Cross-Modal Knowledge Distillation

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 83

All topics

Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
May 12, 2026Seonghoon Yu, Dongjun Nam, Byung-Kwan Lee +1Cross-Modal Knowledge Distillation CoT Distillation
1KAIST · 3POSTECH · 2NVIDIA
Thermal-Det: Language-Guided Cross-Modal Distillation for Open-Vocabulary Thermal Object Detection
May 11, 2026Yasiru Ranasinghe, Elim Schenck, Florence Yellin +3Open-Vocabulary Object Detection Cross-Modal Knowledge Distillation
Johns Hopkins University · Kitware · DEVCOM Army Research Laboratory
Hyperbolic Distillation: Geometry-Guided Cross-Modal Transfer for Robust 3D Object Detection
May 11, 2026Kanglin Ning, Wenrui Li, Houde Quan +3Cross-Modal Knowledge Distillation 3D Object Detection
Faculty of Computing, Harbin Institute of Technology, Harbin 150001, China · Suzhou Research Institute of HIT
Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT
May 10, 2026Alaa Asfour, Christopher Indris, Leihan Chen +2Cross-Modal Knowledge Distillation 3D Spatial Reasoning
Department of Computer Science, Toronto Metropolitan University, Toronto, ON, Canada
Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification
May 6, 2026Wen Wen, Hao Chen, Shiliang ZhangCross-Modal Knowledge Distillation Continual Learning
University of Electronic Science and Technology of China, China · Harbin Institute of Technology, Shenzhen, China · Peking University, China
SpectraDINO: Bridging the Spectral Gap in Vision Foundation Models via Lightweight Adapters
May 4, 2026Yagiz Nalcakan, Hyeongjin Ju, Incheol Park +3Cross-Modal Knowledge Distillation Multispectral Object Detection
Yonsei University, Seoul, Republic of Korea
FLoRA: Fusion-Latent for Optical Reconstruction and Flood Area Segmentation via Cross-Modal Multi-Task Distillation Network
May 4, 2026Jagrati Talreja, Tewodros Syum Gebre, Leila Hashemi-BeniCross-Modal Knowledge Distillation Multi-Source Image Fusion
Geomatics Program, College of Science and Technology, North Carolina A&T Technical State University, Greensboro, North Carolina 27411, USA · Institute for Water, Environment and Health, United Nations University, Richmond Hill, Ontario, Canada
From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation
Apr 21, 2026Zhong Han Ervin Yeoh, Jiang KanCross-Modal Knowledge Distillation Few-Shot Learning
Department of Business Analytics School of Computing National University of Singapore · Department of Computer Science School of Computing National University of Singapore
Feasibility of Indoor Frame-Wise Lidar Semantic Segmentation via Distillation from Visual Foundation Model
Apr 20, 2026Haiyang Wu, Juan J. Gonzales Torres, George Vosselman +1Cross-Modal Knowledge Distillation Vision Foundation Model Adaptation
Department of Earth Observation Science, Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7522 NB Enschede, The Netherlands
Source-Free Domain Adaptation with Vision-Language Prior
Apr 20, 2026Song Tang, Yunxiang Bai, Wenxin Su +3Source-Free Domain Adaptation Cross-Modal Knowledge Distillation
Institute of Machine Intelligence (IMI), University of Shanghai for Science and Technology, Shanghai, China · Technical Aspects of Multimodal Systems (TAMS) Group, Department of Informatics, Universität Hamburg, Hamburg, Germany · European Molecular Biology Laboratory, Heidelberg, Germany +2
Intervention-Aware Multiscale Representation Learning from Imaging Phenomics and Perturbation Transcriptomics
Apr 19, 2026Jiayuan Chen, Ruoqi Liu, Zishan Gu +1Cross-Modal Knowledge Distillation Cross-Modal Representation Learning
The Ohio State University
OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction
Apr 18, 2026Zhongyuan Liang, Junhyung Jo, Hyang-Jung Lee +2Contrastive Learning Cross-Modal Knowledge Distillation
Computational Precision Health UC Berkeley, UCSF · Samsung Advanced Institute of Technology (SAIT) · Computational Precision Health UC Berkeley, UCSF[cs.LG]
Channel Attention-Guided Cross-Modal Knowledge Distillation for Referring Image Segmentation
Apr 18, 2026Chen YangCross-Modal Learning Cross-Modal Knowledge Distillation
School of Information Science and Technology, TaiShan University, Taian, China
Temporal Cross-Modal Knowledge-Distillation-Based Transfer-Learning for Gas Turbine Vibration Fault Detection
Apr 16, 2026Ali Bagheri Nejad, Mahdi Aliyari-Shoorehdeli, Abolfazl HasanzadehCross-Modal Knowledge Distillation Predictive Maintenance
Electrical Engineering Department K. N. Toosi University of Technology, Tehran, Iran · MECO, Karaj, Iran
Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models
Apr 16, 2026Haoyi Sun, Xiaoxiao Wang, Ning Mao +5Cross-Modal Knowledge Distillation Vision-Language Models
Li Auto Inc.
MINT: Multimodal Imaging-to-Speech Knowledge Transfer for Early Alzheimer's Screening
Feb 27, 2026Vrushank Ahire, Yogesh Kumar, Anouck Girard +1Cross-Modal Knowledge Distillation Alzheimer's Disease
Department of Computer Science and Engineering, Indian Institute of Technology Ropar, India · Embry-Riddle Aeronautical University, Florida, USA
Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
Jan 30, 2026Yanlong Chen, Amirhossein Habibian, Luca Benini +1Cross-Modal Knowledge Distillation Vision-Language Models
Department of Information Technology and Electrical Engineering, ETH Zurich, Zurich, Switzerland · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · Qualcomm AI Research, Amsterdam, the Netherlands +1
MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment
Sep 17, 2025Elena Camuffo, Francesco Barbato, Mete Ozay +2Cross-Modal Knowledge Distillation Efficient Object Detection
Samsung R&D Institute UK, United Kingdom · University of Padova, Italy
GenRecal: Generation after Recalibration from Large to Small Vision-Language Models
Jun 18, 2025Byung-Kwan Lee, Ryo Hachiuma, Yong Man Ro +2Cross-Modal Knowledge Distillation VLM Distillation
NVIDIA · KAIST
TeD-Loc: Text Distillation for Weakly Supervised Object Localization
Jan 22, 2025Shakeeb Murtaza, Soufiane Belharbi, Alexis Guichemerre +2Cross-Modal Knowledge Distillation Weakly Supervised Learning
LIVIA, ILLS, Dept. of Systems Engineering, ETS Montreal, Canada
Tuned Reverse Distillation: Enhancing Multimodal Industrial Anomaly Detection with Crossmodal Tuners
Dec 12, 2024Xinyue Liu, Jianyuan Wang, Biao Leng +1Cross-Modal Knowledge Distillation Industrial Anomaly Detection
School of Computer Science and Engineering, Beihang University, Beijing 100191, China · Key Laboratory of Intelligent Bionic Unmanned Systems, Ministry of Education, and the School of Artificial Intelligence, University of Science and Technology Beijing, Beijing 100083, China · School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China
A Multimodal Feature Distillation with Mamba-Transformer Network for Brain Tumor Segmentation with Incomplete Modalities
Apr 22, 2024Ming Kang, Fung Fung Ting, Shier Nee Saw +3Cross-Modal Knowledge Distillation Cross-Modality Medical Image Segmentation
School of Information Technology, Monash University, Malaysia Campus, Subang Jaya 47500, Malaysia · Augmented Intelligence and Multimodal analytics (AIM) for Health Lab, Faculty of Information Technology, Monash University, Clayton VIC 3800, Australia · Monash Medical AI Group, Monash University, Clayton VIC 3800, Australia +1
CLIP-RD: Relational Distillation for Efficient CLIP Knowledge Distillation
Date pendingJeannie Chung, Hanna Jang, Ingyeong Yang +2Cross-Modal Learning Cross-Modal Knowledge Distillation
Ewha Womans University, Seoul 03760, South Korea

