Compressed Model

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, up 25% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 41

All topics

A Tilted Bowl Is Not a Slippery Slope: Compressing Looped Models
Sep 30, 2026Steven Kolawole, Pearse Jim, Opegbemi M. Busoye +2Compressed Model Model Weights
Carnegie Mellon University · ML Collective
KV-Kaizen: Learning Context-Adaptive Cache Compression Choices
Sep 29, 2026Joao Monteiro, Louis Béthune, Anastasiia Filippova +3Key-Value Cache Compression Large Language Model Compression
Apple
FairCompressAgent: An Agentic Framework for Fairness-Aware Model Compression for FPGA Deployment
Sep 15, 2026Yuanbo Guo, Yiyu ShiCompressed Model Quantization-Aware Training
Department of Computer Science and Engineering University of Notre Dame Notre Dame, USA
The Cost of Compression: A Rate-Distortion Limit on Factual Hallucination
Sep 14, 2026Xi Wang, Shijia Xu, Rongfeng GuoFactual Recall Visual Hallucinations
Hefei Institutes of Physical Science, Chinese Academy of Sciences, China · University of Science and Technology of China, China · Chongqing University, China +1
On the Interaction Between Model Compression and Test-Time Adaptation
Sep 3, 2026Francesco Corti, Dong Wang, Young D. Kwon +2Stable Test-Time Adaptation Compressed Model
Graz University of Technology Graz, Austria · Samsung AI Center-Cambridge University of Cambridge Cambridge, United Kingdom · University of Cambridge Cambridge, United Kingdom +1
Emergence of Fibrations, Compression, and Symmetry Breaking in Artificial Neural Networks
Sep 1, 2026Osvaldo M Velarde, Lucas C Parra, Alireza Hashemi +1Symmetry Compressed Model
Levich Institute and Physics Department, City College of New York, 160 Convent Ave, NY, 10031, NY, USA. · Biomedical Engineering Department, City College of New York, 160 Convent Ave, NY, 610101, NY, USA.
Linear Reusable Neural Bases Architecture for Network Compression
Sep 1, 2026Binshuai Wang, Peng Wei, Mahyar GhazanfariCompressed Model Recurrent Neural Networks
Department of Computer Science The George Washington University Washington D.C., USA
Breaking the Compression Barrier: Cross-Architecture Compression Boundary Learning via Reverse Regrowth
Aug 17, 2026Zhaocen Liu, Satvik Praveen, Yi ShengCompressed Model Task-Aware Compression
University of British Columbia Vancouver, British Columbia, CA · University of South Florida Tampa, Florida, USA
UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models
Aug 9, 2026Lei Xin, Bin Gu, Peize Li +8Experts Compressed Model
Kuaishou Technology · Hohai University · Wuhan University +4
ZIPBrain: Can EEG Foundation Models Be Faster, Locally Deployable, but Accurate?
Aug 7, 2026Lingwei Li, Yirong Kan, Peng Chen +3Electroencephalography Foundation Models Electroencephalography
Nara Institute of Science and Technology, Nara, Japan · RIKEN Center for Computational Science, Hyogo, Japan · University of Illinois Urbana-Champaign, USA +1
Topological Simplification in Predictive Coding Networks
Aug 3, 2026Adam Shaw, Jiayu Li, Michael Sperling +2Predictive Coding Compressed Model
University of Southern California 3551 Trousdale Parkway, Los Angeles, CA 90089
Kilobyte Models: Neural Networks as a Seed and a Quantized Latent
Aug 1, 2026Sahil Rajesh DhayalkarCompressed Model Model Weights
Arizona State University
SparseKAN: Compressing Kolmogorov--Arnold Networks Across Basis Functions, Neurons, and Bits
Aug 1, 2026Kazi Ahmed Asif Fuad, Lizhong ChenKolmogorov-Arnold Networks Compressed Model
Department of EECS Oregon State University Corvallis, OR 97331
Progressive $^2$ : A Teacher-Student Progressive Co-Evolving Knowledge Distillation Method for Substantial Model Compression
Jul 31, 2026Tiancong Cheng, Ying Zhang, Zhiwen Yu +2Teacher-Student Distillation Knowledge Distillation
School of Computer Science, Northwestern Polytechnical University, Xi’an 710129, China
Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution
Jul 30, 2026I. Kennedy, T. KennedyLarge Language Model Safety Compressed Model
Memory Efficient Tabular Foundation Models
Jul 30, 2026Shuting Luo, Monika Mikhail Kanaan, Cameron Gordon +2Tabular Foundation Models Tabular Learning
Commonwealth Bank of Australia, Australia · Australian Institute for Machine Learning, University of Adelaide, Adelaide, Australia
Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems
Jul 15, 2026Dhruv Shivkant, Saket Mohanty, Utkarsh WadhwaOptimization Modeling Compressed Model
Indian Institute of Science · EXL
CineMobile: On-Device Image-to-Video Diffusion for Cinematic Camera Motion Generation
Jul 4, 2026Xuyao Huang, Zelai Deng, Xu Wang +2Diffusion Transformers Camera Control
Shanghai Jiao Tong University · Nankai University · Transsion
What Survives When You Compress a Recursive Reasoner for the Edge?
Jun 25, 2026Pearse Jim, Steven Kolawole, Opegbemi Matthias Busoye +2Compressed Model Recursive Reasoner
ML Collective · Carnegie Mellon University
Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks
Jun 22, 2026Minh-Loi Nguyen, Long-Bao Nguyen, Van-Hieu Huynh +2Compressed Model Neural Network Inference
University of Science, Ho Chi Minh city, Vietnam · Vietnam National University, Ho Chi Minh city, Vietnam
MoECodec: Image Compression for joint human and machine perception via Mixture-of-Experts
Jun 19, 2026Jiancheng Zhao, Xiang Ji, Yifan Zhan +2Learned Image Compression Compressed Model
The University of Tokyo
From Compression to Deployment: Real-Time and Energy-Efficient FastGRNN on Ultra-Constrained Microcontrollers
Jun 15, 2026Emre Can KizilatesCortex Neural Network Inference
Independent Researcher, Izmir, Turkey
Improved Knowledge Distillation for Land-Use Image Classification
Jun 12, 2026Arundhuti Sur, Abhiroop Chatterjee, Susmita Ghosh +1Knowledge Distillation Land Cover
Jadavpur University, India · Rochester Institute of Technology, USA
Compressed Computation is (probably) not Computation in Superposition
Jun 12, 2026Jai Bhagat, Sara Molas-Medina, Giorgi Giglemiani +1Compressed Model Multilayer Perceptrons
Metamorphic · Independent · UK AI Security Institute +1
Sigma-Branch: Hierarchical Single-Path Network Reconstruction for Dynamic Inference with Reduced Active Parameters
Jun 7, 2026Kohga Tanaka, Hiroaki NishiNeural Network Inference Compressed Model
Graduate School of Science and Technology, Keio University, Kohoku-ku, Yokohama 223-8522, Japan · Department of System Design, Faculty of Science and Technology, Keio University, Kohoku-ku, Yokohama 223-8522, Japan
Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction
Jun 1, 2026Yujia Tong, Yuxi Wang, Yunyang Wan +3Large Language Model Uncertainty Large Language Model Compression
Wuhan University of Technology · Nanyang Technological University
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
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
KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs
May 28, 2026Debopam Sanyal, Anantharaman Iyer, Alind Khare +5Capability-Speed Trade-Offs Imagenet
Georgia Institute of Technology · Microsoft M365 Research · Cisco Research +1
FTerViT: Fully Ternary Vision Transformer
May 20, 2026Szymon Ruciński, Pietro Bonazzi, Engin Türetken +3Self-Supervised Vision Transformers Vision Transformer
CSEM, Neuchâtel, Switzerland · ETH Zürich, Zurich, Switzerland
Dynamic Model Merging Made Slim
May 17, 2026Guodong Du, Wanyu LinContinual Model Merging Mixture-Of-Experts Architectures
The Hong Kong Polytechnic University
Complexity Horizons of Compressed Models in Analog Circuit Analysis
May 4, 2026Pacome Simon MbonimpaCompressed Model Analog Design
Carnegie Mellon University-Africa
Hierarchical Spatio-Channel Clustering for Efficient Model Compression in Medical Image Analysis
Apr 25, 2026Sisipho Hamlomo, Marcellin Atemkeng, Habte Tadesse Likassa +5Compressed Model Low-Rank Structure
Department of Mathematics, Rhodes University, Makhanda 6140, South Africa · Department of Statistics, Rhodes University, Makhanda 6140, South Africa · National Institute for Theoretical and Computational Sciences, Stellenbosch 7600, South Africa +8
Efficient VQ-QAT and Mixed Vector/Linear quantized Neural Networks
Apr 25, 2026Terry Gou, Puneet GuptaResidual Vector Quantization Compressed Model
Evolutionary fine tuning of quantized convolution-based deep learning models
Apr 19, 2026Marcin PietrońQuantized Compressed Model
AGH University Kraków, Poland
TStore: Rethinking AI Model Hub with Tensor-Centric Compression
Apr 18, 2026Tingfeng Lan, Zirui Wang, Yunjia Zheng +3Compressed Model Artificial Intelligence Models
University of Virginia · Harvard University
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)
Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism
Jun 2, 2025Sameera Ramasinghe, Thalaiyasingam Ajanthan, Gil Avraham +2Compressed Model Decentralized Learning
Pluralis Research
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
DarwinLM: Evolutionary Structured Pruning of Large Language Models
Feb 11, 2025Shengkun Tang, Oliver Sieberling, Eldar Kurtic +2Large Language Model Compression Unstructured Pruning
MBZUAI · ETH Zurich · ISTA +1

