Layer-Wise

Ask about this topic

Momentum

7 papers in the last four weeks, up 75% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21
View on map

Latest papers 104

All topics
CardsList

  1. Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs

    Oct 1, 2026Youngwoo Shin, Yusung Ro, Minseo Kim +1Inference-TimeLayer-Wise

    Korea Advanced Institute of Science and Technology (KAIST)

  2. Persistent Depth Ordering amid Shifting Block-Bypass Responses in Language Model Pretraining

    Oct 1, 2026Shengye Tao, Yinzhu Cheng, Haihua XieLayer-WiseResponses

    Beijing University of Civil Engineering and Architecture · Beijing Institute of Mathematical Sciences and Applications (BIMSA) · Institute of Statistics and Big Data, Renmin University of China

  3. Increasing Width Allows Greedy Layer-wise Training to Rival End-to-End Backpropagation in Self-Supervised Learning

    Sep 30, 2026Syon Mansur, Joel ZylberbergBackpropagationLayer-Wise

    Jules Stein Eye Institute University of California, Los Angeles Los Angeles, CA 90095, USA

  4. Right In-Place (RiP) Convolution: A Simple, General, and Near-Optimal Strategy for Memory-Efficient CNN Inference

    Sep 30, 2026Opegbemi Matthias Busoye, Tolulope Matthew Busoye, Eghonghon-aye EigbeNeural Network InferenceConvolutional

    PowerLabs Technologies, Lagos, Nigeria

  5. Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding

    Sep 28, 2026Haohui Zhang, Keyu Chen, Haocheng Sun +4Speculative DecodingDrafter

    Shanghai Jiao Tong University · Tencent YouTu Lab · Xiamen University

  6. LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations

    Sep 23, 2026Sandra Arcos-Holzinger, Debashish Chakraborty, Rohita Mocharla +7Multimodal RepresentationsFine-Grained Video Understanding

    Johns Hopkins University · University of Melbourne · Human Language Technology Center of Excellence +2

  7. Beyond Depth Truncation: Controlled Evaluation of Depth Utilization in Recursive Language Models

    Sep 17, 2026Ha Van Dau, Thanh Tung Khuat, Nguyen Thanh DungLayer-WiseTruncation

    NuverxAI - AI & Creative Innovation Company Limited · Ho Chi Minh City University of Technology (HCMUT)

  8. Pre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VLM Vision Encoders

    Sep 14, 2026Qingtao Xia, Jiahua Bao, Siyao Cheng +1Parameter-Efficient Fine-Tuning MethodsVision-Language Model Adaptation

    Faculty of Computing Harbin Institute of Technology Harbin, China

  9. Temporal Recurrence Favors Fewer Layers

    Sep 14, 2026Ivan Anokhin, Johan Obando-Ceron, Irina Rish +1Recurrent ModelRecurrence

    Mila – Qu´ebec AI Institute · Universit´e de Montr´eal · Sakana AI

  10. Charts Are Beyond Pixels: Probing for Layer-Wise Chart Understanding and Editing

    Sep 8, 2026Xiaochuan Zhong, Yifan Hou, Chenxi Pang +1ChartLayer-Wise

    DeepDelta Lab, School of Artificial Intelligence, Shanghai Jiao Tong University · ETH Zurich · Google DeepMind

  11. Some Emotions Run Deeper: Layer-wise Probing and Causal Intervention in Large Language Models

    Sep 1, 2026Tian Fang, Gaël Guibon, Davide BuscaldiEmotionLayer-Wise

    1Université Sorbonne Paris Nord, CNRS, Laboratoire d’Informatique de Paris Nord, LIPN · 2LORIA, CNRS, Université de Lorraine

  12. Toppling the Hierarchy in Byte-level Language Modeling

    Aug 31, 2026Lukas Edman, Alexander FraserLanguage ModelingLayer-Wise

    School of Computation, Information and Technology, TU Munich · Munich Center for Machine Learning · Munich Data Science Institute

