Reparameterization

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 35

All topics

Reprogramming Vision-Language Models via Structured Prompt Reparameterization
Sep 29, 2026Zizhao Li, Chengyi Cai, Mohammed Yaqoob Ansari +3Contrastive Language-Image Pre-Training Model Intra-Class
The University of Melbourne, Melbourne, Australia
Softmax Reparameterization for Output-Head Quantization
Sep 25, 2026Asim Kadav, Christian Flores, Chirag Arora +5Gradient Quantization Reparameterization
Adobe Search, Discovery & ContentAI
Recency Forcing: Bridging the Long-Horizon Gap in Autoregressive Video Generation
Sep 17, 2026Tri Cao, Hung Nguyen, Phong Nguyen +1Autoregressive Video Generation Video Generation
Qualcomm AI Research
Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks
Aug 12, 2026Andrew Cheng, Ali Eslamian, Jie Cheng +2Neural Network Representations Reparameterization
Department of Computer Science, Tsinghua University, Beijing, China · Department of Computer Science, The University of Manchester, Manchester, UK · Department of Computer Science, University of Kentucky, Lexington, KY, USA +3
Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension
Aug 11, 2026Tingan Jin, Shuhang Dong, Haosong Li +1Intrinsic Dimensionality Concept Erasure
UCLA · Independent Researcher · Cal Poly Pomona
TEMPER: Tensorized Efficient Manifold-constrained Parameterization for Expressive Residual Routing
Aug 8, 2026Yuxuan Gu, Wuyang Zhou, Huijun Xing +1Residual Connections Reparameterization
Department of Electrical and Electronic Engineering, Imperial College London
Establishing Boundary KKT Convergence of Mirror Descent through Reparameterization
Aug 7, 2026Kuangyu Ding, Kim-Chuan TohMirror Descent Convergence
School of Industrial Engineering, Purdue University, West Lafayette, IN 47907, USA. · Department of Mathematics, National University of Singapore, Singapore 119076.
URNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation
Aug 6, 2026Guoan Xu, Zhengxue Wang, Yang Xiao +3U-Net Cross-Modal Fusion
University of Technology Sydney Sydney, New South Wales, Australia · Nanjing University of Science and Technology Nanjing, China · Honor Device Co., Ltd. Beijing, China +1
Smooth Reparameterizations of Functions on Simplicial Product Spaces: Applications to Probabilistic Tensor Decomposition and Functional Data Registration
Aug 3, 2026Shashwat Kumar, Arafat Rahman, Anuj Srivastava +1Reparameterization Simplex
Department of Biomedical Engineering, Johns Hopkins University, USA · Department of Systems and Information Engineering, University of Virginia, USA · Department of Applied Mathematics and Statistics, Johns Hopkins University, USA +1
Output-Aware Rotation for INT2 KV-Cache Quantization
Aug 3, 2026Vincent-Daniel Yun, Woosang Lim, Minsoo Cheong +4Key-Value Cache Quantization Kv-Cache Management
University of Southern California · Seoul National University · Inha University
ReFP-AD: Rectified Flow Preconditioning for Energy-Based Anomaly Detection
Aug 3, 2026Camile Lendering, Erkut Akdag, Joaquín Figueira +1Graph Anomaly Detection Rectified Flow
AIMS Group, Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
Thermodynamics-Informed Input Reparameterization for Neural Prediction of Real-Fluid Thermodynamic Properties in Supercritical Combustion
Jul 21, 2026Haoze Zhang, Han Li, Ke Xiao +3Combustion Control Thermodynamics
State Key Laboratory of Turbulence and Complex Systems, College of Engineering, Peking University, Beijing 100871, China · AI for Science Institute (AISI), Beijing 100080, China
Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization
Jul 10, 2026Ethan SmithWeight-Space Reparameterization
Canva Research
QCNN with Rough Path Signature Kernels
Jul 8, 2026Leonardo Nogueira Falabella, Vasily SazonovQuantum Neural Networks Hybrid Quantum-Classical Pipeline
Université Paris-Saclay, CEA, List, F-91120, Palaiseau, France
Adaptive Reparametrized Time for Score-Based Diffusion Sampling
Jul 2, 2026Yilie Huang, Wenpin Tang, Xun Yu ZhouDiffusion Sampling Timestep
Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong. · Department of Industrial Engineering and Operations Research, Columbia University, New York, NY 10027, USA. · Department of Industrial Engineering and Operations Research and Data Science Institute, Columbia University, New York, NY 10027, USA.
FiRe: Frequency Reparameterization as a Preconditioner for Periodic Implicit Neural Representations
Jun 28, 2026Harinandan Shukla, Rajarshi Verma, Jitin SinglaNeural Representations Reparameterization
Department of Computer Science and Engineering, IIT Roorkee · Department of Biosciences and Bioengineering, IIT Roorkee
Tensor Train Decomposition-based 3D Implicit Full Waveform Inversion with Multi-scale Structural Similarity
Jun 22, 2026Liangsheng He, Chao Song, Tiansheng Chen +2Wavelets Subsurface Scattering
State Key Laboratory of Deep Earth Exploration and Imaging College of GeoExploration Science and Technology, Jilin University Changchun, Jilin, 130021, China · State Key Laboratory of DeepChaoEarthSong Exploration and Imaging College of GeoExploration Science and Technology, Jilin University Changchun, Jilin, 130021, China · Petroleum Exploration and Production Research Institute, Sinopec Beijing, 100083, China
