Tag Index

active-visual-exploration

1 item with this tag.

Apr 04, 2024
AdaGlimpse - Active Visual Exploration with Arbitrary Glimpse Position and Scale

adaptation

5 items with this tag.

benchmark

1 item with this tag.

Jun 11, 2025
IntPhys 2 - Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments

clustering

2 items with this tag.

Feb 12, 2025
Cluster and Predict Latents Patches for Improved Masked Image Modeling
Jun 18, 2022
Self-Supervised Learning of Object Parts for Semantic Segmentation

cnn

10 items with this tag.

cognitive-science

2 items with this tag.

Jan 01, 2025
Global Precedence Effect
- cognitive-science
- psychology
Jan 01, 2025
Perceptual Priming and the Overfitted Brain Hypothesis
- cognitive-science

compilers

1 item with this tag.

Jan 01, 2024
PyTorch Functionalization
- pytorch
- compilers

compression

1 item with this tag.

Nov 22, 2023
White-Box Transformers via Sparse Rate Reduction - Compression Is All There Is
- compression
- dl_theory

computer_vision

52 items with this tag. Showing first 10 tags.

continual_learning

5 items with this tag.

contrastive_learning

convolutions

3 items with this tag.

dataset

1 item with this tag.

Jun 11, 2025
IntPhys 2 - Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments

dense

2 items with this tag.

dense_ssl

3 items with this tag.

Apr 24, 2023
A Cookbook of Self-Supervised Learning
Mar 22, 2023
Correlational Image Modeling for Self-Supervised Visual Pre-Training
- ssl
- dense_ssl
Oct 04, 2022
VICRegL - Self-Supervised Learning of Local Visual Features

diffusion

3 items with this tag.

Oct 13, 2025
Diffusion Transformers with Representation Autoencoders
Feb 10, 2025
From Image to Video - An Empirical Study of Diffusion Representations
- video
- diffusion
Jun 17, 2023
Self-Guided Diffusion Models
- computer_vision
- diffusion

disentanglement

1 item with this tag.

Dec 05, 2018
Towards a Definition of Disentangled Representations
- disentanglement
- dl_theory

distillation

1 item with this tag.

Feb 17, 2024
On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models

dl_theory

79 items with this tag. Showing first 10 tags.

Oct 08, 2025
Into the Rabbit Hull - From Task-Relevant Concepts in DINO to Minkowski Geometry
Apr 02, 2025
Learning from Streaming Video with Orthogonal Gradients
Mar 11, 2025
Principal Components Enable A New Language of Images
Mar 03, 2025
Deep Learning is Not So Mysterious or Different
Feb 26, 2025
Rate–Distortion–Perception Trade-Off in Information Theory, Generative Models, and Intelligent Communications
- information_theory
- dl_theory
Feb 14, 2025
Simplifying DINO via Coding Rate Regularization
Jan 01, 2025
Are less inductive biases better or worse?
- dl_theory
- question
Jan 01, 2025
Rate Distortion and Spectral Analysis on Representations
Jan 01, 2025
Should we separate semantics and pose?
Dec 04, 2024
Beyond cls - Exploring the true potential of Masked Image Modeling representations

dl-theory

5 items with this tag.

Oct 25, 2025
Vision Transformers Don't Need Trained Registers
- vit
- dl-theory
Oct 14, 2025
Joint Embedding vs Reconstruction - Provable Benefits of Latent Space Prediction for Self Supervised Learning
- dl-theory
- ssl
Oct 13, 2025
Diffusion Transformers with Representation Autoencoders
Feb 07, 2023
Equivariance-aware architectural optimization of neural networks
- dl-theory
- equivariance
Feb 04, 2023
Equi-Tuning - Group Equivariant Fine-Tuning of Pretrained Models
- dl-theory
- equivariance

efficient_dl

37 items with this tag. Showing first 10 tags.