May 12, 2026, cs.CVJ/K move · Enter open · S save

Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation

Seonghoon Yu, Dongjun Nam, Byung-Kwan Lee, Jeany Son

1KAIST · 3POSTECH · 2NVIDIA

Cross-Modal Knowledge Distillation CoT Distillation VLM Distillation VLM Reasoning

Open paper AskPDF arXiv

Recent think-answer approaches in VLMs, such as Qwen3-VL-Thinking, boost reasoning performance by leveraging intermediate thinking steps before the final answer, but their computational cost becomes substantial, especially for larger VLMs. To distill such capabilities into compact think-answer VLMs, a primary objective is to improve the student's ability to utilize visual evidence throughout its reasoning trace, as long think-answer traces suffer from visual forgetting issues. To this end, we introduce a novel think-answer distillation framework that encourages the student to anchor its thinking on visual information by masking the student's salient reasoning prefixes. To compensate for such masked textual cues, the student is encouraged to rely more on visual evidence as an alternative source of information during distillation. Our masking strategies include: 1) token-wise salient reasoning-prefix masking, which masks high-influence reasoning prefixes selectively for each next-token prediction, and 2) self-paced masking budget scheduling, which gradually increases the masking scale according to distillation difficulty, measured by the discrepancy between teacher--student distributions. In the distillation phase, the student is guided by our salient reasoning-prefix mask, which blocks both future tokens and salient reasoning cues, in place of the standard causal mask used for auto-regressive language modeling. Experimental results show that our approach outperforms recent open-source VLMs, VLM distillation, and self-distillation methods on multimodal reasoning benchmarks, while further analyzes confirm enhanced visual utilization along the student thinking process.

Momentum

Related topics

Latest papers 83