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

High-Fidelity Video Compression based on Invertible Neural Transform and Implicit Conditioning
Jun 11, 2026Siyue Teng, Ho Man Kwan, Yuxuan Jiang +2Video Compression Video Coding
Visual Information Lab, University of Bristol, UK
MemRefine: LLM-Guided Compression for Long-Term Agent Memory
Jun 11, 2026Minjae Kim, Jinheon Baek, Soyeong Jeong +1Long-Term Agent Memory Large Language Model Memory
Korea University · KAIST
REACH: Interpretability-Driven Feature Identification and Architecture Compression for Multi-Channel Vehicular Channel Estimation
Jun 10, 2026Simbarashe Aldrin Ngorima, Albert Helberg, Marelie H. DavelChannel Estimation Channel
Faculty of Engineering, North-West University, South Africa · Centre for Artificial Intelligence Research, South Africa · National Institute for Theoretical and Computational Sciences, South Africa
Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering
Jun 10, 2026Haoning Xu, Zhaoqing Li, Huimeng Wang +4Task-Aware Compression Unstructured Pruning
The Chinese University of Hong Kong, Hong Kong SAR, China · National Research Council Canada, Canada
Signed Compression Progress on a Sealed Audit is Goodhart-Resistant
Jun 9, 2026Ayush Mittal, Dhruv GuptaModel Auditing Bounded Adversary
What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents
Jun 9, 2026Martin Andres Bertran, Aaron Roth, Zhiwei Steven WuMle-Bench Lite Overfitting
Amazon Responsible AI · University of Pennsylvania · Carnegie Mellon University
Hidden Consensus:Preference-Validity Compression in Human Feedback
Jun 9, 2026Dorcas Chia Ern Chua, Karen Myn Hui Lee, Jia Yue Tan +9Preference Alignment Reinforcement Learning From Human Feedback
1YTL AI Labs · 2Universiti Malaya
Few-step Generative Models as Lossy Compression
Jun 9, 2026Fuma Kimishima, Jinjia ZhouGenerative Image Compression Data Compression Methods
Hosei University, Tokyo, Japan
MAAM: Anchor-Preserving Compression and Contextual Calibration for Chinese Discriminatory Language Detection
Jun 8, 2026Yuxin Fu, Shijing SiSemantic Anchor Data Compression Methods
School of Economics and Finance, Shanghai International Studies University · Shanghai, China
The Bioelectrical Information Theory: Investigating the theoretical compression limit of bioelectrical signals under artificial intelligence
Jun 7, 2026Jiawen Zou, Bo YanBrain-Computer Interface Information-Theoretic Limits
College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai 200433, P.R. China
TextEconomizer: Enhancing Lossy Text Compression with Denoising Transformers and Entropy Coding
Jun 6, 2026Mahbub E Sobhani, Anika Tasnim Rodela, Chowdhury Mofizur Rahman +2Data Compression Methods Transformer Architectures
United International University, Department of Computer Science and Engineering Dhaka, Bangladesh · BRAC University, Department of Computer Science and Engineering Dhaka, Bangladesh · Southeast University, Department of Computer Science and Engineering Dhaka, Bangladesh
Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents
Jun 6, 2026Xinyu Guan, Qianyang Zhao, Yuming DengContextual Reasoning Language-Model Agents
Alibaba Group, China
Planning-aligned Token Compression for Long-Context Autonomous Driving
Jun 5, 2026Zhixuan Liang, Yuxiao Chen, Yurong You +12Token Compression Autonomous Driving
NVIDIA Research · School of Computing and Data Science, The University of Hong Kong
SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices
Jun 5, 2026Ernests Lavrinovics, Marco Letizia, Roy Janco +3Large Language Model Compression Data Compression Methods
Department of Computer Science, Aalborg University Copenhagen, Denmark · MaLGa-DIBRIS, University of Genoa, Genoa, Italy · INFN, Sezione di Genova, Genoa, Italy +2
MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering
Jun 4, 2026Qing Yang, Pengcheng Huang, Xinze Li +6Long Video Question Answering Peak Memory
School of Computer Science and Engineering, Northeastern University, Shenyang, China · Department of Computer Science and Technology, Tsinghua University, Beijing, China · Digital China Group, Beijing, China
Balancing Image Compression and Generation with Bootstrapped Tokenization
Jun 4, 2026Haozhe Chi, Jinghan Li, Hao Jiang +4Visual Tokenizers Autoregressive Image Generation
1Peking University · 2Central Media Technology Institute, Huawei
Learned Subspace Compression for Communication-Efficient Pipeline Parallelism
Jun 3, 2026Paul Janson, Edouard Oyallon, Eugene BelilovskySubspace Data Compression Methods
Concordia University · Mila Quebec AI Institute · CNRS, Sorbonne University
Residual Modeling for High-Fidelity Learned Compression of Scientific Data
Jun 3, 2026Liangji Zhu, Sanjay Ranka, Anand RangarajanGenerative Image Compression Data Compression Methods
Department of Computer & Information Science & Engineering University of Florida Gainesville, FL, USA
Prediction Under Imperfect Compression: A Theory of Approximate MDL
Jun 3, 2026Qian Li, Xinyu Mao, Shang-Hua Teng +1Model Selection Prediction Error