Jul 11, 2025
KV Cache Steering for Inducing Reasoning in Small Language Models
Jan 01, 2025
Dynamic Resource Allocation in Vision
- efficient_dl
- efficient_vision
Jul 29, 2024
Apple Intelligence Foundation Language Models
- efficient_dl
Jun 24, 2024
Building on Efficient Foundations - Effectively Training LLMs with Structured Feedforward Layers
Jun 04, 2024
Block Transformer - Global-to-Local Language Modeling for Fast Inference
- efficient_dl
- transformers
Apr 21, 2024
Mixture of LoRa Experts
- peft
- efficient_dl
Apr 12, 2024
Scaling (Down) CLIP - A Comprehensive Analysis of Data, Architecture, and Training Strategies
Apr 03, 2024
Talaria - Interactively Optimizing Machine Learning Models for Efficient Inference
- efficient_dl
Mar 29, 2024
Efficient Modulation for Vision Networks
- efficient_dl
- computer_vision
Mar 29, 2024
Rewrite the Stars
- dl_theory
- efficient_dl

efficient_vision

12 items with this tag. Showing first 10 tags.

entropy

1 item with this tag.

Jan 01, 2025
Rate Distortion and Spectral Analysis on Representations

equivariance

26 items with this tag. Showing first 10 tags.

flexible_vit

2 items with this tag.

Sep 26, 2024
HydraViT - Stacking Heads for a Scalable ViT
Oct 11, 2023
MatFormer - Nested Transformer for Elastic Inference

foundation_models

24 items with this tag. Showing first 10 tags.

Dec 17, 2025
Multi-View Foundation Models
- foundation_models
Aug 13, 2025
DINOv3
Jul 18, 2025
Franca - Nested Matryoshka Clustering for Scalable Visual Representation Learning
Apr 22, 2024
OpenELM - An Efficient Language Model Family with Open-source Training and Inference Framework
- llm
- foundation_models
Feb 17, 2024
On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models
Jan 09, 2024
Low-Resource Vision Challenges for Foundation Models
Jan 01, 2024
Do Vision Foundation models exist?
Jan 01, 2024
Masked Image Modelling
- foundation_models
- computer_vision
Dec 01, 2023
Mamba - Linear-Time Sequence Modeling with Selective State Spaces
- foundation_models
- convolutions
Nov 30, 2023
Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models
- efficient_dl
- foundation_models

gcn

1 item with this tag.

Nov 13, 2019
A Hierarchy of Graph Neural Networks Based on Learnable Local Features

generative

1 item with this tag.

Oct 13, 2025
Diffusion Transformers with Representation Autoencoders

geometric_dl

3 items with this tag.

geometry

3 items with this tag.

gnn

1 item with this tag.

Nov 13, 2019
A Hierarchy of Graph Neural Networks Based on Learnable Local Features

graphs

1 item with this tag.

Nov 13, 2019
A Hierarchy of Graph Neural Networks Based on Learnable Local Features

hardware_aware_dl

1 item with this tag.

Jan 01, 2024
Hardware-specific structured pruning
- efficient_dl
- hardware_aware_dl

hierarchical

1 item with this tag.

Jun 01, 2023
Hiera - A Hierarchical Vision Transformer without the Bells-and-Whistles

hyperbolic

2 items with this tag.

hypernetworks

1 item with this tag.

Jun 12, 2023
A Brief Review of Hypernetworks in Deep Learning
- hypernetworks

hyperspherical

2 items with this tag.

image

2 items with this tag.

inductive_bias

3 items with this tag.

Mar 03, 2025
Deep Learning is Not So Mysterious or Different
Jan 01, 2025
Should we separate semantics and pose?
Jun 01, 2023
Hiera - A Hierarchical Vision Transformer without the Bells-and-Whistles

information_theory

interpretability

4 items with this tag.

linear_connectivity

1 item with this tag.

Apr 09, 2024
Simultaneous linear connectivity of neural networks modulo permutation

llm

9 items with this tag.

Jul 11, 2025
KV Cache Steering for Inducing Reasoning in Small Language Models
Jul 08, 2025
NeoBabel - A Multilingual Open Tower for Visual Generation
- multimodal
- llm
Dec 13, 2024
Byte Latent Transformer - Patches Scale Better Than Tokens
- llm
- nlp
Oct 10, 2024
Lost in Time - A New Temporal Benchmark for VideoLLMs
Jul 04, 2024
Improving Self Consistency in LLMs through Probabilistic Tokenization
- llm
- dl_theory
Jun 24, 2024
Building on Efficient Foundations - Effectively Training LLMs with Structured Feedforward Layers
Apr 22, 2024
OpenELM - An Efficient Language Model Family with Open-source Training and Inference Framework
- llm
- foundation_models
Jul 11, 2023
Memorization Through the Lens of Curvature of Loss Function Around Samples
- dl_theory
- llm
Jun 22, 2023
Learning Unseen Modality Interaction
- multimodal
- llm

long-context

1 item with this tag.

