Picture for Sanjiv Kumar

Sanjiv Kumar

Google Research

ELM: Embedding and Logit Margins for Long-Tail Learning

Add code
Apr 27, 2022
Figure 1 for ELM: Embedding and Logit Margins for Long-Tail Learning
Figure 2 for ELM: Embedding and Logit Margins for Long-Tail Learning
Figure 3 for ELM: Embedding and Logit Margins for Long-Tail Learning
Figure 4 for ELM: Embedding and Logit Margins for Long-Tail Learning
Viaarxiv icon

Predicting on the Edge: Identifying Where a Larger Model Does Better

Add code
Feb 15, 2022
Viaarxiv icon

Robust Training of Neural Networks using Scale Invariant Architectures

Add code
Feb 02, 2022
Figure 1 for Robust Training of Neural Networks using Scale Invariant Architectures
Figure 2 for Robust Training of Neural Networks using Scale Invariant Architectures
Figure 3 for Robust Training of Neural Networks using Scale Invariant Architectures
Figure 4 for Robust Training of Neural Networks using Scale Invariant Architectures
Viaarxiv icon

When in Doubt, Summon the Titans: Efficient Inference with Large Models

Add code
Oct 19, 2021
Figure 1 for When in Doubt, Summon the Titans: Efficient Inference with Large Models
Figure 2 for When in Doubt, Summon the Titans: Efficient Inference with Large Models
Figure 3 for When in Doubt, Summon the Titans: Efficient Inference with Large Models
Figure 4 for When in Doubt, Summon the Titans: Efficient Inference with Large Models
Viaarxiv icon

Leveraging redundancy in attention with Reuse Transformers

Add code
Oct 13, 2021
Figure 1 for Leveraging redundancy in attention with Reuse Transformers
Figure 2 for Leveraging redundancy in attention with Reuse Transformers
Figure 3 for Leveraging redundancy in attention with Reuse Transformers
Figure 4 for Leveraging redundancy in attention with Reuse Transformers
Viaarxiv icon

Batch Active Learning at Scale

Add code
Jul 29, 2021
Figure 1 for Batch Active Learning at Scale
Figure 2 for Batch Active Learning at Scale
Figure 3 for Batch Active Learning at Scale
Figure 4 for Batch Active Learning at Scale
Viaarxiv icon

Teacher's pet: understanding and mitigating biases in distillation

Add code
Jul 08, 2021
Figure 1 for Teacher's pet: understanding and mitigating biases in distillation
Figure 2 for Teacher's pet: understanding and mitigating biases in distillation
Figure 3 for Teacher's pet: understanding and mitigating biases in distillation
Figure 4 for Teacher's pet: understanding and mitigating biases in distillation
Viaarxiv icon

Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation

Add code
Jun 16, 2021
Figure 1 for Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation
Figure 2 for Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation
Figure 3 for Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation
Figure 4 for Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation
Viaarxiv icon

Scaling Hierarchical Agglomerative Clustering to Billion-sized Datasets

Add code
May 25, 2021
Figure 1 for Scaling Hierarchical Agglomerative Clustering to Billion-sized Datasets
Figure 2 for Scaling Hierarchical Agglomerative Clustering to Billion-sized Datasets
Figure 3 for Scaling Hierarchical Agglomerative Clustering to Billion-sized Datasets
Figure 4 for Scaling Hierarchical Agglomerative Clustering to Billion-sized Datasets
Viaarxiv icon

Balancing Robustness and Sensitivity using Feature Contrastive Learning

Add code
May 19, 2021
Figure 1 for Balancing Robustness and Sensitivity using Feature Contrastive Learning
Figure 2 for Balancing Robustness and Sensitivity using Feature Contrastive Learning
Figure 3 for Balancing Robustness and Sensitivity using Feature Contrastive Learning
Figure 4 for Balancing Robustness and Sensitivity using Feature Contrastive Learning
Viaarxiv icon