Noisy Data

Follow this topic Ask about this topic

Momentum

5 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 53

All topics

Residual-Stream Burden Shapes Representation Learning in Diffusion Transformers
Sep 27, 2026Tongtong Liang, Siqi Kou, Ziqiao Xi +6Diffusion Transformers Transformer Residual Streams
UC San Diego · Shanghai Jiao Tong University · Aether AI
Rethinking Diffusion Segmentation: When Does It Rely on Its Noisy State, and Does Diffusion Matter?
Sep 21, 2026Hengzhuo Yang, Yuming Zeng, Yuling YangText-Conditioned Diffusion Model Diffusion Models
Department of Mathematics, Northeastern University, Boston, MA 02115 USA · Department of Mechanical and Industrial Engineering, Northeastern University, Boston, MA 02115 USA
Fast Graph Laplacian Estimation using Effective Resistance
Sep 20, 2026Christoffer Kjellson, Claudio Altafini, Emma TeglingGraph Laplacians Graph Signal Processing
Department of Automatic Control, Lund University · ELLIIT Strategic Research Area · Division of Automatic Control, Department of Electrical Engineering, Linköping University
When Noise Fabricates Bias: The Fragility of LLM-as-a-Judge Bias Measurement under Noisy Text
Sep 10, 2026DongHyun Ryu, Jaehyeok Lee, YeongJun Hwang +1Large Language Model Bias Llm-As-A-Judge
Sungkyunkwan University, Suwon, South Korea
Optimal estimation for Functional Linear Regression with Noisy Discretized Data
Sep 8, 2026Sixtine SphabmixayCovariates Noisy Data
Université Paris Cité, CNRS, MAP5, F-75006 Paris, France
Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation
Aug 31, 2026Atta Ul Asad, Ahsan Bilal, Muhammad Ali +2Key-Value Cache Quantization Faithfulness
1Lahore University of Management Sciences (LUMS) · University of Oklahoma · 3Air University +1
PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization
Aug 31, 2026Boryeong Cho, Sumyeong Ahn, Se-Young YunBacktranslation Augmented Direct Preference Optimization Preference Learning
KAIST AI · KENTECH
Risk-Aware Decision Policies for Agents Under Noisy Perception
Aug 5, 2026David SzczecinaPredator-Prey Models Noisy Data
University of Waterloo, Canada
Wrong Operator or Blind Design? A Reference-Free Diagnostic for Physics-Informed Coefficient Learning
Aug 4, 2026Eric FockParametric Physics-Informed Neural Network Physics-Informed Learning
PIMENT Laboratory, Universit´e de La R´eunion, Le Tampon 97430, La R´eunion, France
RIDGE: Re-Noising with Internal Dynamic Guidance for Image Editing
Aug 4, 2026Ruiliang Gong, Zhen Wang, Yanghao Wang +1Diffusion-Based Image Editing Image Editing
Department of Computer Science and Engineering The Hong Kong University of Science and Technology
Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark
Jul 31, 2026Muyao Niu, Mingze Ma, Yifan Zhan +5Low-Light Images Infrared
The University of Tokyo Tokyo, Japan · Adelaide University Adelaide, Australia · School of Artificial Intelligence (SAI) Shanghai Jiao Tong University Shanghai, China +1
Dynamics-aware identification of governing equations from sparse and noisy data
Jul 31, 2026Pongpisit Thanasutives, Yoshinobu KawaharaSystem Identification Dynamic Mode Decomposition
Center for Advanced Intelligence Project (AIP), RIKEN, Osaka, Japan · 2Graduate School of Information Science and Technology, The University of Osaka, Osaka, Japan
On the robustness of noisy solutions in non-convex neural networks
Jul 29, 2026Enrico M. Malatesta, Alessandra Passalacqua, Riccardo ZecchinaSlow Relaxation Modes Infinities
Department of Computing Sciences, Bocconi University, Milano, Italy · Bocconi Institute for Data Science and Analytics (BIDSA)
Robust Conformalized Selection with Noisy Responses
Jul 25, 2026Chengyao Yu, Hongxin Wei, Bingyi JingFalse Discovery Rate Conformal Inference
Department of Statistics and Data Science Southern University of Science and Technology Shenzhen 518055, China · School of Artificial Intelligence The Chinese University of Hong Kong, Shenzhen Shenzhen Loop Area Institute Shenzhen 518172, China
From Pixels to Pairs: A Comprehensive Benchmark of LLM-Driven Key-Value Extraction in Noisy Document Settings
Jul 14, 2026Zahra AnvariExtraction Keys And Value
Independent AI Researcher.
Stochastic Order Learning: An Approach to Rank Estimation Using Noisy Data
Jul 9, 2026Chaewon Lee, Seon-Ho Lee, Chang-Su KimNoisy Labels Noisy Data
School of Electrical Engineering, Korea University, Seoul, Korea · Amazon AGI, Seattle, USA
From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization
Jul 8, 2026Ying Chang, Jiahang Xu, Xuan Feng +3Agentic Optimization Traces
University of Chinese Academy of Sciences, Beijing, China · Microsoft Research.
Sensitivity Sampling with Predictions for k-Means Clustering