  13. The Depth Flow of Token Representations Is Nonlinear and Does Not Descend Its Own Density

    Aug 30, 2026Alexandre QuemyLayer-WiseLangevin Dynamics

    Hother Labs

  14. Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling

    Aug 4, 2026Nathan Labiosa, David Buff, Ena Nayak +1Large Language Models FailLayer-Wise

    University of Southern California

  15. Analyzing Speech Condition Effects in Dysarthric ASR: A Layer-wise Probing Study

    Aug 3, 2026Darwin Jelestin Muthu, Navya Gupta, Wei Lin Tay +3Dysarthric SpeechAutomatic Speech Recognition

    Singapore Institute of Technology

  16. Divergent large language model predictions from convergent representations in ambiguous word pairs

    Aug 3, 2026K. Jack Scott, Narun Pat, Veronica LiesaputraTransformer EncoderLayer-Wise

    Department of Psychology, University of Otago, Dunedin, New Zealand · School of Computing, University of Otago, Dunedin, New Zealand

  17. The Learning Objective Governs Perceptual Narrowing: A Cross-Lingual, Layer-Wise, Ten-Seed Study of Self-Supervised Speech Encoders

    Aug 1, 2026Sejin YooSpeech EncoderGrapheme-To-Phoneme

    Independent Researcher

  18. Explicit Layer Modeling for Video Object Insertion and Video Layer Decomposition

    Jul 28, 2026Kyujin Han, Seungjoo Shin, Sunghyun ChoLayer-WiseDecomposition

    POSTECH, Republic of Korea

  19. The Intruder Threshold: A Spectral Law for LoRA Fine-Tuning

    Jul 26, 2026Peng XieModel Fine-TuningLayer-Wise

    Technical University of Munich, Campus Heilbronn

  20. Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation

    Jul 24, 2026Yuqi Li, Xi Xiao, Yunbei Zhang +6Recent Vision Foundation ModelsFrozen Vision-Language Models

    City College of New York, CUNY · New York, NY, USA · University of Alabama at Birmingham +11

  21. An Analysis of Residual-Stream Geometry Across Transformer Depth

    Jul 20, 2026Sunit Bhattacharya, Ravi Shankar KolliTransformer Residual StreamsResidual Stream

    ProRata AI

  22. LionVote: Per-Layer Learning Rate Adaptation for Lion

    Jul 10, 2026Kris AtallahBatchLayer-Wise

    New York University, New York, USA · New York University New York, NY, USA

  23. When Synthetic Speech Is All You Have: Better Call GRPO

    Jul 9, 2026Shashi Kumar, Yanis Labrak, Hasindri Watawana +5Flow-GrpoSpeech-To-Text Alignment

    Idiap Research Institute, Martigny, Switzerland · EPFL, Lausanne, Switzerland · Uniphore, U.S.A. +1

  24. Prompt Compression via Activation Aggregation

    Jul 9, 2026Thibaud Ardoin, Semira Einsele, Evis Bregu +1Large Language Model CompressionInstruction-Tuned Models

    Freie Universität Berlin

  25. Understanding Layer Patching in Model Size Interpolation

    Jul 9, 2026Sara Kangaslahti, Jonathan Geuter, Nihal V. Nayak +3Model SizeLayer-Wise

    1Harvard University · 2Kempner Institute · 3IST Austria

  26. PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning

    Jul 8, 2026Yazdan Jamshidi, Alexey ShvetsUnstructured PruningLarge Language Model Compression

    Palo Alto Networks

  27. InsideSSL: Understanding Self-Supervised Speech Representations using a Model-Centric Perspective

    Jul 7, 2026Samir Sadok, Xavier Alameda-PinedaSelf-Supervised Speech ModelsWav2Vec

    Inria, Universit´e Grenoble Alpes CNRS, LJK, France

  28. Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing

    Jul 6, 2026Babak Barazandeh, Subhabrata Majumdar, Vinay Prithyani +1Layer-WiseLocalized Lora-Moe

    Fortinet · Indian Institute of Management Bangalore · Citadel Securities +1

  29. Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers

    Jul 6, 2026Ligong Han, Kai Xu, Hao Wang +3Homomorphic EncryptionTransformer Architectures

