Model Weights

Ask about this topic

Momentum

21 papers in the last four weeks, up 133% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 127

All topics
CardsList

  1. StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMs

    Oct 5, 2026Zhe Wei, Mengqi Guo, Yuan Yuan +3Model Weights

    Huawei Technologies Ltd.

  2. Understanding the Weight Averaging Mechanism in LLM Training for Post-Training Quantization

    Oct 4, 2026Hanzhang Wang, Tianqi Shen, Zonglin Liu +3Model Weights

    City University of Hong Kong · The University of Hong Kong

  3. Removing spurious minima for planar features by skip connections

    Oct 1, 2026Jakob Paul Zimmermann, Moritz Grillo, Andrei Balakin +1Flat MinimaSkip

    Freie Universität Berlin · Technische Universität Berlin

  4. QK-Wanda: Coupling Queries and Keys for Unstructured Pruning

    Oct 1, 2026Ivan Ilin, Peter RichtárikUnstructured PruningModel Weights

    KAUST

  5. On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D

    Sep 30, 2026Fabio J. Fehr, Philip TorrHypernetworkModel Weights

    University of Oxford

  6. AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing

    Sep 30, 2026Zhihui Gao, Tingjun Chen, Dirk EnglundLLM Inference OptimizationEdge Devices

    Massachusetts Institute of Technology Cambridge, MA, USA · Duke University Durham, NC, USA

  7. Is Weight Tying Still Beneficial for Decoder-Only LLMs in Private Settings Under DP-SGD?

    Sep 30, 2026Razan El Mais, Ali Chehab, Ibrahim Issa +1Model WeightsStochastic Gradient Descent

    Department of Electrical and Computer Engineering American University of Beirut Beirut, Lebanon

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

    Sep 30, 2026Steven Kolawole, Pearse Jim, Opegbemi M. Busoye +2Compressed ModelModel Weights

    Carnegie Mellon University · ML Collective

  9. JARQ: Joint Alternating Refinement for Quantization

    Sep 29, 2026Xinyu Wang, Sicheng Lyu, Xiao-Wen ChangPost-Training QuantizationLanguage Model Perplexity

    McGill University

  10. ShamAN-Q: Shampoo Augmented NanoQuant for Sub-1-bit LLM Weights

    Sep 29, 2026Jonathan Mei, Sang Hyub Kim, Oliver Knitter +2Large Language Model QuantizationQuantized

    Applications R&D IonQ College Park, MD 20740, USA

  11. Security-Enhanced Seed-Based Weight Quantization for Large Language Models

    Sep 29, 2026Qiuyu Ren, Sudipta Paria, Aritra Dasgupta +1Model WeightsSecure Aggregation

    Department of Electrical and Computer Engineering (ECE) University of Florida Gainesville, FL 32611, USA

  12. Tetra: Serving Leech-Lattice Quantized LLMs at 2.7 Bits per Parameter

    Sep 28, 2026Pier-Jean MalandrinoLarge Language Model QuantizationModel Weights

    Scub, Bordeaux, France

  13. Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models

    Sep 28, 2026John SweeneyModel WeightsParametric Memory

    Sideplane AI

  14. EntroPack: Fast and Accurate Entropy-Coded Weight Compression at Arbitrary Bitrates

    Sep 28, 2026Hong Zhang, Zhongjie Duan, Yingda ChenModel WeightsUltra-Low Bitrates

    Alibaba Inc.

  15. TerMeZO: Ternary Sparse Zeroth-Order Optimization for Fine-tuning BitNet Models at the Edge

    Sep 27, 2026Houssem Sifaou, Prabodh Katti, Bipin Rajendran +1Zeroth-Order OptimizationZeroth-Order

    Institute for Intelligent Networked Systems, Northeastern University London, UK

  16. Baseline Shape Decides the Verdict: A Controlled Re-Examination of Ternary Language Models at 60K Parameters

    Sep 24, 2026Gautam VeldandaTransformer ArchitecturesModel Weights

    Independent Researcher

  17. Beyond Scalar Sensitivity: Activation-Aware Mixed-Precision LLM Quantization with Cross-Layer Refinement

    Sep 22, 2026Akihiro Yoshida, Yuma IchikawaMixed-Precision QuantizationLarge Language Model Quantization

    Fujitsu Limited, Institute of Science Tokyo · Fujitsu Limited, RIKEN Center for AIP

  18. Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data

    Sep 16, 2026Jinli Hu, Ross M. Clarke, Yichuan Zhang +1Model WeightsIn-Context Learning

    Boltzbit Limited · University of Cambridge

  19. Breaking the 1.58-bit Barrier for Ternary LLMs

    Sep 14, 2026Evangelos Georganas, Alexander Heinecke, Pradeep DubeyLarge Language Model QuantizationModel Weights

    Intel Corporation

  20. Reproducing and Evaluating the Generalizability of Subliminal Learning in Open-Weight Models

    Sep 14, 2026Daan van der Weijden, Nathan Brack, Selene Baez SantamariaModel WeightsTeacher