Fisher-Geometric Sharpness and the Implicit Bias of SGD toward Flat Minima
Jun 18, 2026Md Sakir Ahmed, Kumaresh Sarmah, Hemen DuttaStochastic Gradient Descent Sharpness-Aware Minimization
Department of Electronics and Communication Technology Gauhati University Guwahati, Assam, India · Department of Mathematics Gauhati University Guwahati, Assam, India
RepNN: Tackling spectral bias in deep neural networks for regression and PDE problems via parameter reparameterization
Jun 15, 2026Yong Wang, Tao Zhou, Xuhui MengReparameterization Oscillatory Dynamics
Institute of Interdisciplinary Research for Mathematics and Applied Science, School of Mathematics and Statistics, Huazhong University of Science and Technology, Wuhan 430074, China · Institute of Computational Mathematics, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China
Continuous Neural Reparameterization as a Deep Geometric Prior for Robust Fixed-Chart UV Repair
Jun 8, 2026Mohammad Sadegh SalehiExtreme Ultraviolet Mesh Generation
Zero One Creative London, UK
Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks
Jun 3, 2026Bin Duan, Zeyu Bai, Guowei YangModel-Agnostic Defense Black-Box Adversarial Attacks
School of Electrical Engineering and Computer Science, The University of Queensland, Australia
Knowledge-Preserved Model Tuning in Null-Space for Robust Spatio-Temporal Video Grounding
Jun 2, 2026Haoxuan Chen, Xianqin Liu, Jian-Fang HuVideo Temporal Grounding Residual Learning
School of Computer Science and Engineering, Sun Yat-sen University, China · National Information Center of GACC (Guangdong), GuangZhou, China · School of Computer Science and Engineering, Sun Yat-sen University, China 3Guangdong Province Key Laboratory of Information Security Technology, China +1
Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models
May 26, 2026Mingze Wang, Shuchen Zhu, Yuxin Fang +3Batch Normalization Large Language Model Pretraining
ByteDance Seed · Peking University
Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate
May 24, 2026Huangyu Xu, Jingqin Yang, Qianqian Xu +1Sparsity Regularization
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China · IIIS, Tsinghua University, Beijing, China +3
Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)
May 18, 2026Michał Brzozowski, Neo Christopher ChungSparse Autoencoder Features Feature Learning
Samsung AI Center, Warsaw, Poland · University of Warsaw, Poland
Continuous Diffusion Scales Competitively with Discrete Diffusion for Language
May 18, 2026Zhihan Yang, Wei Guo, Shuibai Zhang +5Diffusion Language Models Diffusion Models
NVIDIA & Cornell · NVIDIA & Georgia Tech · UW-Madison +3
The Symmetries of Three-Layer ReLU Networks
May 18, 2026Johanna Marie Gegenfurtner, Moritz Grillo, Guido MontúfarRectified Linear Unit Networks Symmetry
Technical University of Denmark · Max Planck Institute for Mathematics in the Sciences · UCLA and MPI MiS
Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics
May 14, 2026Albert Kjøller Jacobsen, Leo Uhre Jakobsen, Johanna Marie Gegenfurtner +1Reparameterization Flat Minima
Section for Cognitive Systems, Technical University of Denmark · Center for Quantum Information Physics, New York University
Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel
May 14, 2026Ruihua Chen, Yisi Luo, Bangyu Wu +2Neural Tangent Kernel Complex Wavefield
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China · School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, Shaanxi, China · School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu 610000, China
The Diffusion Encoder
May 13, 2026Akhil Premkumar, Sarah LucioniDiffusion Models Conditional Variational Autoencoder
Independent Researcher
Revisiting Mixture Policies in Entropy-Regularized Actor-Critic
May 9, 2026Jiamin He, Samuel Neumann, Jincheng Mei +2Entropy Regularized Reinforcement Learning Soft Actor-Critic
University of Alberta & Amii · Google DeepMind · Canada CIFAR AI Chair
DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization
May 9, 2026Ao Li, Xiaoning Liu, Sheng Li +5Image Restoration Wavelets
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, Sichuan, China · School of Communications and Information Engineering, Chongqing University of Posts and Telecommunication, Chongqing 400065, China
Reparameterization through Coverings and Topological Weight Priors
Apr 26, 2026Maxim Beketov, Pavel SnopovTopological Learning Reparameterization
MedMamba: Recasting Mamba for Medical Time Series Classification
Apr 17, 2026ZhengXiao He, Huayu Li, Xiwen Chen +4Time-Series Classification Time Series
Department of Electrical & Computer Engineering at the University of Arizona, Tucson, AZ, USA
ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule
Jan 26, 2026Yilie Huang, Wenpin Tang, Xunyu ZhouTimestep Diffusion Sampling
Department of Industrial Engineering and Operations Research, Columbia University, New York, NY 10027, USA. · Department of Industrial Engineering and Operations Research & Data Science Institute, Columbia University, New York, NY 10027, USA.