Shenzhen Research Institute of Big Data · University of Southern California
Beyond Compression: Quantifying Spectral Accessibility in Vision Representations
Jun 2, 2026Akayou A. Kitessa, Yijun ZhaoVision Encoders Spectral
Fordham University New York City, NY
Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines
Jun 2, 2026Justice Owusu Agyemang, Jerry John Kponyo, Kwame Opuni-Boachie Obour Agyekum +3Token Compression Token-Level Entropy
1VIA Cybersecurity Lab, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana · 2Quantum and Assistive Technologies Lab, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana
LLM Compression with Jointly Optimizing Architectural and Quantization choices
Jun 2, 2026Hoang-Loc La, Truong-Thanh Le, Amir Taherkordi +1Large Language Model Compression LLM Inference Optimization
UiT The Arctic University of Norway · University of Oslo, Norway
PrimeSVT: An Automated Memory-aware Pruning Framework with Prioritized Compression Policy for Spiking Vision Transformers
Jun 2, 2026Rachmad Vidya Wicaksana Putra, Achyuta Muthuvelan, Alberto Marchisio +1Self-Supervised Vision Transformers Data Compression Methods
eBRAIN Lab, Division of Engineering, New York University (NYU) Abu Dhabi, United Arab Emirates (UAE)
HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression
Jun 1, 2026Minghui Zheng, Hongxu Chen, Huimin Ren +8Large Language Model Compression Chain-of-Thought Reasoning
Li Auto Inc.
EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models
Jun 1, 2026Hongyu Lu, Feng Zhang, Wenwei Jin +5Token Compression Vision Encoders
Harbin Institute of Technology · Xiaohongshu · Fudan University
Spatially Distributed Task-Oriented Compression for Multi-Emitter Localization and Characterization with Spectral Overlap
May 31, 2026H. Nazim Bicer, J. Nicholas LanemanTask-Aware Compression Data Compression Methods
Dept. of Electrical Engineering University of Notre Dame Notre Dame, IN, USA
Neural Network Compression by Approximate Differential Equivalence
May 31, 2026Ravi Dhiman, Andrea Passarella, Mirco Tribastone +1Compressed Model Neural Approximations
IMT School for Advanced Studies Lucca 55100, Italy · IIT CNR, Pisa 56124, Italy
LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning
May 31, 2026Mengmeng Ji, Ravi Shanker Raju, Jonathan Lingjie Li +1Efficient Long-Context Inference Long-Context Reasoning
SambaNova Systems, Inc. San Jose, CA, USA
When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression
May 31, 2026Riku Kisako, Hayato Tsukagoshi, Ryohei SasanoText Embeddings Data Compression Methods
Graduate School of Informatics, Nagoya University
Collaborative Few-Step Distillation and Low-Bit Quantization for Wan2.2 Dual-Expert Video Diffusion Models
May 30, 2026Jinyang Du, Shenghao Jin, Ziqian Xu +5Video Diffusion Models Diffusion Models
SenseTime
ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs
May 30, 2026Yiling Gao, Hongchen Wei, Zhenzhong ChenToken Compression Dataset Distillation
School of Remote Sensing and Information Engineering, Wuhan University
ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression
May 30, 2026Wenya Yu, Chao Zhang, Li Wang +2Large Language Model Quantization Post-Training Quantization
School of Mathematics and Statistics, Central South University, Changsha, China · Department of Computer Science, Central South University, Changsha, China · CRAN, Université de Lorraine, CNRS, Nancy, France +1
Skill Reuse as Compression in Agentic RL
May 29, 2026Zhikun Xu, Yu Feng, Jacob Dineen +3Agentic Reinforcement Learning Large Language Model Agents
Arizona State University · University of Pennsylvania · University of Southern California
Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
May 29, 2026Johannes Schusterbauer, Jannik Wiese, Nick Stracke +2Precipitation Nowcasting Rectified Flow
Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Parameter Compression of Deep Neural Networks
May 28, 2026Andrzej Cichocki, Michal WietczakTensor Networks Compressed Model
Systems Research Institute of Polish Academy of Science and Warsaw University of Technology, Poland
Adaptive Targeted Dynamic Chunking for Tokenization-Free Hierarchical Model
May 28, 2026Thang Dang, Akira Nakagawa, Kenichi Kobayashi +1Chunk Data Compression Methods
Fujitsu Research of America · Pittsburgh, PA, USA · Fujitsu Limited +1
Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation
May 28, 2026Mark WalshSufficiency Arbitration
EarlyTom: Early Token Compression Completes Fast Video Understanding
May 28, 2026Hesong Wang, Xin Jin, Lu Lu +4Token Compression Vision Encoders
Zhejiang University · Westlake University · Alibaba Cloud Computing
Accelerating Constrained Decoding with Token Space Compression
May 28, 2026Michael Sullivan, Alexander KollerToken Compression Context-Free Grammars
Department of Language Science and Technology Saarland Informatics Campus Saarland University, Saarbrücken, Germany
Moment-KV: Momentum-Based Decode-Time KV Cache Compression for Long Generation
May 28, 2026Soumyadeep Jana, Sagar Nishad, Sanasam Ranbir SinghKey-Value Cache Compression Large Language Model Decoding
