:: Library Catalog

Imagen de Portada

Guardado en:

Detalles Bibliográficos
Autores principales:	Choudhary, Sakshi, Saxena, Utkarsh, Roy, Kaushik
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	https://arxiv.org/abs/2604.09406
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Eigen Attention: Attention in Low-Rank Space for KV Cache Compression
por: Saxena, Utkarsh, et al.
Publicado: (2024)

TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
por: Nagaraj, Manish, et al.
Publicado: (2025)

KVLinC : KV Cache Quantization with Hadamard Rotation and Linear Correction
por: Saxena, Utkarsh, et al.
Publicado: (2025)

Averaging Rate Scheduler for Decentralized Learning on Heterogeneous Data
por: Aketi, Sai Aparna, et al.
Publicado: (2024)

SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data
por: Choudhary, Sakshi, et al.
Publicado: (2024)

CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning
por: Apolinario, Marco Paul E., et al.
Publicado: (2024)

ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
por: Saxena, Utkarsh, et al.
Publicado: (2024)

Memory-Efficient LLM Training with Online Subspace Descent
por: Liang, Kaizhao, et al.
Publicado: (2024)

PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training
por: Li, Yanyi, et al.
Publicado: (2026)

LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning
por: Apolinario, Marco Paul E., et al.
Publicado: (2025)

SPREAD: Subspace Representation Distillation for Lifelong Imitation Learning
por: Roy, Kaushik, et al.
Publicado: (2026)

SlimDiff: Training-Free, Activation-Guided Hands-free Slimming of Diffusion Models
por: Roy, Arani, et al.
Publicado: (2025)

Learning When to Attend: Conditional Memory Access for Long-Context LLMs
por: Choudhary, Sakshi, et al.
Publicado: (2026)

MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning
por: Awasthi, Ankita, et al.
Publicado: (2026)

A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models
por: Chen, Yiming, et al.
Publicado: (2025)

HCiM: ADC-Less Hybrid Analog-Digital Compute in Memory Accelerator for Deep Learning Workloads
por: Negi, Shubham, et al.
Publicado: (2024)

Scalable Neural Network Training over Distributed Graphs
por: Kolluri, Aashish, et al.
Publicado: (2023)

SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
por: Refael, Yehonathan, et al.
Publicado: (2025)

Post Training Quantization of Large Language Models with Microscaling Formats
por: Sharify, Sayeh, et al.
Publicado: (2024)

On the Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars
por: Tao, Chun, et al.
Publicado: (2021)

CompAct: Compressed Activations for Memory-Efficient LLM Training
por: Shamshoum, Yara, et al.
Publicado: (2024)

EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference
por: Kaushik, Prakhar, et al.
Publicado: (2025)

CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
por: Yang, Zi, et al.
Publicado: (2024)

Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy
por: Li, Tao, et al.
Publicado: (2024)

Randomized Gradient Subspaces for Efficient Large Language Model Training
por: Rajabi, Sahar, et al.
Publicado: (2025)

Efficient Resource-Constrained Training of Transformers via Subspace Optimization
por: Nguyen, Le-Trung, et al.
Publicado: (2025)

Attacking Byzantine Robust Aggregation in High Dimensions
por: Choudhary, Sarthak, et al.
Publicado: (2023)

SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness
por: Kodge, Sangamesh, et al.
Publicado: (2024)

ELLA: Efficient Lifelong Learning for Adapters in Large Language Models
por: Biswas, Shristi Das, et al.
Publicado: (2026)

COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
por: Xi, Haocheng, et al.
Publicado: (2024)

Understanding In-context Learning of Addition via Activation Subspaces
por: Hu, Xinyan, et al.
Publicado: (2025)

Thinking Forward: Memory-Efficient Federated Finetuning of Language Models
por: Panchal, Kunjal, et al.
Publicado: (2024)

Shared LoRA Subspaces for almost Strict Continual Learning
por: Kaushik, Prakhar, et al.
Publicado: (2026)

FINDER: Stochastic Mirroring of Noisy Quasi-Newton Search and Deep Network Training
por: Suman, Uttam, et al.
Publicado: (2024)

WWW: What, When, Where to Compute-in-Memory
por: Sharma, Tanvi, et al.
Publicado: (2023)

Inverted Activations: Reducing Memory Footprint in Neural Network Training
por: Novikov, Georgii, et al.
Publicado: (2024)

The Universal Weight Subspace Hypothesis
por: Kaushik, Prakhar, et al.
Publicado: (2025)

Auction-Based Online Policy Adaptation for Evolving Objectives
por: Shabadi, Guruprerana, et al.
Publicado: (2026)

AdaGossip: Adaptive Consensus Step-size for Decentralized Deep Learning with Communication Compression
por: Aketi, Sai Aparna, et al.
Publicado: (2024)

Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
por: Ravikumar, Deepak, et al.
Publicado: (2024)