Image de couverture de livre

SPECTRE: An FFT-Based Efficient Drop-In Replacement to Self-Attention for Long Contexts

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fein-Ashley, Jacob, Gupta, Neelesh, Kannan, Rajgopal, Prasanna, Viktor
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Studying the Effects of Self-Attention on SAR Automatic Target Recognition
par: Fein-Ashley, Jacob, et autres
Publié: (2024)

Contextual Feedback Loops: Amplifying Deep Reasoning with Iterative Top-Down Feedback
par: Fein-Ashley, Jacob, et autres
Publié: (2024)

Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say
par: Fein-Ashley, Jacob, et autres
Publié: (2025)

Attention, Distillation, and Tabularization: Towards Practical Neural Network-Based Prefetching
par: Zhang, Pengmiao, et autres
Publié: (2023)

A Persistent-State Dataflow Accelerator for Memory-Bound Linear Attention Decode on FPGA
par: Gupta, Neelesh, et autres
Publié: (2026)

A Single Graph Convolution Is All You Need: Efficient Grayscale Image Classification
par: Fein-Ashley, Jacob, et autres
Publié: (2024)

PaCKD: Pattern-Clustered Knowledge Distillation for Compressing Memory Access Prediction Models
par: Gupta, Neelesh, et autres
Publié: (2024)

Enabling Long FFT Convolutions on Memory-Constrained FPGAs via Chunking
par: Wang, Peter, et autres
Publié: (2025)

Benchmarking Deep Learning Classifiers for SAR Automatic Target Recognition
par: Fein-Ashley, Jacob, et autres
Publié: (2023)

Do LLM-derived graph priors improve multi-agent coordination?
par: Gupta, Nikunj, et autres
Publié: (2026)

TypeBandit: Type-Level Context Allocation and Reweighting for Effective Attribute Completion in Heterogeneous Graph Neural Networks
par: Wang, Ta-Yang, et autres
Publié: (2026)

Adversarial Training in Low-Label Regimes with Margin-Based Interpolation
par: Ye, Tian, et autres
Publié: (2024)

Latent Denoising Improves Visual Alignment in Large Multimodal Models
par: Parikh, Dhruv, et autres
Publié: (2026)

Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information
par: Akgül, Ömer Faruk, et autres
Publié: (2024)

HierRouter: Coordinated Routing of Specialized Large Language Models via Reinforcement Learning
par: Gupta, Nikunj, et autres
Publié: (2025)

ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning
par: Parikh, Dhruv, et autres
Publié: (2025)

FACTUAL: A Novel Framework for Contrastive Learning Based Robust SAR Image Classification
par: Wang, Xu, et autres
Publié: (2024)

TabConv: Low-Computation CNN Inference via Table Lookups
par: Gupta, Neelesh, et autres
Publié: (2024)

Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning
par: Gupta, Nikunj, et autres
Publié: (2025)

SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning
par: Gupta, Nikunj, et autres
Publié: (2026)

Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning
par: Gupta, Nikunj, et autres
Publié: (2026)

Context-Driven Performance Modeling for Causal Inference Operators on Neural Processing Units
par: Gupta, Neelesh, et autres
Publié: (2025)

Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants
par: Deng, Gangda, et autres
Publié: (2024)

Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours
par: Yang, Yuxin, et autres
Publié: (2024)

Iterate to Accelerate: A Unified Framework for Iterative Reasoning and Feedback Convergence
par: Fein-Ashley, Jacob
Publié: (2025)

Linear Diffusion Networks
par: Fein-Ashley, Jacob
Publié: (2025)

Flowing Through Layers: A Continuous Dynamical Systems Perspective on Transformers
par: Fein-Ashley, Jacob
Publié: (2025)

A Comparison of Traditional and Deep Learning Methods for Parameter Estimation of the Ornstein-Uhlenbeck Process
par: Fein-Ashley, Jacob
Publié: (2024)

RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion
par: Akgül, Ömer Faruk, et autres
Publié: (2025)

TIGER-MARL: Enhancing Multi-Agent Reinforcement Learning with Temporal Information through Graph-based Embeddings and Representations
par: Gupta, Nikunj, et autres
Publié: (2025)

ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models
par: Parikh, Dhruv, et autres
Publié: (2026)

PAHD: Perception-Action based Human Decision Making using Explainable Graph Neural Networks on SAR Images
par: Wijeratne, Sasindu, et autres
Publié: (2024)

LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
par: Akgül, Ömer Faruk, et autres
Publié: (2025)

Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study
par: Deng, Gangda, et autres
Publié: (2025)

Solve the Loop: Attractor Models for Language and Reasoning
par: Fein-Ashley, Jacob, et autres
Publié: (2026)

LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference
par: Wang, Guangtao, et autres
Publié: (2025)

TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning
par: Deng, Gangda, et autres
Publié: (2024)

Accelerating Sparse MTTKRP for Small Tensor Decomposition on GPU
par: Wijeratne, Sasindu, et autres
Publié: (2025)

AMPED: Accelerating MTTKRP for Billion-Scale Sparse Tensor Decomposition on Multiple GPUs
par: Wijeratne, Sasindu, et autres
Publié: (2025)

Sparse MTTKRP Acceleration for Tensor Decomposition on GPU
par: Wijeratne, Sasindu, et autres
Publié: (2024)