Jul 6, 2026Cristian Boldrin, Fabio VandinK-Means Clustering
University of Padova, Padova, Italy
Learning dynamical systems from noisy data with Weak-form Kernel Ridge Regression
Jun 30, 2026Max Kreider, John Harlim, Daning HuangKernel Ridge Regression Dynamical Systems
Department of Mathematics The Pennsylvania State University, University Park, PA 16802, USA · Department of Mathematics, Institute for Computational and Data Sciences The Pennsylvania State University, University Park, PA 16802, USA · Department of Aerospace Engineering The Pennsylvania State University, University Park, PA 16802, USA
A Bayesian Filtering Approach for Learning Lagrangian Dynamics from Noisy Measurements
Jun 30, 2026Kundan Kumar, Shreya Das, Simo SärkkäBayesian Filtering Lagrangian Methods
Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text
Jun 29, 2026Tanvir Ahmed Sijan, S. M Golam Rifat, Nayeemul Islam +1Encoders Automatic Speech Recognition
Jahangirnagar University, Dhaka, Bangladesh · Rajshahi University of Engineering & Technology, Rajshahi, Bangladesh · Bangladesh University of Engineering and Technology, Dhaka, Bangladesh
Mind the Noise: Sensitivity of Transformer-based Interaction-Aware Trajectory Prediction Models to Noisy Data
Jun 19, 2026Shahab Salehi, Luca Lusvarghi, Miguel Sepulcre +1Trajectory Forecasting Noisy Data
Networked Systems Lab, Universidad Miguel Hernandez de Elche, Elche, Spain
Measurement noise limits the advantage of nonlinear models over linear models in biomedical prediction
Jun 16, 2026Marc-Andre Schulz, Kerstin RitterNonlinearity Noisy Data
Hertie Institute for AI in Brain Health, University of Tübingen, Tübingen, Germany · Tübingen AI Center, University of Tübingen, Tübingen, Germany · Department of Psychiatry and Neurosciences, Charité – Universitätsmedizin Berlin, Berlin, Germany +2
Selective Control under Noisy Perception: Governance Failures Hidden by Aggregate Metrics in Modular Networks
Jun 12, 2026Igor ItkinContent Moderation Governance
Independent Researcher, Tel Aviv, Israel
Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning
Jun 11, 2026Paolo Muratore, Mackenzie Weygandt MathisLatent Dynamics Noisy Data
EPFL
G-MaP-SE: Guided Speech Enhancement via GMM-Based Prior Matching
Jun 7, 2026Yike Zhu, Ziqian Wang, Zikai Liu +5Speech Enhancement Noisy Data
PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents
Jun 6, 2026Zayx ShawnSelf-Evolving Agents Self-Evolution
Independent Researcher
Explainable Runtime Dependency Tracking for AI-RAN Conflict Monitoring
Jun 4, 2026Christie Djidjev, Nicholas KaminskiOpen Radio Access Networks Runtime
Idaho National Laboratory Idaho Falls, United States
Temporal Evidence Routing with Structured Visual Evidence for TimeLogicQA
May 31, 2026Yuyang Sun, Yongliang Wu, Xingyu Zhu +8Long Video Question Answering Temporal Reasoning
Southeast University · National University of Singapore · Independent Researcher +2
Quantifying Uncertainty in Space Debris Capture with Active Tether-Net Systems Caused by Noisy Observations
May 26, 2026Feng Liu, Achira Boonrath, Eleonora M. Botta +1Advanced Jet Trainer Learning-Based Control
University at Buffalo · Buffalo, New York, 14260
Learning Nonlinear Factor Models with Unknown Monotone Links from Incomplete and Noisy Data
May 25, 2026Yutong Chao, Resat Gökhan, Jalal Etesami +1Exploratory Factor Analysis Nonlinearity
School of Computation, Information and Technology, Technical University of Munich, Germany · Munich Institute of Robotics and Machine Intelligence · Department of Economics, Virginia Tech, USA
Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents
May 23, 2026Kaiqiao Han, LuAn Tang, Renliang Sun +6Retrieval-Augmented Generation Pipelines Graph-Based Retrieval Augmented Generation
UCLA · NEC Labs
Adaptive Measurement Allocation for Learning Kernelized SVMs Under Noisy Observations
May 21, 2026Artur MiroszewskiQuantum Kernels Support Vector Machines
Φ-lab, European Space Agency (ESA/ESRIN), Frascati, Italy
UOTIP: Unbalanced Optimal Transport Map for Unpaired Inverse Problems
May 20, 2026Donggyu Lee, Taekyung Lee, Jaewoong ChoiBayesian Inverse Problems Inverse Problem
Department of Mathematical Sciences, Seoul National University · IPAI (Interdisciplinary Program in Artificial Intelligence, Seoul National University) · Sungkyunkwan University
PilotWiMAE: Pilot-Native Representation Learning for Wireless Channels
May 19, 2026Berkay Guler, Giovanni Geraci, Hamid JafarkhaniChannel Representation Learning
Center for Pervasive Communications and Computing, University of California, Irvine CA, USA · Nokia and Universitat Pompeu Fabra, Spain
Measurement-Adapted Eigentask Representations for Photon-Limited Optical Readout