    University of Zurich

  21. Structured Transforms for Low-Overhead Quantization of Language Models

    Sep 11, 2026Daria Cherniuk, Alexander Rudikov, Boris Kashin +1Large Language Model QuantizationModel Weights

    Institute of Numerical Mathematics · Steklov Mathematical Institute

  22. Stochastically Perturbed Weights: Ensembles from Deterministic Machine-Learning Weather Models

    Sep 8, 2026Simon Adamov, Oliver Fuhrer, Reto Knutti +1Artificial Intelligence Weather ModelsModel Weights

    Federal Office for Meteorology and Climatology MeteoSwiss, Zurich, Switzerland · Institute for Atmospheric and Climate Science (IAC), ETH Zurich, Zurich, Switzerland · Department of Applied Mathematics and Theoretical Physics, University of Cambridge, United Kingdom

  23. Online Self-Weighted Fine-Tuning

    Sep 1, 2026Haiquan Wen, Yiwei He, Bei Peng +1Model Fine-TuningModel Weights

    University of Liverpool · University of Sheffield

  24. Arkios: An Open Bilingual English-Nepali Language Model Trained From Scratch, with a Devanagari-Aware Tokenizer

    Aug 30, 2026Sajal Regmi, Siddhartha Pudasaini, Chetan Phakami PunByte-Pair EncodingTransformer Architectures

    Karela Technologies Inc.

  25. FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference

    Aug 24, 2026Gongwei Lee, Ji Liu, Juncheng Jia +1Mixed-Precision QuantizationLLM Inference Optimization

    School of Computer Science and Technology, Soochow University, Suzhou, China · Hithink Research, Hangzhou, China · Electronic Engineering, Tsinghua University, Beijing, China

  26. Activation-Weighted Seeded Residual Coding for Low-Bit LLM Weight Repair

    Aug 24, 2026Zehao Liu, Chuangchuang Fang, Yang RenLarge Language Model QuantizationModel Weights

    Huawei Technologies Research & Development (UK) Limited, Edinburgh, United Kingdom

  27. How Weight Encoding Affects Language Model Placement and Performance on the Apple Neural Engine

    Aug 22, 2026Shahir M AMatched Fp16 IntermediateModel Weights

    Independent researcher

  28. In-Cell Learning: Language Models That Update Their Own Weights in Sequence Without Changing the File They Ship

    Aug 21, 2026Zifeng Liu, Yaxin Lu, Xuanhan Wu +6Model WeightsFull-Precision Performance

    Big Data and Artificial Intelligence Center, The Third Affiliated Hospital of Sun Yat-sen University · Institute for Frontier Interdisciplinary Research in Health Sciences and Technology, Sun Yat-sen University · Sun Yat-sen University Institute of Artificial Intelligence +7

  29. Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification

    Aug 14, 2026Aman Singh Thakur, Rayan KhouryModel CheckpointsModel Weights

    Massachusetts Institute of Technology, USA

  30. Reduced Matrix Multiplication: Input-Adaptive Matrix-Product Reduction for LLM Inference

    Aug 13, 2026Zixuan Lan, Yanhong Li, Jiawei ZhouMatrix MultiplicationLLM Inference Optimization

    University of Chicago · Independent Researcher · Stony Brook University

  31. Weightless Fine-Tuning: Personalizing LLMs via Logit-Space Transport

    Aug 11, 2026Bohan Zhang, Anqi Ni, Yixin Wang +1Model Fine-TuningLogit Lens

    University of Michigan · University of Chicago

  32. LegoLM: Structured Weight Sharing for Large Language Models

    Aug 9, 2026Joseph BinghamLarge Language Model CompressionModel Weights

    Deparment of Biology, Technion – Israel Institute of Technology

  33. Your Prompt Is Not the Only Prompt: How Much Do LLMs Weight Structured-Output Schema Descriptions?

    Aug 8, 2026Sin-Ying LinSchemaPrompt Engineering

    Independent Researcher

  34. Quantization Degradation in Large Language Models: A Signal-Noise Perspective

    Aug 8, 2026Chenxi Zhou, Pengfei Cao, Jinyu Ye +5Large Language Model QuantizationPost-Training Quantization

    School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China · The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China +1

  35. Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space

    Aug 7, 2026Yiwei Chen, Bingqi Shang, Sijia LiuModel WeightsLineages

    Michigan State University

  36. ELMZip: Onboard Satellite Image Compression via Extreme Learning Machines for Efficient Downlink

    Aug 7, 2026Woojin Cho, Junghwan Park, Sangcheol Sim +3Hyperspectral ImagePower Allocation

    TelePIX 07330, Seoul, South Korea

  37. Wan-Animate-2: Pushing the Application Boundaries of Character Animation

    Aug 6, 2026Guangyuan Wang, Li Hu, Dechao Meng +11Latent MotionDiffusion Transformers

    Tongyi Lab, Alibaba Group

  38. Muon Meets Mamba: Spectral Optimization for State Space Models

    Aug 4, 2026Arslan Battalov, Karim Kramin, Alexander Markotenko +1MuonState Space Models

    HSE University · Moscow, Russia

  39. Sparse Weight Decomposition for Efficient Circuit Extraction

    Aug 4, 2026Chuanhao Yan, Xuhan Huang, Yawen Duan +4Transformer ArchitecturesModel Weights

    IQuest Research · Safe AI Forum · University of Oxford +2

  40. Omega-S: A Functional Resilience Index for LLM Fine-Tuning

    Aug 4, 2026Alberto AcedoLarge Language Model Fine-TuningModel Fine-Tuning

    Biome Makers Inc.

