a new tab)

  15. 13

    TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations

    Carnegie Mellon UniversityarXiv 2609.30222 (opens in a new tab)

Models

Hugging Face trending order

No model list exists for this day. Hugging Face does not publish past trending lists, so days before the collector started carry papers only.

About the archive

How far back does the archive go?

Model lists exist from the first day the collector ran: Hugging Face does not publish past trending lists, so they cannot be rebuilt. Paper lists for earlier days were rebuilt from the Hugging Face daily papers archive, and those days are marked "papers only".

What is kept for each day?

The leading models with their task, likes and downloads on that day, the models held back, and the leading papers with their upvotes. Abstracts are not duplicated in the archive; each paper links to arXiv.

Do archived numbers change?

No. A day’s record is the last collection of that day and is not rewritten afterwards. Likes and downloads you see on an archived day are the values on that day, not today’s.

How are weeks defined?

ISO 8601 weeks: Monday to Sunday, numbered so that week 1 contains the first Thursday of the year. The address /week/2026-40 is week 40 of 2026.