Data Compression Methods

Follow this topic Ask about this topic

Momentum

46 papers in the last four weeks, up 39% on the four weeks before. 0.6% of all new papers.

Jul 6Week of Sep 21

Latest papers 324

All topics

HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders
Feb 24, 2026Kun Yuan, Junyu Bi, Daixuan Cheng +5Real-World Content Recommendation Problem Recommendation
Alibaba Group · Beijing, China · Renmin University
DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce
Feb 9, 2026Wenchen Han, Shay Vargaftik, Michael Mitzenmacher +1Gradient Quantization Pytorch
University College London · VMware Research by Broadcom · Harvard University +1
ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure
Feb 1, 2026Jie Deng, Shining Liang, Jun Li +2Large Reasoning Models Reasoning Traces
University of Chinese Academy of Sciences, Beijing, China · 2Microsoft, Beijing, China · 3Tongji University, Shanghai, China
EDGC: Entropy-driven Dynamic Gradient Compression for Efficient LLM Training
Nov 13, 2025Qingao Yi, Jiaang Duan, Jun Zhang +5Large Language Model Training Task-Aware Compression
University of Shanghai for Science and Technology, Shanghai, China · Shanghai Jiao Tong University, Shanghai, China · Zhejiang University, Hangzhou, China
Real-Time Neural Video Compression with Unified Intra and Inter Coding
Oct 16, 2025Hui Xiang, Yifan Bian, Li Li +3Video Compression Data Compression Methods
University of Science and Technology of China · Tencent Shannon Lab
BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression
Sep 29, 2025David González-MartínezLow-Rank Structure Data Compression Methods
Department of Computer Science and Artificial Intelligence, Universidad de Sevilla · Tübingen AI Center
CompLLM: Compression for Long Context Q&A
Sep 23, 2025Gabriele Berton, Jayakrishnan Unnikrishnan, Son Tran +1Efficient Long-Context Inference Large Language Model Compression
Amazon · Center For Research in Computer Vision, University of Central Florida
EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation
Sep 15, 2025Jingyu Xiao, Zhongyi Zhang, Yuxuan Wan +3Token Compression Image-To-Code Generation
The Chinese University of Hong Kong, Hong Kong, China · Huazhong University of Science and Technology, Wuhan, China · Singapore Management University, Singapore, Singapore +1
Reward function compression facilitates goal-dependent reinforcement learning
Sep 8, 2025Gaia Molinaro, Anne G. E. CollinsGoal-Conditioned Reinforcement Learning Reward Functions
University of California, Berkeley Berkeley, CA 94704
On the Interaction of Compressibility and Adversarial Robustness
Jul 23, 2025Melih Barsbey, Antônio H. Ribeiro, Umut Şimşekli +1Compressed Model Data Compression Methods
Department of Computing, Imperial College London, UK · Department of Information Technology, Uppsala University, Sweden · INRIA, CNRS, Département d’Informatique de l’Ecole Normale Supérieure / PSL, France
GeLaCo: An Evolutionary Approach to Layer Compression
Jul 14, 2025David Ponce, Thierry Etchegoyhen, Javier Del SerLarge Language Model Compression Compressed Model
Fundación Vicomtech, Basque Research and Technology Alliance (BRTA) · University of the Basque Country UPV/EHU · TECNALIA. Basque Research and Technology Alliance (BRTA)
Squeeze3D: Extreme Neural Compression with Latent Space Bridging
Jun 9, 2025Rishit Dagli, Yushi Guan, Sankeerth Durvasula +2Large-Scale 3D Editing Dataset 3D Generation
University of Toronto
Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism
Jun 2, 2025Sameera Ramasinghe, Thalaiyasingam Ajanthan, Gil Avraham +2Compressed Model Decentralized Learning
Pluralis Research
InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing
May 28, 2025Shuaiyi Li, Zhisong Zhang, Yang Deng +6Multimodal Knowledge Editing Edit
The Chinese University of Hong Kong · City University of Hong Kong · Singapore Management University +1
Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks
May 26, 2025Safa Hamreras, Sukhbinder Singh, Román OrúsTensor Networks Neural Network
Donostia International Physics Center, Paseo Manuel de Lardizabal 4, E-20018 San Sebastián, Spain · Multiverse Computing, Spadina Ave., Toronto, ON M5T 2C2, Canada · Multiverse Computing, Paseo de Miramón 170, E-20014 San Sebastián, Spain
Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Efficient Reasoning
May 13, 2025Ren ZhuangChain-of-Thought Reasoning Skip
School of Information Science and Technology, Hangzhou Normal University
Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
Feb 3, 2025Siqi Zeng, Yifei He, Meitong Liu +5Task-Aware Compression Data Compression Methods
University of Illinois Urbana-Champaign · University of Pennsylvania · Okinawa Institute of Science and Technology
QABBA: Symbolic Time-Series Compression via Integer-Quantized Aggregation
Nov 20, 2024Erin Carson, Xinye Chen, Fei He +1Task-Aware Compression Data Compression Methods
Department of Numerical Mathematics, Charles University, Prague, Czech Republic · LIP6, Sorbonne Université, CNRS, Paris, France · Centre for Computational Science and Mathematical Modelling, Coventry University, Coventry, United Kingdom +1
FastE: Readout-Triggered Token Compression for LLM Embedding Inference
Date pendingJinsong Shu, Jinyong Wen, Baokun Wang +4Large Language Model Compression Qwen3
Zhejiang University · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security · Ant Group +1
SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting
Date pendingSeokhyun Youn, Soohyun Lee, Geonho Kim +3Gaussian Splatting Gaussian Primitives
Kyung Hee University, South Korea · Kyung Hee University, Seoul, South Korea
Statistical Mechanics of Semantic Compression
Date pendingTankut CanData Compression Methods Statistical Physics
Department of Physics, Emory University, Atlanta, GA
SeDeM: Selective Decompression of Hidden-State Memories for Long-Context Question Answering
Date pendingMaryam Haghifam, Jason Cong, Yizhou SunEfficient Long-Context Inference Long-Context Reasoning
University of California, Los Angeles, USA
UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures
Date pendingHoma Esfahanizadeh, Matin Mortaheb, Adeel Mahmood +2Task-Aware Compression Data Compression Methods
Nokia Bell Labs, Murray Hill, NJ 07974, USA
LLM Compression by Block Removal with Constrained Binary Optimization
Date pendingDavid Jansen, Roman Rausch, Ali Hashemi +2Large Language Model Compression Data Compression Methods
Multiverse Computing · Donostia International Physics Center Ikerbasque Foundation for Science