  41. Not the Dimension, the Norm: What Matters in Gradient-Free Weight Perturbation of Language Models

    Aug 3, 2026Taeyeong Kim, Ahhyun Kim, TaeHyeon Kim +1Model WeightsNorm

    Chosun University · Korea University Sejong Campus

  42. Kilobyte Models: Neural Networks as a Seed and a Quantized Latent

    Aug 1, 2026Sahil Rajesh DhayalkarCompressed ModelModel Weights

    Arizona State University

  43. Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting

    Jul 30, 2026Xiang Yuan, Kaiqing Lei, Zhenyu Jin +3ReweightingModel Weights

    School of Mathematics and Statistics, Xi’an Jiaotong University · Northwest University, Shaanxi, China

  44. Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights

    Jul 29, 2026Kevin GuanLatent StatesModel Weights

    Department of Mathematics, Princeton University

  45. Kimi K3: Open Frontier Intelligence

    Jul 27, 2026Kimi Team, Tongtong Bai, Yifan Bai +399Qwen3Intelligence

  46. PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization

    Jul 17, 2026Yuchen Yang, Yifan Zhao, Anisha Dasgupta +1Graphics Processing Unit MemoryMixture-Of-Experts Large Language Models

    University of Illinois Urbana-Champaign

  47. CoG-Guided Weight Correction for Fault-Tolerant Deep Neural Networks

    Jul 17, 2026Bahram Parchekani, Samira Nazari, Ali Azarpeyvand +3Model WeightsNeural Network

    University of Zanjan, Zanjan, Iran · Tallinn University of Technology, Tallinn, Estonia

  48. Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents

    Jul 17, 2026Zhengyu Chen, Teng Xiao, Huaisheng Zhu +3Agent HarnessLarge Language Model Agents

    Meituan · Allen Institute for AI · Independent

  49. Counterfactuals for Feature-Weighted Clustering

    Jul 16, 2026Richard J. Fawley, Renato Cordeiro de AmorimClusteringCounterfactual Explanation

    School of Computer Science and Electronic Engineering, University of Essex, Wivenhoe, UK.

  50. LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks

    Jul 15, 2026Nilay Anurag, Shital Adhikari, Taniya Kapoor +1Parametric Physics-Informed Neural NetworkPartial Differential Equations

    Department of Computer Science, Stevens Institute of Technology · Artificial Intelligence Group, Wageningen University & Research

  51. ExTernD: Expanded-Rank Ternary Decomposition Ternary LLM PTQ with Accuracy Approaching Any Quantization Level

    Jul 15, 2026Chethan Reddy G. PLarge Language Model QuantizationModel Weights

  52. Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs

    Jul 12, 2026Shrestha Datta, Hongfu Liu, Anshuman ChhabraModel WeightsGradient

    University of South Florida, Tampa, FL, USA · Brandeis University, Waltham, MA, USA

  53. modelDNA: Calibrated Lineage Verification and Merge Decomposition from Sampled Weight Fingerprints

    Jul 12, 2026Muhammad Awais Bin Adil, Saad AamirLineagesFingerprint

    Independent

  54. Reliability-Aware Ensemble Classification Under Class Imbalance: A Calibration Study on Liquid-Based Cervical Cytology

    Jul 10, 2026Nisreen Albzour, Sarah S. LamCancer DetectionImbalanced Classification

    School of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA

  55. Super Weights in LLMs and the Failure of Selective Training

    Jul 9, 2026Shreyas Subramanian, Adewale Akinfaderin, Akarsha SehwagModel WeightsLow-Rank Structure

    Amazon Web Services

  56. ManifoldFlow: SPD-Relaxed Stiefel Layers with Learnable Singular Spectrum

    Jul 5, 2026Haiwen Yi, Xinyuan SongOrthogonalityModel Weights

    University of Toronto · Emory University

  57. Decentralized Aggregation of LLM Predictions via Wagering Mechanisms

    Jul 5, 2026Yuhong Luo, David M. Pennock, Xintong WangDecentralized LearningBetting

    Rutgers University · DIMACS, Rutgers University

  58. Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions

    Jul 4, 2026Haochen Luo, Yi Huang, Sichun Luo +5Evolving HarnessSelf-Evolution

    School of Computing and Data Science, The University of Hong Kong · Grace Investment Machine · Jiutian Research, China Mobile

  59. Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types

    Jul 3, 2026Paria Vali Zadeh, Sven TomfordeAnimal VocalizationsPassive Acoustic Monitoring

    Kiel University, Kiel, Germany

  60. Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights

    Jul 3, 2026Naoya Chiba, Satoshi Sugiyama, Yuki UranishiSymmetryModel Weights

    D3 Center, The Unversity of Osaka