Adaptive Loss Weighting

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 66

All topics

Time-Frequency Weighted Losses for Phoneme Reconstruction in DNN-Based Speech Enhancement
Jun 19, 2026Nasser-Eddine Monir, Paul Magron, Romain SerizelSpeech Enhancement Adaptive Loss Weighting
Université de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France
SCR-Guided Difficulty-Aware Optimization for Infrared Small Target Detection
Jun 17, 2026Yunus Sevim, Behçet Uğur TöreyinInfrared Small Target Detection Adaptive Loss Weighting
Aselsan · Ankara, Turkey · Istanbul Technical University +1
Multi-Level Analyzation of Imbalance to Resolve Non-IID-Ness in Federated Learning
Jun 8, 2026Haengbok Chung, Jae Sung LeeClass-Imbalanced Learning Federated Learning Aggregation
Interdisciplinary Program in Artificial Intelligence, Seoul National University, Republic of Korea · Department of Nuclear Medicine, Seoul National University College of Medicine, Republic of Korea · Brightonix Imaging Inc. Seoul, Republic of Korea
Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment
Jun 7, 2026Mohammadnavid Ghader, Saeed Reza Kheradpisheh, Bahar Farahani +1Adaptive Loss Weighting Convolutional Neural Networks
Department of Computer and Data Science, Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran, Iran · Cyberspace Research Institute, Shahid Beheshti University, Tehran, Iran · Cybersecurity and Computing Systems Research Group, University of Hertfordshire, Hatfield, United Kingdom
Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
Jun 5, 2026Zixi Li, Youzhen LiText-to-Music Generation Diffusion Transformer
Sun Yat-sen University · Datawhale
FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysis
Jun 3, 2026Shuo Liu, Xianghong Lin, Yukun Wei +1Class-Imbalanced Learning Few-Shot Learning
International School, Beijing University of Posts and Telecommunications, Beijing 100876, China · School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876, China
Towards Compact Autonomous Driving Perception with Balanced Learning and Multi-sensor Fusion
Jun 2, 2026Oskar Natan, Jun MiuraDepth Estimation Autonomous Driving Perception
Department of Computer Science and Engineering, Toyohashi University of Technology, Aichi 441-8580, Japan · Department of Computer Science and Electronics, Gadjah Mada University, Yogyakarta 55281, Indonesia
MoEIoU: Rethinking Bounding-Box Regression as a Mixture of Experts
May 30, 2026Vinay Edula, Priyanka BagadeMixture of Experts Adaptive Loss Weighting
Department of Computer Science and Engineering Indian Institute of Technology Kanpur Kanpur, U.P, India
AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates
May 27, 2026Shaolong Chen, Madalina Ciobanu, Qingqing Mao +1LLM Alignment Direct Preference Optimization
Incept Labs Houston, TX · Incept Labs, Houston, TX · Titan Holdings, San Francisco, CA
Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration
May 27, 2026Zili Wang, Jiajun Chai, Lin Chen +3Multi-Token Prediction RL for Language Model Reasoning
School of Artificial Intelligence, University of Chinese Academy of Sciences, China · MAIS, Institute of Automation, Chinese Academy of Sciences, China · Meituan
GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
May 25, 2026Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2Supervised Fine-Tuning Adaptive Loss Weighting
Shanghai Jiao Tong University · Shanghai Maritime University
Self-Balancing Gradient Allocation for Heterogeneity-Aware Feature Generation in Click-Through Rate Prediction
May 24, 2026Moyu Zhang, Yun Chen, Yujun Jin +3Adaptive Loss Weighting CTR Prediction
Alibaba Group · Beijing, China
OSDTW: Optimal Shared Depth and Task Weighting for Long-Tailed Recognition
May 24, 2026Chang Chu, Qingyue Zhang, Shao-Lun Huang +1Long-Tailed Classification Representation Learning
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Shenzhen Zkosemi Semiconductor Technology Co., Ltd, Shenzhen, China
Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens
May 20, 2026Meng Shen, Minghao Wu, Deepu RajanVision-Language Models Hallucination in Language Models
Nanyang Technological University · Monash University
LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models
May 19, 2026Hyunsoo Han, Sangyeop Yeo, Jaejun YooModel Compression Diffusion Model Distillation
Ulsan National Institute of Science and Technology (UNIST)
Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization
May 18, 2026Anh B. H. Nguyen, Ba Tho Phan, Viet Cuong TaClass-Imbalanced Learning Long-Tail Learning
VNU University of Engineering and Technology, Hanoi, Vietnam
Avoiding Structural Failure Modes in Tabular Fair SSL: Online Primal-Dual Allocation under Confidence Gating
May 15, 2026Hangchuan Liang, Changchun LiPrimal-Dual Optimization Group Fairness
College of Computer Science and Technology, Jilin University, China · Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, Jilin University, China
InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting
May 14, 2026Mahdi Sabbaghi, George Pappas, Adel Javanmard +1Supervised Fine-Tuning Adaptive Loss Weighting
