Image de couverture de livre

Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Tianyi, Su, Junda, Desai, Aditya, Wu, Oscar, Xu, Zhaozhuo, Shrivastava, Anshumali
Format:	Preprint
Publié:	2024
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

Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM Inference
par: Le, Hoang Anh Duy, et autres
Publié: (2026)

KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
par: Zhang, Tianyi, et autres
Publié: (2024)

NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention
par: Zhang, Tianyi, et autres
Publié: (2024)

LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid
par: Zhang, Tianyi, et autres
Publié: (2024)

To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration
par: Yang, Zeyu, et autres
Publié: (2025)

LLM-Sketch: Enhancing Network Sketches with LLM
par: Li, Yuanpeng, et autres
Publié: (2025)

Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation
par: Ran, Yide, et autres
Publié: (2026)

Empowering Distributed Training with Sparsity-driven Data Synchronization
par: Wang, Zhuang, et autres
Publié: (2023)

Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching
par: Aytes, Simon A., et autres
Publié: (2025)

CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems
par: Zhang, Haochen, et autres
Publié: (2025)

UltraSketchLLM: Saliency-Driven Sketching for Ultra-Low Bit LLM Compression
par: Zou, Sunan, et autres
Publié: (2025)

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
par: Zhang, Tianyi, et autres
Publié: (2025)

Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms
par: Deb, Rohan, et autres
Publié: (2025)

IDentity with Locality: An ideal hash for gene sequence search
par: Desai, Aditya, et autres
Publié: (2024)

Learning Scalable Structural Representations for Link Prediction with Bloom Signatures
par: Zhang, Tianyi, et autres
Publié: (2023)

Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining
par: Zhang, Haochen, et autres
Publié: (2025)

U-Sketch: An Efficient Approach for Sketch to Image Diffusion Models
par: Mitsouras, Ilias, et autres
Publié: (2024)

Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching
par: Zhi, Weiming, et autres
Publié: (2023)

PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels
par: Kacham, Praneeth, et autres
Publié: (2023)

Revisiting Matrix Sketching in Linear Bandits: Achieving Sublinear Regret via Dyadic Block Sketching
par: Wen, Dongxie, et autres
Publié: (2024)

SketchQL Demonstration: Zero-shot Video Moment Querying with Sketches
par: Wu, Renzhi, et autres
Publié: (2024)

SOCKET: SOft Collision Kernel EsTimator for Sparse Attention
par: Joshi, Sahil, et autres
Publié: (2026)

Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels
par: Ahmad, Tamim El, et autres
Publié: (2023)

SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values
par: Zhang, Yunfan, et autres
Publié: (2024)

Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams
par: Feng, Yuan, et autres
Publié: (2025)

SketchOGD: Memory-Efficient Continual Learning
par: Min, Youngjae, et autres
Publié: (2023)

On the (Generative) Linear Sketching Problem
par: Yuan, Xinyu, et autres
Publié: (2026)

Private Sketches for Linear Regression
par: Das, Shrutimoy, et autres
Publié: (2025)

Inference Time Context Sparsity: Illusion or Opportunity?
par: Joshi, Sahil, et autres
Publié: (2026)

Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
par: Schioppa, Andrea
Publié: (2024)

Communication-Efficient Federated Learning over Wireless Channels via Gradient Sketching
par: Gattani, Vineet Sunil, et autres
Publié: (2024)

FLRQ: Faster LLM Quantization with Flexible Low-Rank Matrix Sketching
par: Gul, Hongyaoxing, et autres
Publié: (2026)

Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching
par: Jiang, Shan, et autres
Publié: (2026)

SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation
par: Chereddy, Sathvik, et autres
Publié: (2025)

Private and Communication-Efficient Federated Learning based on Differentially Private Sketches
par: Zhang, Meifan, et autres
Publié: (2024)

Optimized Learned Count-Min Sketch
par: Nishishita, Kyosuke, et autres
Publié: (2025)

Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval
par: Yang, Zeyu, et autres
Publié: (2026)

SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling
par: Ye, Fanjiang, et autres
Publié: (2025)

Adaptive-GraphSketch: Real-Time Edge Anomaly Detection via Multi-Layer Tensor Sketching and Temporal Decay
par: Ekle, Ocheme Anthony, et autres
Publié: (2025)

Sketched Sum-Product Networks for Joins
par: Tsan, Brian, et autres
Publié: (2025)