Sep 29, 2026, cs.CVJ/K move · Enter open · S save

Reprogramming Vision-Language Models via Structured Prompt Reparameterization

Zizhao Li, Chengyi Cai, Mohammed Yaqoob Ansari, Feng Liu+2

The University of Melbourne, Melbourne, Australia

Contrastive Language-Image Pre-Training Model Intra-Class Reparameterization

Open paper AskPDF arXiv

Visual reprogramming adapts pretrained models to downstream tasks by modifying their input and output interfaces while keeping the backbone fixed. In vision-language models, existing methods mainly rely on intra-class prompt aggregation and do not explicitly model relationships among classes. However, fine-grained categories often exhibit highly overlapping attribute descriptions and strong inter-class correlation in the text embedding space, where discriminative cues lie in subtle low-variance components. We propose Reparameterized Inter-Class Visual Reprogramming (RVP), a structured framework that aggregates multiple text prompts within each class and applies residual correction across classes. We also show that CLIP-based visual reprogramming with input-independent linear output aggregation can be expressed as a linear mapping from frozen image embeddings to downstream logits, and use this view to design a structured reparameterization that models shared semantic components and class-specific differences. RVP uses only a single visual prompt and can be reparameterized at inference into a frozen backbone followed by a linear classifier, incurring nearly zero computational overhead. Across 11 few-shot classification benchmarks and four CLIP backbones, RVP consistently improves over prior visual reprogramming methods with comparable or better inference efficiency.

Momentum

Related topics

Latest papers 35