DyABD is the first benchmark dataset for abdominal muscle segmentation in dynamic MRIs featuring exercise-induced anatomical changes and pre/post-surgery scans, where existing models achieve an average Dice score of 0.82.
super hub Canonical reference
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Canonical reference. 86% of citing Pith papers cite this work as background.
425
Pith papers citing it
Background
86% of classified citations
abstract
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.
hub tools
citation-role summary
background 6
method 1
citation-polarity summary
claims ledger
- abstract While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple m
authors
co-cited works
representative citing papers
CheXTemporal supplies paired chest X-rays with explicit temporal progression taxonomy and spatial grounding to benchmark and improve models on longitudinal reasoning tasks.
A Particle Transformer jet tagger contains a sparse six-head circuit whose source-relay-readout structure recovers most performance and whose residual stream preferentially encodes 2-prong energy correlators.
NLI autonomously discovers a vocabulary of primitive operations and interprets variable-length programs via a neural executor, allowing end-to-end training and gradient-based test-time adaptation that outperforms prior methods on combinatorial generalization tasks.
Diffusion Policy models robot actions as a conditional diffusion process, outperforming prior state-of-the-art methods by 46.9% on average across 12 manipulation tasks from four benchmarks.
S4 is an efficient state space sequence model that captures long-range dependencies via structured parameterization of the SSM, achieving state-of-the-art results on the Long Range Arena and other benchmarks while being faster than Transformers for generation.
SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
QLAM extends state-space models with quantum superposition in the hidden state for linear-time long-sequence modeling and reports consistent gains over RNN and transformer baselines on sequential image tasks.
MedCore achieves 60% parameter and 58.4% FLOP reduction on MedSAM with Dice 0.9549 and preserved boundary metrics via dual-intervention pruning and a new boundary leverage principle.
A new dual-input feature fusion network using RGB images and channel impulse responses identifies LoS/NLoS conditions for UAVs with up to 97.69% accuracy and reduces trilateration positioning error by about 70%.
RotVLA models latent actions as continuous SO(n) rotations with triplet-frame supervision and flow-matching to reach 98.2% success on LIBERO and 89.6%/88.5% on RoboTwin2.0 using a 1.7B-parameter model.
KamonBench is a grammar-generated synthetic dataset of compositional kamon crests with explicit factor annotations to evaluate factor recovery in vision-language models.
Backdoors can be realized as statistically natural latent directions in modern neural networks, achieving high attack success with negligible clean accuracy loss and resisting existing defenses.
SubPopMark protects distilled datasets by injecting verifiable subpopulation biases that create distinguishable model behaviors for copyright tracing without using backdoors.
MindVLA-U1 introduces a unified streaming VLA with shared backbone, framewise memory, and language-guided action diffusion that surpasses human drivers on WOD-E2E planning metrics.
MoLA infers a mixture of latent actions from generated future videos via modality-aware inverse dynamics models to improve robot manipulation policies.
SVL uses language embeddings aligned with global image representations via shadow ratio regression and global-to-local coupling to improve shadow detection robustness in ambiguous cases.
SkyPart uses learnable prototypes for patch grouping, altitude modulation only in training, graph-attention readout, and Kendall-weighted loss to set new state-of-the-art single-pass performance on SUES-200, University-1652, and DenseUAV while widening gains under weather corruptions.
The first integrated taxonomy, empirical study of interplay and shallow dememorization, plus a theoretical guarantee on dememorization depth for certified unlearning.
TCP-SSM conditions stable poles on visual tokens to explicitly control memory decay and oscillation in SSMs, cutting computation up to 44% while matching or exceeding accuracy on classification, segmentation, and detection.
GraphScan replaces geometric or coordinate-based scanning in Vision SSMs with learned local semantic graph routing, yielding SOTA results among such models on classification and segmentation tasks.
RelFlexformers enable flexible integrable 3D RPE in attention via NU-FFT, generalizing prior methods to heterogeneous token positions with O(L log L) complexity.
A new annotated dataset of zebrafish embryo image sequences enables a spatiotemporal transformer to classify fertility at 98% accuracy and detect compound-induced malformations at 92% accuracy.
Temporal correlations from lazy random walks enable efficient SGD learning of k-juntas via temporal-difference loss on ReLU networks, achieving linear sample complexity in d.
citing papers explorer
-
Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
Diffusion Policy models robot actions as a conditional diffusion process, outperforming prior state-of-the-art methods by 46.9% on average across 12 manipulation tasks from four benchmarks.
-
Eliciting Latent Predictions from Transformers with the Tuned Lens
Training per-layer affine probes on frozen transformers yields more reliable latent predictions than the logit lens and enables detection of malicious inputs from prediction trajectories.
-
BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs
BiomedCLIP, pretrained on the new 15-million-pair PMC-15M dataset, achieves state-of-the-art performance on diverse biomedical vision-language tasks and even outperforms radiology-specific models on chest X-ray pneumonia detection.
-
Accelerating Large Language Model Decoding with Speculative Sampling
Speculative sampling accelerates LLM decoding 2-2.5x by letting a draft model propose short sequences that the target model scores in parallel, then applies modified rejection sampling to keep the exact target distribution.
-
MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action
MM-REACT uses textual prompts to let ChatGPT collaborate with external vision experts for zero-shot multimodal reasoning and action on advanced visual tasks.
-
PaLM-E: An Embodied Multimodal Language Model
PaLM-E is a single 562B-parameter multimodal model that performs embodied reasoning tasks like robotic manipulation planning and visual question answering by interleaving vision, state, and text inputs with positive transfer from joint training on language and robotics data.
-
Improved Baselines with Visual Instruction Tuning
Simple changes to LLaVA using CLIP-ViT-L-336px, an MLP connector, and academic VQA data yield state-of-the-art results on 11 benchmarks with only 1.2M public examples and one-day training on 8 A100 GPUs.