ImageNet

Timeline

1. Oct 8, 2026 · Research paper · 2 sources
   One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
   In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate feature distillation. reViT restores depth-specific transformations by representing the FFN at each recurrent depth as a convex combination of a small shared expert bank.
2. Oct 8, 2026 · Research paper · 1 source
   Few-Step Generation via Data-Space Iteration
   Flow matching has emerged as a scalable paradigm for training high-quality generative models, but sampling from the learned probability flow requires many network evaluations.
3. Oct 8, 2026 · Research paper · 1 source
   Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing
   We study the sample complexity of noisy one-bit compressed sensing for signals drawn from a prior distribution.
4. Oct 8, 2026 · Research paper · 1 source
   Dino Forcing Flow Models: Do not denoise what you can predict
   Co-denoising pretrained representations such as DINO can substantially improve the training speed and quality of flow matching models, but it introduces a second denoising trajectory and requires carefully designed schedules.
5. Oct 8, 2026 · Research paper · 1 source
   HAND: A Biologically-Inspired Activation Function that Improves Generalisation and Sample Efficiency in Image Classification
   We incorporate a biologically-inspired inductive bias into a new activation function, HAND (Homeostasis, Accelerating Nonlinearity, and Divisive-nomalisation), and show its effectiveness with CNNs trained on image classification.
6. Oct 8, 2026 · Research paper · 1 source
   MCL: Meta Convolution Layer
   Dynamic convolution enhances convolutional neural networks (CNNs) by adapting kernels to input content, but it expresses the effective kernel as a linear mixture of a small number of basis kernels, which limits expressivity and complicates optimization as the mixture size grows.
7. Oct 7, 2026 · Research paper · 1 source
   Velocity Scaling in Flow Matching
   Scaling a learned flow-matching velocity field $vθ$ by a gain $γ(t)$ was recently shown to greatly improve generation quality.
8. Oct 7, 2026 · Research paper · 1 source
   QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation
   We introduce QuadTok, a novel framework for visual tokenization and autoregressive image generation.
9. Oct 7, 2026 · Research paper · 1 source
   Koopman Observers for Diffusion Acceleration: Correcting Feature Forecasts with Shallow Measurements
   We introduce an observation-corrected Koopman framework for accelerating frozen diffusion models.
10. Oct 7, 2026 · Research paper · 1 source
    Kinetic Langevin Meets Split Gibbs: Accelerated Posterior Sampling for Imaging Inverse Problems with Diffusion Priors
    Split Gibbs sampling (SGS) is a popular framework for posterior sampling in Bayesian imaging inverse problems.
11. Oct 7, 2026 · Research paper · 1 source
    Progress and Prospect of AI in ARPES Workflow
    Artificial intelligence (AI) is becoming an increasingly useful tool across the experimental sciences, including angle-resolved photoemission spectroscopy (ARPES), which routinely produces large, multidimensional datasets of electronic structure.
12. Oct 7, 2026 · Research paper · 1 source
    DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models
    We introduce DisParQ (Discrete Parts with Quantized attributes), a method that learns spatially grounded, discrete concept representations from a powerful frozen vision-only self-supervised backbone.
13. Oct 7, 2026 · Research paper · 1 source
    Beyond Group Splits: Specimen-Level Cross-Validation and Visual Attribution for Remaining-Shelf-Life Regression in Climacteric Fruit
    Estimating remaining shelf life (RSL) from images could provide affordable decision support for perishable produce, but evaluation protocols can substantially affect reported performance when repeated images are available from the same biological specimen.
14. Oct 7, 2026 · Research paper · 1 source
    MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
    In post-deployment time, inputs to deep learning models may or may not be adversarially patched.
15. Oct 7, 2026 · Research paper · 1 source
    Pooling Representation Autoencoders for Efficient Diffusion
    Motivated by local feature correlations, we introduce PoolDINO, a learned affine pooling operator that merges neighboring tokens.
16. Oct 6, 2026 · Research paper · 1 source
    Consistent Distribution Matching for Data-Free Diffusion Distillation
    In this work, we propose Consistent Distribution Matching, a simulation-free and data-free distillation method for accelerating diffusion and flow models while preserving strong generative capacity.
17. Oct 6, 2026 · Research paper · 1 source
    Co-Evolving Paths and Flows via Path-Flow Alignment
    We study path-flow alignment as a unified training objective for flow matching.
18. Oct 6, 2026 · Research paper · 1 source
    From the Drosophila Visual Connectome to General-Purpose Computer Vision
    We develop ConnectomeX around FlyVision, a trainable architecture that preserves parallel ON/OFF processing, recurrent computation and population-level graph interaction while scaling model capacity across tasks.
19. Oct 6, 2026 · Research paper · 1 source
    Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration
    We propose Quantizer-Aligned Recalibration (QuAR), a single-pass TTA method tailored to quantized ViTs that neither backpropagates nor updates any model parameters.
20. Oct 6, 2026 · Research paper · 1 source
    Compact Robot Policies Need Fine-Grained Visual Representations
    To test this, we build CoRP (Compressed Representation Policy), a deliberately compact policy (48.9M parameters, no vision-language model and no video-generative prior) that factorizes into a representation extractor and a flow-matching action generator.
21. Oct 6, 2026 · Research paper · 1 source
    Two Halves are More than One: Phase-wise Velocity Distillation for Fast and High-Quality Image Generation
    Recent diffusion-based image generation backbones have grown substantially in scale, making the network inference cost increase rapidly.
22. Oct 6, 2026 · Research paper · 1 source
    Later Is Better: Token Reduction for ViTs Under Distribution Shift
    Training-free token reduction accelerates vision transformers by removing redundant tokens across layers, recovering most of the original accuracy at a fraction of the compute.
23. Oct 1, 2026 · Model release · 1 source
    nvidia/PixelDiT2-ImageNet
    nvidia published the model PixelDiT2-ImageNet on Hugging Face.

Often appears with