Feb 24, 2026, cs.IRJ/K move · Enter open · S save

HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders

Kun Yuan, Junyu Bi, Daixuan Cheng, Changfa Wu+4

Alibaba Group · Beijing, China · Renmin University

Real-World Content Recommendation Problem Recommendation Sequence Modeling Data Compression Methods

Open paper AskPDF arXiv

Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints. While summarizing history via interest centers offers a practical alternative, existing methods struggle to (1) identify user-specific centers at appropriate granularity and (2) accurately assign behaviors, leading to quantization errors and loss of long-tail preferences. To alleviate these issues, we propose Hierarchical Sparse Activation Compression (HiSAC), an efficient framework for personalized sequence modeling. HiSAC encodes interactions into multi-level semantic IDs and constructs a global hierarchical codebook. A hierarchical voting mechanism sparsely activates personalized interest-agents as fine-grained preference centers. Guided by these agents, Soft-Routing Attention aggregates historical signals in semantic space, weighting by similarity to minimize quantization error and retain long-tail behaviors. Deployed on Taobao's "Guess What You Like" homepage, HiSAC achieves significant compression and cost reduction, with online A/B tests showing a consistent 1.65% CTR uplift -- demonstrating its scalability and real-world effectiveness.

Momentum

Related topics

Latest papers 324