Indian Institute of Technology Guwahati, India
BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base
May 28, 2026Rohan ShravanByte-Pair Encoding Tokenizer
The School of AI India
Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor
May 27, 2026Guoxin Ma, Yibing Liu, Chengzhengxu Li +7Efficient Long-Context Inference LLM Inference Optimization
Baidu Inc., Beijing, China · Xi’an Jiaotong University · City University of Hong Kong +1
ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay
May 27, 2026Zhexin Hu, Li Wang, Xiaohan Wang +4Data Compression Methods Hindsight
1Meituan · Institute of Software, Chinese Academy of Sciences
Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression
May 26, 2026Kabir Swain, Sijie Han, Daniel Karl I. Weidele +3Key-Value Cache Quantization Key-Value Cache Compression
Massachusetts Institute of Technology, Cambridge, MA, USA · University of Toronto, Toronto, Canada · IBM Research, Cambridge, MA, USA.
O-MARC: Omni Memory-Augmented Compression Distillation for Efficient Video Understanding
May 26, 2026Peiran Wu, Yunze Liu, Chi-Hao Wu +2Audio-Visual Reasoning Video Understanding
University of Bristol · Memories.ai Research · University of Central Florida
Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion
May 25, 2026Tuna Tuncer, Felix Becker, Thomas PfeilAutoregressive Video Diffusion Models Key-Value Cache Quantization
1Technical University of Munich · 2Tensordyne
Scale When Needed: Adaptive Neuron-level Mixed Precision Quantization Aware Training
May 24, 2026Ayush K. Varshney, Konstantinos Vandikas, Šarūnas Girdzijauskas +2Mixed-Precision Quantization Quantization-Aware Training
Ericsson Research, Ericsson AB, Stockholm, Sweden · KTH Royal Institute of Technology, Stockholm, Sweden · RISE Research Institutes of Sweden, Stockholm, Sweden
SemanticZip: A Pilot Framework for Lossy Text Compression with LLMs as Semantic Decompressors
May 23, 2026Natalia Trukhina, Vadim VashkelisLarge Language Model Compression Data Compression Methods
Embedded Intelligence Lab (EMILAB)
WorldKV: Efficient World Memory with World Retrieval and Compression
May 21, 2026Jung Yi, Minjae Kim, Paul Hyunbin Cho +3Video World Models Autoregressive Video Diffusion Models
1KAIST AI · 2Naver AI Lab
DIVE: Embedding Compression via Self-Limiting Gradient Updates
May 20, 2026Dongfang ZhaoTask-Aware Compression Data Compression Methods
Quantized Machine Learning Models for Medical Imaging in Low-Resource Healthcare Settings
May 19, 2026Sumanth Meenan Kanneti, Aryan ShahQuantization-Aware Training Mobilenetv2
Georgia State University · University of Southern California
Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs
May 18, 2026Junyi Wu, Tianchen Zhao, Shaoqiu Zhang +3Diffusion Language Models Large Language Model Decoding
Tsinghua University · Shanghai Jiao Tong University · Infinigence AI
CATRF: Codec-Adaptive TriPlane Radiance Fields for Volumetric Content Delivery
May 18, 2026Tung-I Chen, Lingdong Wang, Subhransu Maji +1Volumetric Video Wireless Radiance Field
University of Massachusetts Amherst
OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
May 18, 2026Morunliu Yang, Ruotao Xu, Le Li +6Visual Token Pruning Modality-Specific Encoders
1Soochow University · Peking University
TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
May 18, 2026Zhaoyuan Ding, Yijing Yang, Han Shu +1Video Object Segmentation Segment Anything Model
Huawei Noahs Ark Lab
Inter-LPCM: Learning-based Inter-Frame Predictive Coding for LiDAR Point Cloud Compression
May 18, 2026Chang Sun, Hui Yuan, Shiqi Jiang +3Light Detection And Ranging Point Clouds Point Clouds
School of Control Science and Engineering, Shandong University, Jinan 250061, China · Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan 250061, China · School of Computer Science and Technology, Shandong University, Qingdao, 266237, China +1
Deep learning-based compression of giga-resolution whole slide images
May 17, 2026Maren Høibø, Etienne Gaucher, Ingerid Reinertsen +2Whole-Slide Images Learned Image Compression
Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology (NTNU), NO-7491 Trondheim, Norway · Department of Health Research, SINTEF Digital, NO-7465 Trondheim, Norway · Department of Circulation and Medical Imaging, Norwegian University of Science and Technology (NTNU), NO-7491 Trondheim, Norway +1
Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compression
May 17, 2026Natalia Trukhina, Vadim VashkelisLarge Language Model Compression Context Length
Embedded Intelligence Lab (EMILAB)
IO-SVD: Input-Output Whitened SVD for Adaptive-Rank LLM Compression
May 15, 2026Ali Abbasi, Chayne Thrash, Haoran Qin +2Large Language Model Compression Singular Value Decomposition
Vanderbilt University · University of California, Davis
KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy
May 14, 2026Yingbing Huang, Tharun Adithya Srikrishnan, Steven K. Reinhardt +1Key-Value Cache Compression Token Compression
University of Illinois Urbana-Champaign · AMD

