Similarity and Metrics

Follow this topic Ask about this topic

Momentum

51 papers in the last four weeks, up 122% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 331

All topics

OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction
Apr 18, 2026Zhongyuan Liang, Junhyung Jo, Hyang-Jung Lee +2Cross-Modal Distillation International Classification Of Disease Coding
Computational Precision Health UC Berkeley, UCSF · Samsung Advanced Institute of Technology (SAIT) · Computational Precision Health UC Berkeley, UCSF[cs.LG]
UniCon: Unified Framework for Efficient Contrastive Alignment via Kernels
Apr 17, 2026Hangke Sui, Yuqing Wang, Minh N DoContrastive Alignment Large Multimodal Models
Department of Electrical & Computer Engineering, The Grainger College of Engineering, UIUC · Coordinated Science Laboratory, University of Illinois Urbana-Champaign (UIUC) · Siebel School of Computing and Data Science, The Grainger College of Engineering, UIUC +1
Aligning Backchannel and Dialogue Context Representations via Contrastive LLM Fine-Tuning
Apr 17, 2026Livia Qian, Gabriel SkantzeDialogue Benchmarks Large Language Model Backbones
Department for Speech, Music and Hearing KTH Royal Institute of Technology, Sweden
UsefulBench: Towards Decision-Useful Information as a Target for Information Retrieval
Apr 17, 2026Tobias Schimanski, Stefanie Lewandowski, Christian Woerle +3Relevance Similarity and Metrics
University of Zurich · ETH Zurich · score4more GmbH +2
What Makes a Bacterial Model a Good Reservoir Computer? Predicting Performance from Separability and Similarity
Apr 17, 2026Laura Alonso Bartolomé, Jean-Loup Faulon, Xavier HinautBacterial Colony Counting Reservoir Computing
MICALIS, Mnemosyne · University Paris Saclay, INRAE, AgroParisTech, MICALIS Institute, 78350 Jouy-en-Josas, France · Centre Inria de l’Universit´e de Bordeaux, France +4
Collaborative Filtering Through Weighted Similarities of User and Item Embeddings
Apr 16, 2026Pedro R. Pires, Rafael T. Sereicikas, Gregorio F. Azevedo +1Collaborative Filtering Recommendation Quality
Federal University of São Carlos
Brain Score Tracks Shared Properties of Languages: Evidence from Many Natural Languages and Structured Sequences
Apr 16, 2026Jingnong Qu, Ashvin Ranjan, Shane Steinert-ThrelkeldNatural Language Processing Model Activations
University of Washington
Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classification
Apr 16, 2026Meijia Wang, Guochao Wang, Haozhen Chu +4Fine-Grained Perception Similarity and Metrics
School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an 710000, China
CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space
Apr 13, 2026Sohwi Lim, Lee Hyoseok, Jungjoon Park +1Multimodal Retrieval Similarity and Metrics
KAIST
Contrast Matters: Understanding Robustness of In-Context Fine-Tuning to Target-Context Relatedness
Apr 2, 2026Deeptanshu Malu, Deevyanshu Malu, Aditya Nemiwal +1In-Context Learning Similarity and Metrics
IIT Bombay
Similarity of Neural Network Representations in Superposition
Mar 31, 2026Sunny Liu, Habon Issa, André Longon +4Representational Similarity Analysis Neural Network Representations
Cold Spring Harbor Laboratory · UC San Diego · Anthropic +2
PROMPT2BOX: Uncovering Entailment Structure among LLM Prompts
Mar 22, 2026Neeladri Bhuiya, Shib Sankar Dasgupta, Andrew McCallum +1Prompt Engineering Text Embeddings
CICS, University of Massachusetts Amherst, USA · Amazon AWS AI
Rethinking Evaluation in Retrieval-Augmented Personalized Dialogue: A Cognitive and Linguistic Perspective
Mar 15, 2026Tianyi Zhang, David TraumDialogue Benchmarks Dialogue
Institute for Creative Technologies, University of Southern California 12015 Waterfront Drive, Los Angeles, CA 90094-2536, USA
JEPA-Bisim: Learning Robust Visual Representations for Planning with Joint-Embedding Predictive World Models
Feb 20, 2026Leonardo F. Toso, Davit Shadunts, Yunyang Lu +5Latent World Models Latent Prediction
Department of Electrical Engineering, Columbia University, New York, USA. · Capital One, USA.
Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance
Feb 1, 2026Wei Yang, Hong Xie, Tao Tan +3Vision-Language Foundation Models Model Selection
School of AI and Data Science USTC
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
Jan 30, 2026Zhixiang Zhang, Zesen Liu, Yuchong Xie +2Attacker Large Language Model Large Language Model Memory
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology · Fudan University
Nonnegative matrix factorizations and related compositional models: Equivalence, identifiability, and an application on the grain-size analysis of sediments
Dec 25, 2025Qianqian Qi, Peter G. M. van der Heijden, Maarten A. PrinsNonnegative Matrix Factorization Identifiability
Hangzhou Dianzi University, China · Utrecht University, the Netherlands · University of Southampton, UK +1
Interpretable Similarity of Synthetic Image Utility
Dec 18, 2025Panagiota Gatoula, George Dimas, Dimitris K. IakovidisSynthetic Image Detection Medical Image Generation
University of Thessaly, Department of Computer Science and Biomedical Informatics, Lamia 35131 Greece
Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity
Oct 17, 2025Naoki Yoshida, Satoshi Hayakawa, Yuhta Takida +3Multimodal Contrastive Learning Contrastive Loss
The University of Tokyo · Sony Group Corporation · Sony AI
Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever
Aug 20, 2025Yixin Chen, Ying Xiong, Shangyu Wu +4Large Language Model Tool Use Retrievers
City University of Hong Kong · Mohamed Bin Zayed University of Artificial Intelligence · McGill University
NMIXX: Domain-Adapted Neural Embeddings for Cross-Lingual eXploration of Finance
Jul 13, 2025Hanwool Lee, Sara Yu, Yewon Hwang +4Financial Sentiment Analysis Cross-Lingual Consistency
FinancialNLPLab, MODULABS Shinhan Securities Seoul, Republic of Korea · FinancialNLPLab, MODULABS KT Seoul, Republic of Korea · FinancialNLPLab, MODULABS EMRO Seoul, Republic of Korea +4
Divergence-Based Similarity Function for Multi-View Contrastive Learning
Jul 9, 2025Jaehyoung Jeon, Cheolsu Lim, Myungjoo KangContrastive Learning Multi-View
Department of Mathematics, Seoul National University, Seoul, Korea · Research Institute of Mathematics, Seoul National University, Seoul, Korea
HiT-JEPA: A Hierarchical Self-supervised Trajectory Embedding Framework for Similarity Computation
Jun 17, 2025Lihuan Li, Hao Xue, Shuang Ao +2Urban Mobility Trajectory Generation
University of New South Wales Sydney, Australia · Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China
Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning
Jun 14, 2025Sara Rajaram, R. James Cotton, Fabian H. SinzReinforcement Learning From Human Feedback Preference Alignment Learning
Institute for Computer Science and Campus Institute for Data Science, University of Göttingen, Göttingen, Germany · University Hospital Tübingen, Tübingen, Germany · International Max Planck Research School for Intelligent Systems, Tübingen, Germany +2
TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree
Jun 12, 2025Yu-Yang Qian, Yuan-Ze Xu, Zhen-Yu Zhang +2Replay-Based Continual Learning Training-Side Stage-Aware Low-Rank Adaptation
National Key Laboratory for Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China · RIKEN AIP, Tokyo, Japan
Multimodal Language Models as Text-to-Image Model Evaluators
May 1, 2025Jiahui Chen, Candace Ross, Reyhane Askari-Hemmat +5Modern Text-To-Image Models Text-To-Image
1FAIR at Meta · University of Texas at Austin · ∗Work done at Meta +3
Learning from Many Voices: Literary MT Using Multi-Reference Human and Synthetic Data
Dec 24, 2024Si Wu, John Wieting, David A. SmithMachine Translation Multimodal Dataset
Northeastern University · Google DeepMind
Personalized Additive Modeling for Multi-level Federated Learning
May 26, 2024Shutong Chen, Guodong Long, Tianyi Zhou +3Federated Learning Generalized Linear Model
University of Technology Sydney, Australia · Mohamed bin Zayed University of Artificial Intelligence, UAE · The Hong Kong Polytechnic University, China
Knowledge Graph and Accurate Portrait Construction of Scientific and Technological Academic Conferences
Apr 11, 2022Runyu Yu, Zhe Xue, Ang LiKnowledge Graphs Portraits
Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, School of Computer Science (National Pilot School of Software Engineering), Beijing University of Posts and Telecommunications Beijing, China
CatSIM: A Categorical Image Similarity Metric
Apr 20, 2020Geoffrey Z. Thompson, Ranjan MaitraImage Quality Assessment Similarity and Metrics
Department of Statistics at Iowa State University, Ames, Iowa 50011, USA
CLIP-RD: Relational Distillation for Efficient CLIP Knowledge Distillation
Date pendingJeannie Chung, Hanna Jang, Ingyeong Yang +2Contrastive Language-Image Pre-Training Model Similarity and Metrics
Ewha Womans University, Seoul 03760, South Korea