Sep 30, 2026, cs.LGJ/K move · Enter open · S save

A Tilted Bowl Is Not a Slippery Slope: Compressing Looped Models

Steven Kolawole, Pearse Jim, Opegbemi M. Busoye, Glory Bagai+1

Carnegie Mellon University · ML Collective

Compressed Model Model Weights Loop Maze Task Reasoning Skills

Open paper AskPDF arXiv

Looped models reason by applying the same block of weights many times, so compressing that block saves memory traffic on every loop. Compressed looped models, however, often collapse, and the collapse is usually blamed on rounding error that accumulates from loop to loop. In this work we test that account on more than 30 models from five families and find, to our surprise, that it holds only for loops that never settle. When a loop settles, a fixed rounding error does not accumulate. It moves the point where the loop settles, much as tilting a bowl moves where a ball comes to rest, and the answer is lost only when the shift is larger than the readout tolerates. This picture lets us predict which models fail from a single label-free measurement, and it tells us why failed models recover: their loops still settle, so a few final loops with 8-bit weights bring the answer back. Motivated by these findings, we build a controller that stops when the model's halting head fires and then finishes with 8-bit loops. On Sudoku-Extreme and Maze-Hard it beats fixed-depth inference by up to 15 points under a third of the weight traffic.

Momentum

Related topics

Latest papers 41