Summary of Fast: Factorizable Attention For Speeding Up Transformers, by Armin Gerami et al.
FAST: Factorizable Attention for Speeding up Transformersby Armin Gerami, Monte Hoover, Pranav S. Dulepet, Ramani…
Summary of Graph Structure Inference with Bam: Introducing the Bilinear Attention Mechanism, by Philipp Froehlich and Heinz Koeppl
Graph Structure Inference with BAM: Introducing the Bilinear Attention Mechanismby Philipp Froehlich, Heinz KoepplFirst submitted…
Summary of Generalization Bounds For Heavy-tailed Sdes Through the Fractional Fokker-planck Equation, by Benjamin Dupuis et al.
Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equationby Benjamin Dupuis, Umut ŞimşekliFirst submitted…
Summary of The I/o Complexity Of Attention, or How Optimal Is Flash Attention?, by Barna Saha et al.
The I/O Complexity of Attention, or How Optimal is Flash Attention?by Barna Saha, Christopher YeFirst…
Summary of Summing Up the Facts: Additive Mechanisms Behind Factual Recall in Llms, by Bilal Chughtai et al.
Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMsby Bilal Chughtai, Alan Cooney,…
Summary of Gsina: Improving Subgraph Extraction For Graph Invariant Learning Via Graph Sinkhorn Attention, by Fangyu Ding et al.
GSINA: Improving Subgraph Extraction for Graph Invariant Learning via Graph Sinkhorn Attentionby Fangyu Ding, Haiyang…
Summary of Topological Neural Networks: Mitigating the Bottlenecks Of Graph Neural Networks Via Higher-order Interactions, by Lorenzo Giusti
Topological Neural Networks: Mitigating the Bottlenecks of Graph Neural Networks via Higher-Order Interactionsby Lorenzo GiustiFirst…
Summary of Lirank: Industrial Large Scale Ranking Models at Linkedin, by Fedor Borisyuk et al.
LiRank: Industrial Large Scale Ranking Models at LinkedInby Fedor Borisyuk, Mingzhou Zhou, Qingquan Song, Siyu…
Summary of Video Annotator: a Framework For Efficiently Building Video Classifiers Using Vision-language Models and Active Learning, by Amir Ziai et al.
Video Annotator: A framework for efficiently building video classifiers using vision-language models and active learningby…
Summary of Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings, By Yichen Jiang et al.
Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddingsby Yichen Jiang, Xiang Zhou, Mohit…