REVIEW 19 cited by
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Axial Attention in Multidimensional Transformers
read the original abstract
We propose Axial Transformers, a self-attention-based autoregressive model for images and other data organized as high dimensional tensors. Existing autoregressive models either suffer from excessively large computational resource requirements for high dimensional data, or make compromises in terms of distribution expressiveness or ease of implementation in order to decrease resource requirements. Our architecture, by contrast, maintains both full expressiveness over joint distributions over data and ease of implementation with standard deep learning frameworks, while requiring reasonable memory and computation and achieving state-of-the-art results on standard generative modeling benchmarks. Our models are based on axial attention, a simple generalization of self-attention that naturally aligns with the multiple dimensions of the tensors in both the encoding and the decoding settings. Notably the proposed structure of the layers allows for the vast majority of the context to be computed in parallel during decoding without introducing any independence assumptions. This semi-parallel structure goes a long way to making decoding from even a very large Axial Transformer broadly applicable. We demonstrate state-of-the-art results for the Axial Transformer on the ImageNet-32 and ImageNet-64 image benchmarks as well as on the BAIR Robotic Pushing video benchmark. We open source the implementation of Axial Transformers.
Forward citations
Cited by 19 Pith papers
-
Sampling the Schwinger Model with Gauge-Equivariant Diffusion
A gauge-equivariant diffusion model samples Schwinger model configurations, yielding unbiased observables matching MCMC and qualitatively less topological freezing than HMC.
-
UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
UniverSat is a ViT-style model with a universal patch encoder enabling self-supervised training on heterogeneous multimodal Earth observation data from varying resolutions and sensors.
-
Training Agents Inside of Scalable World Models
Dreamer 4 is the first agent to obtain diamonds in Minecraft from only offline data by reinforcement learning inside a scalable world model that accurately predicts game mechanics.
-
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Medusa augments LLMs with multiple decoding heads and tree-based attention to predict and verify several tokens in parallel, yielding 2.2-3.6x inference speedup via two fine-tuning regimes.
-
Video Diffusion Models
A diffusion model for video generation extends image architectures with joint image-video training and improved conditional sampling, delivering first large-scale text-to-video results and state-of-the-art performance...
-
Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders
C-GSPN scales 2D spatial propagation to foundation vision encoders via a fast CUDA kernel, compressed blocks, and two-stage distillation, matching ViT performance with 15% fewer parameters and 4x block speedup at 2K r...
-
Elastic Attention Cores for Scalable Vision Transformers
VECA learns effective visual representations using core-periphery attention where patches interact exclusively via a resolution-invariant set of learned core embeddings, achieving linear O(N) complexity while maintain...
-
The Transformer as a Polar State Estimator
Transformer components arise as the natural solution to precision-weighted directional state estimation on the hypersphere.
-
The Transformer as a Polar State Estimator
The standard Transformer block arises as a first-order approximation to a polar state estimator on the hypersphere, with a Polar Transformer retaining higher-order terms.
-
Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting
ESFM is a single open foundation model that unifies heterogeneous Earth data sources and forecasts missing regions while preserving inter-variable physical relationships.
-
MoBA: Mixture of Block Attention for Long-Context LLMs
MoBA routes attention over blocks via MoE-style gating to enable dynamic, bias-light long-context attention that matches full attention performance at lower cost.
-
YOLOv12: Attention-Centric Real-Time Object Detectors
YOLOv12 is a new attention-based real-time object detector that reports higher accuracy than YOLOv10, YOLOv11, and RT-DETR variants at comparable or better speed and efficiency.
-
Deformable DETR: Deformable Transformers for End-to-End Object Detection
Deformable DETR achieves higher accuracy than DETR, especially on small objects, while converging in one-tenth the training epochs by using sparse deformable attention on image features.
-
Jukebox: A Generative Model for Music
Jukebox generates high-fidelity and diverse songs with singing and coherence up to multiple minutes by compressing raw audio via multi-scale VQ-VAE and modeling the codes with large autoregressive Transformers conditi...
-
GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generation
GeoFlow improves OD flow prediction and generation by augmenting area representations with geospatial attributes and using a geometric-intrinsic fusion encoder with axial-global attention decoder.
-
TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery
TabCausal is a causal discovery foundation model pretrained across diverse synthetic causal environments that reports better macro-averaged performance than baselines on both synthetic and LLM-audited semantic benchmarks.
-
SwInception -- Local Attention Meets Convolutions
SwInception augments Swin transformers with Inception-style multi-branch convolutions in feed-forward layers plus decoder modifications, reporting gains over prior backbones on eleven medical segmentation datasets inc...
-
Multi-Block Attention for Efficient Channel Estimation in IRS-Assisted mmWave MIMO
A multi-block attention neural network reduces pilot overhead by 87% and NMSE by 51% at 10 dB SNR for cascaded channel estimation in IRS-assisted mmWave MIMO-OFDM systems.
-
A Point Cloud Transformer for Remote Monitoring and Automated Assessment of Physical Rehabilitation Exercises
A point cloud transformer using axial self-attention and curve-based feature aggregation assesses rehabilitation exercise performance on Kimore, UI-PRMD, and IRDS datasets, claiming superior results with a compact model.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.