Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Daniel Y. Fu

Daniel Y. Fu

Lost in Transmission: On the Impact of Networking Corruptions on Video Machine Learning Models



Trenton Chang , Daniel Y. Fu

Figure 1 for Lost in Transmission: On the Impact of Networking Corruptions on Video Machine Learning Models
Figure 2 for Lost in Transmission: On the Impact of Networking Corruptions on Video Machine Learning Models
Figure 3 for Lost in Transmission: On the Impact of Networking Corruptions on Video Machine Learning Models
Figure 4 for Lost in Transmission: On the Impact of Networking Corruptions on Video Machine Learning Models
* 12 pages, 12 figures (with supplemental: 34 pages) 
   Access Paper or Ask Questions

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness



Tri Dao , Daniel Y. Fu , Stefano Ermon , Atri Rudra , Christopher Ré

Figure 1 for FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Figure 2 for FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Figure 3 for FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Figure 4 for FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

   Access Paper or Ask Questions

TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval



Megan Leszczynski , Daniel Y. Fu , Mayee F. Chen , Christopher Ré

Figure 1 for TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval
Figure 2 for TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval
Figure 3 for TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval
Figure 4 for TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval
* Accepted to Findings of ACL 2022 
   Access Paper or Ask Questions

Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning



Mayee F. Chen , Daniel Y. Fu , Avanika Narayan , Michael Zhang , Zhao Song , Kayvon Fatahalian , Christopher Ré

Figure 1 for Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
Figure 2 for Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
Figure 3 for Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
Figure 4 for Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning

   Access Paper or Ask Questions

Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision



Mayee F. Chen , Daniel Y. Fu , Dyah Adila , Michael Zhang , Frederic Sala , Kayvon Fatahalian , Christopher Ré

Figure 1 for Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
Figure 2 for Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
Figure 3 for Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
Figure 4 for Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision

   Access Paper or Ask Questions

Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings



Mayee F. Chen , Daniel Y. Fu , Frederic Sala , Sen Wu , Ravi Teja Mullapudi , Fait Poms , Kayvon Fatahalian , Christopher Ré

Figure 1 for Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings
Figure 2 for Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings
Figure 3 for Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings
Figure 4 for Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings

   Access Paper or Ask Questions

Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods



Daniel Y. Fu , Mayee F. Chen , Frederic Sala , Sarah M. Hooper , Kayvon Fatahalian , Christopher Ré

Figure 1 for Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
Figure 2 for Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
Figure 3 for Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
Figure 4 for Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods

   Access Paper or Ask Questions

Multi-Resolution Weak Supervision for Sequential Data



Frederic Sala , Paroma Varma , Jason Fries , Daniel Y. Fu , Shiori Sagawa , Saelig Khattar , Ashwini Ramamoorthy , Ke Xiao , Kayvon Fatahalian , James Priest , Christopher Ré

Figure 1 for Multi-Resolution Weak Supervision for Sequential Data
Figure 2 for Multi-Resolution Weak Supervision for Sequential Data
Figure 3 for Multi-Resolution Weak Supervision for Sequential Data
Figure 4 for Multi-Resolution Weak Supervision for Sequential Data
* NeurIPS 2019 (Conference on Neural Information Processing Systems) 
   Access Paper or Ask Questions

Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels



Daniel Y. Fu , Will Crichton , James Hong , Xinwei Yao , Haotian Zhang , Anh Truong , Avanika Narayan , Maneesh Agrawala , Christopher Ré , Kayvon Fatahalian

Figure 1 for Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
Figure 2 for Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
Figure 3 for Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
Figure 4 for Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels

   Access Paper or Ask Questions

Influencing Flock Formation in Low-Density Settings



Daniel Y. Fu , Emily S. Wang , Peter M. Krafft , Barbara J. Grosz

Figure 1 for Influencing Flock Formation in Low-Density Settings
Figure 2 for Influencing Flock Formation in Low-Density Settings
Figure 3 for Influencing Flock Formation in Low-Density Settings
Figure 4 for Influencing Flock Formation in Low-Density Settings
* 9 pages, 5 figures, accepted to AAMAS 2018 
   Access Paper or Ask Questions