    MBZUAI IFM · Red Hat AI Innovation · MIT-IBM Watson AI Lab +3

  30. Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space

    Jul 2, 2026Di Wu, Huan Liu, Zhixiang Chi +3Neural RepresentationsNeural Network Inference

    University of Toronto · National University of Singapore · McMaster University +1

  31. Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

    Jul 1, 2026Zijian Zhang, Rizhen Hu, Athanasios Glentis +4Transformer ArchitecturesLayer-Wise

    University of Minnesota · Peking University · Amazon

  32. Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization

    Jun 29, 2026Haoming Meng, Anton Sugolov, Vardan PapyanGradientLayer-Wise

    Department of Mathematics, University of Toronto, Toronto, Canada · Vector Institute, Toronto, Canada

  33. LWDrive: Layer-Wise World-Model-Guided Vision-Language Model Planning for Autonomous Driving

    Jun 29, 2026Chen Yang, Yuhao Wei, Ze Xu +6Autonomous DrivingClassical Planning

    Chongqing University

  34. CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry

    Jun 25, 2026Huzama Ahmad, Cao Viet Hai Nam, Se-Young YunTransformer ArchitecturesLayer-Wise

    KAIST

  35. Layer-wise Probing of wav2vec 2.0 and Whisper for Consonant Cluster Reduction in African American English

    Jun 22, 2026Hamid Mojarad, Kevin TangWav2VecGrapheme-To-Phoneme

    Department of English Language and Linguistics, Institute of English and American Studies, Faculty of Arts and Humanities, Heinrich Heine University Dösseldorf, Germany · Department of Linguistics, University of Florida, United States of America

  36. Tapered Language Models

    Jun 22, 2026Reza Bayat, Ali Behrouz, Aaron CourvilleLanguage ModelingLayer-Wise

    1Mila · 2Cornell University · 3Université de Montréal +1

  37. How Well Do Self-Supervised Speech Models Encode Age and Gender in Children's Speech? A Layer-Wise Analysis Across Multiple Architectures

    Jun 20, 2026Abhijit Sinha, Hemant Kumar Kathania, Mohit Joshi +3Self-Supervised Speech ModelsWav2Vec

    aNational Institute of Technology Sikkim, India · bSignal Analysis and Interpretation Lab (SAIL), University of Southern California, USA

  38. Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling

    Jun 19, 2026Borui Cai, Yao ZhaoNeural DynamicsSequence Modeling

    Hangzhou International Innovation Institute, Beihang University, China · Victoria University, Melbourne, Australia

  39. HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization

    Jun 18, 2026Zhentao Tan, Wei Chen, Jingyi Shen +4Efficient Long-Context InferenceLayer-Wise

    Alibaba Group

  40. RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer

    Jun 16, 2026Jinhao You, Shuo Lyu, Zhuohang Lyu +5Visual Geometry Grounded TransformerSelf-Supervised Vision Transformers

    University of Pennsylvania · University of California, Irvine · Nanyang Technological University +1

  41. Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning

    Jun 15, 2026Tobias Jan Wieczorek, Leon de Andrade, Thomas Möllenhoff +1Bayesian Neural NetworksUncertainty

    TU Darmstadt & hessian.AI, Darmstadt, Germany · RIKEN Center for Advanced Intelligence Project, Tokyo, Japan

  42. Beyond Layer Importance in Layer-wise Sparsity: An Inter-Layer Perturbation-Absorption Perspective

    Jun 13, 2026Tao Jing, Ningxin Wu, Chen Kang +3Unstructured PruningLayer-Wise

  43. Learning Dynamics Reveal a Hierarchy of Weight-Induced Layerwise Gram Metrics

    Jun 8, 2026Claudio NordioRectified Linear Unit NetworksLearning Dynamics

  44. Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis

    Jun 8, 2026Samuele Punzo, Niccolò Caselli, Ippokratis Pantelidis +3Video Foundation ModelsFoundation Model

    University of Amsterdam, Netherlands.