Apr 18, 2026, cs.LGJ/K move · Enter open · S save

OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction

Zhongyuan Liang, Junhyung Jo, Hyang-Jung Lee, Sang Kyu Kim+1

Computational Precision Health UC Berkeley, UCSF · Samsung Advanced Institute of Technology (SAIT) · Computational Precision Health UC Berkeley, UCSF[cs.LG]

Cross-Modal Distillation International Classification Of Disease Coding Complementary Modalities Contrastive Learning Similarity and Metrics

Open paper AskPDF arXiv

Early prediction of severe clinical deterioration and remaining length of stay can enable timely intervention and better resource allocation in high-acuity settings such as the ICU. This has driven the development of machine learning models that leverage continuous streams of vital signs and other physiological signals for real-time risk prediction. Despite their promise, existing methods have important limitations. Contrastive pretraining treats all patients as equally strong negatives, failing to capture clinically meaningful similarity between patients with related diagnoses. Meanwhile, downstream fine-tuning typically ignores complementary modalities such as clinical notes, which provide rich contextual information unavailable in physiological signals alone. To address these challenges, we propose OC-Distill, a two-stage framework that leverages multimodal supervision during training while requiring only vital signs at inference. In the first stage, we introduce an ontology-aware contrastive objective that exploits the ICD hierarchy to quantify patient similarity and learn clinically grounded representations. In the second stage, we fine-tune the pretrained encoder via cross-modal knowledge distillation, transferring complementary information from clinical notes into the model. Across multiple ICU prediction tasks on MIMIC, OC-Distill demonstrates improved label efficiency and achieves state-of-the-art performance among methods that use only vital signs at inference.

Momentum

Related topics

Latest papers 331