University of Pennsylvania · University of Southern California
A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions
May 12, 2026Mohamed Mahmoud Amar, Nairouz Mrabah, Mohamed Bouguessa +1Graph Representation Learning Graph SSL
Department of Computer Science, University of Quebec at Montreal, Montreal, QC, Canada
Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing
May 11, 2026Jinchang Zhu, Jindong Li, Chengyu Zou +4Long-Context Language Modeling Adaptive Loss Weighting
1The Hong Kong University of Science and Technology (Guangzhou) · Institute of Artificial Intelligence (TeleAI), China Telecom
Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks
May 11, 2026Bum Jun Kim, Gnankan Landry Regis N'guessanGradient Interference Adaptive Loss Weighting
The University of Tokyo, Japan · Axiom Research Group · Department of Applied Mathematics and Computational Science, NM-AIST, Tanzania +3
Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View
May 11, 2026Jinping Wang, Zixin Tong, Zhiwu Xie +1Long-Tailed Classification Adaptive Loss Weighting
CSMT, Wenzhou-Kean University · International Frontier Interdisciplinary Research Institute, Wenzhou-Kean University
When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretraining
May 8, 2026Ivan Karpukhin, Andrey SavchenkoSelf-Supervised Pre-Training Adaptive Loss Weighting
Sber AI Lab · HSE University ISP RAS Research Center for Trusted Artificial Intelligence
Beyond the False Trade-off: Adaptive EWC for Stealthy and Generalizable T2I Backdoors
May 8, 2026Lu Bowen, Xinyu Tang, Yin Yin Low +1Backdoor Attacks Elastic Weight Consolidation
Monash University
TsallisPGD: Adaptive Gradient Weighting for Adversarial Attacks on Semantic Segmentation
May 5, 2026Alexander Matyasko, Xin Lou, Indriyati Atmosukarto +1Adversarial Attacks Adaptive Loss Weighting
Singapore Institute of Technology, Singapore
Dynamic Distillation and Gradient Consistency for Robust Long-Tailed Incremental Learning
May 5, 2026Taigo Sakai, Kazuhiro HottaClass-Incremental Learning Long-Tail Learning
Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya 468-8502, Japan
Adaptive Equilibrium: Dynamic Weighting Framework for Generalized Interruption of DeepFake Models
May 1, 2026Hongrui Zheng, Liejun Wang, Zhiqing GuoAdversarial Attacks Adaptive Loss Weighting
School of Computer Science and Technology, Xinjiang University, Urumqi, China · Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, Urumqi, China · Silk Road Multilingual Cognitive Computing International Cooperation Joint Laboratory, Xinjiang University, Urumqi, China
IMPA-Net: Meteorology-Aware Multi-Scale Attention and Dynamic Loss for Extreme Convective Radar Nowcasting
Apr 27, 2026Haofei Cui, Guangxin He, Juanzhen Sun +5Precipitation Forecasting Multi-Scale Feature Fusion
Key Laboratory of Meteorological Disaster, Ministry of Education (KLME) / International Joint Research Laboratory on Climate and Environment Change (ILCEC) / Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters, Nanjing University of Information Science and Technology, Nanjing 210044, China. · Nanchang Meteorological Bureau, Nanchang 330000, China. · National Center for Atmospheric Research, Boulder, CO 80301, USA. +3
Weighting What Matters: Boosting Sample Efficiency in Medical Report Generation via Token Reweighting
Apr 22, 2026Alexander Weers, Daniel Rueckert, Martin J. MentenMedical Report Generation Healthcare
TUM School of Computation, Information and Technology, Technical University of Munich, DE · Munich Center for Machine Learning (MCML), DE · Department of Computing, Imperial College London, UK
Meta Additive Model: Interpretable Sparse Learning With Auto Weighting
Apr 22, 2026Xuelin Zhang, Xinyue Liu, Lingjuan Wu +1Robust Regression Adaptive Loss Weighting
College of Informatics, Huazhong Agricultural University, Wuhan, China

Jun 19, 2026, cs.SDJ/K move · Enter open · S save

Time-Frequency Weighted Losses for Phoneme Reconstruction in DNN-Based Speech Enhancement

Nasser-Eddine Monir, Paul Magron, Romain Serizel

Université de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France

Speech Enhancement Adaptive Loss Weighting

Open paper AskPDF arXiv

Conventional training losses for speech enhancement based on the signal-to-distortion ratio (SDR) treat all time-frequency (TF) regions uniformly, overlooking the fine-grained spectral cues that are relevant to specific phoneme intelligibility. We propose a TF weighting framework that modulates the SDR objective based on local speech presence, speech-to-interference ratio (SIR), and spectral flux. By integrating these factors into a differentiable objective, the framework emphasizes TF bins with high speech-noise competition while also accounting for transient cues such as consonant bursts. Experimental results show that our approach improves objective frequency-weighted enhancement metrics, as well as phoneme recognition accuracy, particularly for consonants. Spectral analysis shows better reconstruction of mid-frequency structures at less adverse SIR.

Momentum

Related topics

Latest papers 66