Jun 11, 2026, eess.IVJ/K move · Enter open · S save

High-Fidelity Video Compression based on Invertible Neural Transform and Implicit Conditioning

Siyue Teng, Ho Man Kwan, Yuxuan Jiang, Fan Zhang+1

Visual Information Lab, University of Bristol, UK

Video Compression Video Coding Data Compression Methods Distortion

Open paper AskPDF arXiv

Learning-based video compression has recently achieved competitive rate-distortion performance compared to conventional video codecs. However, most existing methods rely on non-invertible analysis-synthesis transforms, with reconstruction quality subject to both quantization and transform approximation errors. This limitation becomes particularly restrictive at higher quality points, where quantization errors are small and transform-induced distortion dominates. To address this, we propose InnVC, an Invertible neural network based Video Codec for wide-range and high-fidelity compression. The core idea is to preserve an invertible main transform path prior to quantization, while injecting content-adaptive context through a compact implicit conditioning field. This decouples strongly correlated video content from harder-to-model fine details, allowing different components to specialize in complementary reconstruction tasks for more efficient compression. To further improve compressibility, we introduce a scheduled masking strategy that progressively concentrates informative content into fewer latent channels for more effective entropy coding. Experiments on the UVG and MCL-JCV benchmarks show that InnVC achieves strong compression performance over a broad quality range, being particularly effective in the high-quality regime, yielding BD-rate reductions of 21.66% in PSNR and 46.06% in MS-SSIM relative to x265 on UVG. To the best of our knowledge, InnVC is the first neural video codec covers operating poins from low bitrate to high fidelity within a single architecture scale, spanning more than 20 dB in PSNR.

Momentum

Related topics

Latest papers 324