Sampling Bias Compensation

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 13

All topics

Task-Oriented Visual Feature Compression via Residual Vector Quantization for Device-Edge Multimodal Inference
Sep 29, 2026Luning Pang, Cheng Yuan, Jiawei Shao +2Residual Vector Quantization Multimodal Learning
Department of Electronic Engineering, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China · Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing 100033, China
Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed Execution
Sep 10, 2026Anirudh Malik, M Sparsh Mehra, Poojith DevanModel Size Qwen3
OneBit AI
Comparing SGLD and a fixed-noise Predictor-Corrector adaptation in canonical Joint Energy-Based Models on CIFAR-10
Aug 5, 2026Dmytro KnopovDiscriminative Models Sampling Bias Compensation
Faculty of Computer Sciences, Department of Mathematics, National University of Kyiv-Mohyla Academy, Kyiv, Ukraine.
Rotational Motion-Induced Error Compensation for Phase-Shifting Profilometry-Based Eye Reconstruction
Jul 16, 2026Seong-Jin An, Sanghoon Jeon, Yatong An +1Vision-Language Reprojection Consistency Augmented Reality
Department of Mechanical Engineering, Yonsei University, 03722, Seoul, Republic of Korea · Meta Reality Labs, Redmond, 98052, Washington, USA
Sampling Bias Compensation for Robust Evaluation of Audio Classification Systems with Partially Labeled Evaluation Datasets
Jul 5, 2026Javier Naranjo-Alcazar, Annamaria Mesaros, Tuomas Virtanen +1Importance Weighting Audio Understanding
Instituto Tecnologico de Informatica (ITI), Valencia, Spain · Tampere University, Tampere, Finland
Robust Autonomous UAV Landing on Maritime Platforms via Multimodal Agentic AI and Active Wave Compensation
Jun 30, 2026Francisco S. Neves, Pedro N. Pereira, Raul D. S. G. Campilho +1Cooperative Air Combat Autonomous Underwater Vehicles
Faculty of Engineering, University of Porto (FEUP) · Instituto Superior de Engenharia do Porto (ISEP)
Morphology-Specific Closed-Loop Control of Logarithmic-Spiral Continuum Arms via Online Jacobian Error Compensation
Jun 24, 2026Partha Datta, Yi Jin, Wei Lin +1Robotic Manipulator Closed-Loop Feedback
Laboratory for Soft Machines and Electronics, Department of Mechanical and Aerospace Engineering, Case Western Reserve University, Cleveland, OH, USA · Department of Electrical, Computer and Systems Engineering, Case Western Reserve University, Cleveland, OH, USA · Laboratory for Soft Machines and Electronics, Department of Mechanical and Aerospace Engineering, Case Western Reserve University, Cleveland, OH 44106, USA +3
MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation
Jun 8, 2026Dohwan Kim, Jung-Woo ChoiSpeech Separation Sampling Bias Compensation
School of Electrical Engineering, KAIST, Daejeon, Republic of Korea
MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization
May 20, 2026Zhong Wang, Zukang Xu, Xing Hu +1Large Language Model Quantization Sampling Bias Compensation
Bauman Moscow State Technical University · Houmo AI
Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization
May 14, 2026Peilin Sun, Jianxin WuPost-Training Quantization Sampling Bias Compensation
State Key Laboratory of Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China
Conservative Flows: A New Paradigm of Generative Models
May 7, 2026Eshed Gal, Md Shahriar Rahim Siddiqui, Moshe Eliasof +1Generative Flow Networks Generative Models
The University of British Columbia Vancouver, Canada · University of Cambridge Cambridge, United Kingdom
HCInfer: An Efficient Inference System via Error Compensation for Resource-Constrained Devices
May 7, 2026Shen Xu, Xiangwen Zhuge, Zhe Xu +3Efficient Inference Sampling Bias Compensation
Tsinghua University · Huazhong University of Science and Technology
SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing
Mar 9, 2026Xuanyi Zhou, Qiuyang Mang, Shuo Yang +7Video Diffusion Models Diffusion Transformers
UC Berkeley, USA

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

Task-Oriented Visual Feature Compression via Residual Vector Quantization for Device-Edge Multimodal Inference

Luning Pang, Cheng Yuan, Jiawei Shao, Mingtao Huang+1

Department of Electronic Engineering, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China · Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing 100033, China

Residual Vector Quantization Multimodal Learning Sampling Bias Compensation

Open paper AskPDF arXiv

Large multimodal models (LMMs) support diverse visual understanding and reasoning tasks but are often impractical to run entirely on resource-constrained devices. Device-edge co-inference reduces device computation, yet transmitting visual data over bandwidth-limited uplinks can introduce substantial delay. Task-oriented feature compression (TOFC) reduces the payload through feature aggregation and entropy coding. However, continuous-feature coding remains costly, and query-agnostic aggregation may discard task-relevant local evidence. We propose query-guided task-oriented feature compression (Q-TOFC) for device-edge multimodal inference. Q-TOFC employs residual vector quantization (RVQ) to encode each merged feature as a compact sequence of codebook indices, reducing its representation cost and allowing more features to be transmitted. It further incorporates query relevance into feature aggregation and uses a quantization error compensation adapter to mitigate the distortion introduced by discrete quantization. Experiments on seven multimodal benchmarks show that Q-TOFC reduces the visual payload by 53.6% relative to TOFC while maintaining comparable average normalized task performance. End-to-end latency evaluations further demonstrate lower latency under bandwidth-constrained uplinks.

Momentum

Related topics

Latest papers 13