May 11, 2026Tianyang Chen, Mandar M. Sohoni, Saeed A. Khan +5Low-Light Images Readout
Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544, USA · School of Applied and Engineering Physics, Cornell University, Ithaca, NY 14853, USA · USRA Research Institute for Advanced Computer Science, Mountain View, CA 94035, USA +1
Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions
May 10, 2026Dier Tang, Guangyue HanFeature Selection Symmetry
Department of Mathematics, The University of Hong Kong, Hong Kong, China · Department of Mathematics The University of Hong Kong Hong Kong, China
NoisyCausal: A Benchmark for Evaluating Causal Reasoning Under Structured Noise
May 5, 2026Zhi Xu, Yun FuLLM Reasoning Strategies Causal Reasoning
Northeastern University
Noise2Params: Unification and Parameter Determination from Noise via a Probabilistic Event Camera Model
May 4, 2026Owen Root, Julinda Mujo, Min XuSingle-Photon Avalanche Diode Calibrated Uncertainty
Department of Physics and Astronomy, CUNY Hunter College, 695 Park Ave, New York, 10065, NY, USA.
Black-box optimization of noisy functions with unknown smoothness
May 4, 2026Jean-Bastien Grill, Michal Valko, Rémi MunosBlack-Box Optimization Smoothness
SequeL team, INRIA Lille - Nord Europe, France · Google DeepMind, UK∗
Generalizable Friction Coefficient Estimation via Material Embedding and Proxy Interaction Modeling
Apr 27, 2026Zhendong Wang, Huamin WangFriction Materials
Style3D Research Hangzhou, China
Learning from Noisy Prompts: Saliency-Guided Prompt Distillation for Robust Segmentation with SAM
Apr 25, 2026Jingxuan Kang, Ziqi Zhang, Shaoming Zheng +9Semi-Supervised Medical Image Segmentation Segment Anything Model
Imperial College London · Beihang University · National Health Service +1
Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation
Apr 22, 2026Jie Xu, Haaris Mehmood, Rogier Van Dalen +2Federated Learning Privacy-Preserving Framework
Samsung R&D Institute UK (SRUK) · Samsung AI Centre Cambridge
Clusterability-Based Assessment of Potentially Noisy Views for Multi-View Clustering
Apr 20, 2026Mudi Jiang, Jiahui Zhou, Xinying Liu +2Clustering Multi-View
School of Software, Dalian University of Technology, Dalian, China · School of Software, Dalian University of Technology, Dalian, China, and Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province, Dalian, China
Machine Learning Hamiltonian Dynamical Systems with Sparse and Noisy Data
Apr 19, 2026Vedanta Thapar, Abhinav GuptaHamiltonian Dynamical Systems
The Mathematical Institute, University of Oxford, Oxford OX2 6GG, United Kingdom · Center for Theoretical Physics, St. Stephen’s College, University of Delhi, Delhi 110007, India
RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference
Apr 16, 2026Yuxin Liu, Yiqing Dong, Wenxue Yu +4Iterative Denoising Methods Velocity Field
School of Computer Science and Engineering, Southeast University, China · Department of Optical Sciences, University of Arizona, USA · School of Instrument Science and Engineering, Southeast University, China +1
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise
Feb 13, 2026Yuejie Li, Ke Yang, Yueying Hua +4Acoustic Noisy Data
Ant Group Hangzhou, China · Soochow University Suzhou, China · University of Science and Technology of China Hefei, China +3
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
Jan 29, 2026Baorui Ma, Jiahui Yang, Donglin Di +53D Perception Camera Intrinsics
Li Auto Inc
NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems
Jan 16, 2026Jiayu Liu, Rui Wang, Qing Zong +9Confidence Calibration Agentic Retrieval-Augmented Generation Systems
HKUST · UIUC · Northwestern University
Early Estimation of Language to Latent Alignment in Diffusion Models
Dec 9, 2025Vasco Ramos, Regev Cohen, Idan Szpektor +1Diffusion Models Latent Representation Alignment
NOVALINCS, NOVA University of Lisbon, Portugal · Google Research
The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements
Sep 1, 2025Youssef Chaabouni, David GamarnikSparsity Optimal Sample Complexity
Massachusetts Institute of Technology
Universality of Benign Overfitting in Binary Linear Classification
Jan 17, 2025Ichiro Hashimoto, Stanislav Volgushev, Piotr ZwiernikOverfitting Empirical Risk Minimization
Department of Statistical Sciences, University of Toronto
Multiple Testing of Linear Forms for Noisy Matrix Completion
Dec 1, 2023Wanteng Ma, Lilun Du, Dong Xia +1Tensor Completion False Discovery Rate
Department of Statistics and Data Science, University of Pennsylvania, USA · Department of Decision Analytics and Operations, City University of Hong Kong, Hong Kong · Department of Mathematics, Hong Kong University of Science and Technology, Hong Kong +1