  45. Trajectory Geometry of Transformer Representations Across Layers

    Jun 8, 2026Vishal Pandey, Gopal Singh, Yacine MahdidTransformer ArchitecturesLayer-Wise

    London, UK · Athens, GR · Montreal, CA

  46. RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT

    Jun 6, 2026Kyumin Choi, Ikbeom JangVisual Token PruningSelf-Supervised Vision Transformers

    Hankuk University of Foreign Studies Seoul, South Korea

  47. The Geometry of Last-Layer Model Stealing

    Jun 5, 2026Snigdha Chandan KhilarLayer-WiseTransformer Architectures

    Independent Researcher.

  48. Skip a Layer or Loop It? Learning Program-of-Layers in LLMs

    Jun 4, 2026Ziyue Li, Yang Li, Tianyi ZhouLLM Inference OptimizationLLM Reasoning Strategies

    University of Maryland, College Park, MD, USA · 2MBZUAI, Abu Dhabi, UAE.

  49. Class-Specific Branch Attention for Mitigating Gradient Interference under Class Imbalance

    Jun 4, 2026Arush Singhal, Umang SoniImbalanced ClassificationClass Imbalance

    aThapar Institute of Engineering and Technology, Patiala, India · bNetaji Subhash University of Technology, New Delhi, India

  50. Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs

    Jun 3, 2026Wanhao Yu, Ziyan Wang, Zheng Wang +7Continual Fine-TuningZeroth-Order

    University of North Carolina at Charlotte · University of Houston · State University of New York at Binghamton +2

  51. Depth-Attention: Cross-Layer Value Mixing for Language Models

    Jun 3, 2026Boyi Zeng, Yiqin Hao, Zitong Wang +7Layer-WiseCross-Layer Interactions

    LUMIA Lab, School of Artificial Intelligence, Shanghai Jiao Tong University · Sun Yat-sen University · Shanghai Innovation Institute +2

  52. PURGE: Projected Unlearning via Retain-Guided Erasure

    Jun 2, 2026Vedant Jawandhia, Daksh Ahuja, Ghufran Alam Siddiqui +3Machine UnlearningConcept Erasure

    1BITS Pilani, Pilani Campus, India

  53. Beyond Compression: Quantifying Spectral Accessibility in Vision Representations

    Jun 2, 2026Akayou A. Kitessa, Yijun ZhaoVision EncodersSpectral

    Fordham University New York City, NY

  54. Refit the Probe: Single-Direction Ablation Is Not a Necessity Test

    May 30, 2026Yuhang JiangLayer-WiseSequence Modeling

    Independent Researcher

  55. LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training

    May 28, 2026Minju Gwak, Minseo Kwak, Dongseok Lee +3Reinforcement Learning Post-TrainingRepresentation-Level Misalignment

    Yonsei University · Seoul National University · Georgia Institute of Technology

  56. When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception

    May 28, 2026Vahideh ZolfaghariDeceptionLayer-Wise

    Algoverse AI Research, Algoverse AI Research Mentorship Program, USA. · Medical Sciences Education Research Center, Mashhad University of Medical Sciences, Mashhad, Iran. · Student Research Committee, Department of Health Information Technology and Management, Medical Informatics, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran.

  57. Model Merging by Output-Space Projection

    May 27, 2026Bethan Evans, Benjamin Etheridge, Stephen Roberts +1Continual Model MergingMulti--Task Learning

    Department of Mathematics, University of Oxford, Oxford, UK · Department of Engineering Science, University of Oxford, Oxford, UK.

  58. Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations

    May 27, 2026Simardeep Singh, Paras ChopraPerceptuallyLayer-Wise

    Indian Institute of Technology Roorkee, Roorkee, India · Lossfunk, India

  59. Do Agents Think Deeper? A Mechanistic Investigation of Layer-Wise Dynamics in Sequential Planning

    May 27, 2026Zhenyu Cui, Xiangzhong LuoLarge Language Model AgentsLLM Reasoning Strategies

  60. Locality-Aware Redundancy Pruning for LLM Depth Compression

    May 27, 2026Vincent-Daniel Yun, Youngrae Kim, Woosang Lim +3Large Language Model CompressionLayer-Wise

    University of Southern California, United States · Neural Superintelligence Lab, MODULABS, Republic of Korea · Seoul National University, Republic of Korea +1