Jul 21, 2024
xT - Nested Tokenization for Larger Context in Large Images

mamba

1 item with this tag.

Jan 17, 2024
Vision Mamba - Efficient Visual Representation Learning with Bidirectional State Space Model

masked_image_modelling

1 item with this tag.

Feb 10, 2025
From Pixels to Components - Eigenvector Masking for Visual Representation Learning

mechinterp

memory

2 items with this tag.

May 31, 2024
Memory Consolidation Enables Long-Context Video Understanding
Jun 01, 2022
MeMViT - Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition

multimodal

nas

1 item with this tag.

Dec 02, 2018
ProxylessNAS - Direct Neural Architecture Search on Target Task and Hardware
- efficient_dl
- nas

network_permutation_symmetries

1 item with this tag.

Apr 09, 2024
Simultaneous linear connectivity of neural networks modulo permutation

nlp

1 item with this tag.

Dec 13, 2024
Byte Latent Transformer - Patches Scale Better Than Tokens
- llm
- nlp

non_euclidean

2 items with this tag.

object_detection

object_localisation

1 item with this tag.

Feb 13, 2024
PIN - Positional Insert Unlocks Object Localisation Abilities in VLMs
- multimodal
- object_localisation

optimizability

7 items with this tag.

optimization

4 items with this tag.

partial_equivariance

1 item with this tag.

Oct 19, 2021
Learning Partial Equivariances from Data
- equivariance
- partial_equivariance

patch_level

2 items with this tag.

peft

personal

3 items with this tag.

Jun 24, 2024
Building on Efficient Foundations - Effectively Training LLMs with Structured Feedforward Layers
Sep 28, 2023
Vision Transformers Need Registers
Nov 08, 2019
On the Relationship between Self-Attention and Convolutional Layers

posembed

2 items with this tag.

post_training

1 item with this tag.

Aug 20, 2024
Near, far - Patch-ordering enhances vision foundation models' scene understanding

pruning

2 items with this tag.

Mar 26, 2024
The Unreasonable Ineffectiveness of the Deeper Layers
Jun 08, 2015
Learning both Weights and Connections for Efficient Neural Networks

psychology

1 item with this tag.

Jan 01, 2025
Global Precedence Effect
- cognitive-science
- psychology

pytorch

1 item with this tag.

Jan 01, 2024
PyTorch Functionalization
- pytorch
- compilers

quantization

4 items with this tag.

Mar 26, 2024
The Unreasonable Ineffectiveness of the Deeper Layers
Jan 01, 2024
PyTorch Quantization for TensorRT
- quantization
- efficient_dl
Jun 01, 2023
AWQ - Activation-aware Weight Quantization for LLM Compression and Acceleration
- efficient_dl
- quantization
Jun 07, 2017
Training quantized nets - A deeper understanding
- quantization

question

2 items with this tag.

Jan 01, 2025
Are less inductive biases better or worse?
- dl_theory
- question
Jan 01, 2024
Do Vision Foundation models exist?

reasoning

1 item with this tag.

Jul 11, 2025
KV Cache Steering for Inducing Reasoning in Small Language Models

regularization

3 items with this tag.

relaxed_equivariance

representation_analysis

2 items with this tag.

representation_learning

11 items with this tag. Showing first 10 tags.

rl

2 items with this tag.

robustness

1 item with this tag.

May 25, 2024
Certifying Adapters - Enabling and Enhancing the Certification of Classifier Adversarial Robustness
- robustness

rq

1 item with this tag.

Oct 06, 2023
Model Compression in Practice - Lessons Learned from Practitioners Creating On-device Machine Learning Experiences
- efficient_dl
- rq

segmentation

1 item with this tag.

Apr 05, 2023
Segment Anything

self-distillation

2 items with this tag.

sequence_models

1 item with this tag.