Sep 27, 2026, cs.CVJ/K move · Enter open · S save

Residual-Stream Burden Shapes Representation Learning in Diffusion Transformers

Tongtong Liang, Siqi Kou, Ziqiao Xi, Esha Singh+5

UC San Diego · Shanghai Jiao Tong University · Aether AI

Diffusion Transformers Transformer Residual Streams Residual Stream Transformer Architectures Representation Learning Spectral+1

Open paper AskPDF arXiv

In diffusion-based generation, a neural network can be trained to predict the clean data, the noise, or the velocity from a noisy input. These prediction targets are interconvertible and describe the same generative process, yet plain Diffusion Transformers operating on large pixel patches succeed with clean prediction and fail with noise or velocity prediction. We argue that this asymmetry arises because noisy targets require the residual stream to preserve noise-dependent input variation through depth for the final readout, forcing subsequent layers to compute on noisy representations. A spectrally concentrated clean target imposes a lighter demand, leaving greater freedom to organize hidden representations for subsequent computation. We call this preservation requirement residual-stream burden and show how it shapes representation learning in Diffusion Transformers. Controlled experiments indicate that the exploitable structure is spectral concentration in patch space and that the bandwidth of the persistent residual state is a key resource for noisy prediction. We further show that this account is consistent with recent decoupled pixel-space architectures, whose diverse designs all reduce the residual-stream burden on the main pathway. To examine this understanding from a complementary direction, we expand and reorganize the residual-stream bandwidth directly, introducing Spatially Indexed Hyper-Connections (SiHC) that reach FID 1.71 on ImageNet

256^2

. Together, these results identify residual-stream burden as a mechanism through which prediction targets and architecture jointly shape representation learning in Diffusion Transformers.

Momentum

Related topics

Latest papers 53