Jul 13, 2024
Hydra - Bidirectional State Space Models Through Generalized Matrix Mixers
- sequence_models

spectral

ssl

48 items with this tag. Showing first 10 tags.

Oct 14, 2025
Joint Embedding vs Reconstruction - Provable Benefits of Latent Space Prediction for Self Supervised Learning
- dl-theory
- ssl
Oct 08, 2025
Into the Rabbit Hull - From Task-Relevant Concepts in DINO to Minkowski Geometry
Sep 29, 2025
Rethinking JEPA - Compute-Efficient Video SSL with Frozen Teachers
- video
- ssl
Aug 13, 2025
DINOv3
Jul 25, 2025
Back to the Features - DINO as a Foundation for Video World Models
Jun 11, 2025
IntPhys 2 - Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments
Jun 10, 2025
MoSiC - Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning
- computer_vision
- ssl
Jun 01, 2025
Self-supervised learning of intertwined content and positional features for object detection
- vit
- ssl
Apr 28, 2025
Perception Encoder - The best visual embeddings are not at the output of the network
Apr 02, 2025
Learning from Streaming Video with Orthogonal Gradients

ssm

1 item with this tag.

Jan 17, 2024
Vision Mamba - Efficient Visual Representation Learning with Bidirectional State Space Model

temporal

5 items with this tag.

Dec 15, 2025
Recurrent Video Masked Autoencoders
- temporal
- vit
Apr 20, 2025
Exploring Temporally-Aware Features for Point Tracking
Oct 10, 2024
Lost in Time - A New Temporal Benchmark for VideoLLMs
Oct 12, 2023
Is ImageNet worth 1 video Learning strong image encoders from 1 long unlabelled video
Feb 12, 2018
Quo Vadis, Action Recognition A New Model and the Kinetics Dataset

theory

3 items with this tag.

Jan 01, 2024
Input-dependent convolutions
- cnn
- theory
Dec 13, 2023
Harmonics of Learning - Universal Fourier Features Emerge in Invariant Networks
Nov 08, 2019
On the Relationship between Self-Attention and Convolutional Layers

tokenization

3 items with this tag.

Mar 11, 2025
Principal Components Enable A New Language of Images
Feb 19, 2025
FlexTok - Resampling Images into 1D Token Sequences of Flexible Length
Jul 21, 2024
xT - Nested Tokenization for Larger Context in Large Images

transformers

33 items with this tag. Showing first 10 tags.

variance

1 item with this tag.

Sep 29, 2022
Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations

video

31 items with this tag. Showing first 10 tags.

Jan 11, 2026
Adaptation of Image Models to Video
Jan 08, 2026
Learning Latent Action World Models In The Wild
- video
- world-models
Jan 08, 2026
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models
Sep 29, 2025
Rethinking JEPA - Compute-Efficient Video SSL with Frozen Teachers
- video
- ssl
Sep 16, 2025
ResidualViT for Efficient Temporally Dense Video Encoding
Jul 25, 2025
Back to the Features - DINO as a Foundation for Video World Models
Jun 30, 2025
D$^2$ST-Adapter - Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition
Jun 12, 2025
TDS-CLIP - Temporal Difference Side Network for Efficient VideoAction Recognition
Jun 11, 2025
IntPhys 2 - Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments
Apr 28, 2025
Perception Encoder - The best visual embeddings are not at the output of the network

vit

64 items with this tag. Showing first 10 tags.

Jan 08, 2026
Bi-Orthogonal Factor Decomposition for Vision Transformers
Jan 08, 2026
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models
Dec 15, 2025
Recurrent Video Masked Autoencoders
- temporal
- vit
Oct 25, 2025
Vision Transformers Don't Need Trained Registers
- vit
- dl-theory
Oct 13, 2025
Diffusion Transformers with Representation Autoencoders
Sep 16, 2025
ResidualViT for Efficient Temporally Dense Video Encoding
Aug 13, 2025
DINOv3
Jul 18, 2025
Franca - Nested Matryoshka Clustering for Scalable Visual Representation Learning
Jun 30, 2025
D$^2$ST-Adapter - Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition
Jun 12, 2025
TDS-CLIP - Temporal Difference Side Network for Efficient VideoAction Recognition

Explorer

Tag Index