Semantic Representation Learning

Latest papers

21 papers2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Assessing Representation Semantics Under Language Pretraining in Fine-Grained Classification
Oct 20, 2026Md Raisul Kibria, Sébastien LafondVisual Representation Learning Semantic Representation Learning
Faculty of Science and Engineering, Åbo Akademi University, Turku, 20500, Finland
Sera: Semantic Representation Aggregation with Knowledge and LLM for Reliable and Interpretable Battery Health Forecasting
Oct 8, 2026Jiawei Li, Fang Liu, Wei Zhang +3Semantic Representation Learning Time Series Forecasting
Infocomm Technology Cluster, Singapore Institute of Technology, Singapore · School of Science and Technology, Singapore University of Social Sciences, Singapore · College of Smart Energy, Shanghai Jiao Tong University, Shanghai, China +2
How to Reduce Localization Ambiguity? Geometry-Semantic Constrained BEV Representation Learning for Satellite-Ground Localization
Sep 30, 2026Junming Feng, Panwang Xia, Qiong Wu +8Representation Learning Cross-View Geo-Localization
The Hong Kong Polytechnic University, Hong Kong · Southern University of Science and Technology · Wuhan University, Wuhan, China +2
Exact semantic readout from compressed vector representations
Sep 16, 2026Daniel QuigleyLinear Probing Embedding Compression
Center for Possible Minds Indiana University Bloomington Bloomington, IN 47408
The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding
Sep 9, 2026Gilad D. Landau, Dulhan Jayalath, Oiwi Parker JonesRepresentation Learning Neural Decoding
PNPL University of Oxford
Learning Representations through Token Prediction: Geometry, Approximation, and Downstream Guarantees
Aug 30, 2026Shulei WangLanguage Model Pretraining Next-Token Prediction
Department of Statistics, University of Illinois at Urbana-Champaign, 605 E. Springfield Ave., Champaign, IL 61820
QuantumPhaseNet: A Gauge-Covariant Geometric and Quantum-Spectral Theory of Semantic Concept Hierarchies with Prototype Validation of a Classical Quantum-Inspired Model
Aug 16, 2026Kiyotaka Kasubuchi, Kazuo FukiyaSemantic Representation Learning Quantum-Inspired ML
Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders
Aug 11, 2026Nikolai Bolik, Lennart Stöpler, Artur AndrzejakRepresentation Learning LLM Interpretability
Heidelberg University
Towards Multi-Label Graph Foundation Models: from Single-Vector Representation Learning to Multi-Semantic Basis Learning
Jul 31, 2026Dongxiao He, Jiayu Zhang, Jitao Zhao +2Domain-Adversarial Learning Representation Learning
Tianjin University Tianjin, China
Relation Geometry in Semantic Space of Language Models
Jul 29, 2026Zhihan Cao, Hiroaki Yamada, Simone Teufel +4Representation Geometry in Language Models Semantic Representation Learning
Graduate School of Information Science and Technology, The University of Tokyo · Faculty of Systems Design, Tokyo Metropolitan University · Department of Computer Science and Technology, University of Cambridge +5
Structure Before Collapse: Transient semantic geometry in next-token prediction
Jun 25, 2026Yize Zhao, Isabel Papadimitriou, Christos ThrampoulidisAutoregressive Language Modeling Next-Token Prediction
Department of Electrical and Computer Engineering, The University of British Columbia · Department of Linguistics, The University of British Columbia
Principles of Concept Representation in Sentence Encoders
Jun 5, 2026Isabelle Mohr, John Dujany, Jonathan Souquet +1Sentence Embeddings Compositional Reasoning
Idiap Research Institute · Merck KGaA
Scene Abstraction for Lexical Semantics: Structured Representations of Situated Meaning
May 21, 2026Yejin Cho, Katrin ErkRepresentation Learning Semantic Representation Learning
The University of Texas at Austin · Department of Linguistics · University of Massachusetts, Amherst
SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations
May 10, 2026Mario Edoardo Pandolfo, Enrico Grimaldi, Lorenzo Marinucci +4Neural Representation Geometry Visual Representation Learning
Dept. Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy. · National Inter-University Consortium for Telecommunications (CNIT), Parma, Italy. · Dept. of Statistical Sciences, Sapienza University of Rome, Rome, Italy. +1
Lost in State Space: Probing Frozen Mamba Representations
Apr 30, 2026Bhagyashree Wagh, Akash SinghRepresentation Geometry Representation Collapse
University of Washington · University of Florida
MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining
Apr 27, 2026Phung Gia Huy, Hai An Vu, Minh-Phuc Truong +4Representation Learning Sentence Embeddings
1Hanoi University of Science and Technology · University of Oregon · 3Monash University
Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning
Apr 16, 2026Aimen BoukhariJoint-Embedding Predictive Architecture Masked Language Modeling
´Ecole Nationale Sup´erieure d’Informatique (ESI), Algiers , Algeria
Fingerprinting Concepts in Data Streams with Supervised and Unsupervised Meta-Information
Mar 11, 2026Ben Halstead, Yun Sing Koh, Patricia Riddle +3Semantic Representation Learning Concept Drift
University of Auckland · Eindhoven University of Technology · University of Waikato and LTCI, Télécom Paris, IP-Paris +1
Epistemology of Generative AI: The Geometry of Knowing
Feb 19, 2026Ilya LevinSemantic Representation Learning Generative Modeling
Holon Institute of Technology, Holon, Israel
Coverage-aware Semantic Representation Learning for Underrepresented Visual Concepts
Feb 18, 2026Sakib Ahammed, Xia Cui, Wenqi Lu +4Representation Learning Visual Representation Learning
Department of Computing and Mathematics, Manchester Metropolitan University The Dalton Building, Chester Street, M1 5GD Manchester
A quantitative analysis of semantic information in deep representations of text and images
May 21, 2025Santiago Acevedo, Andrea Mascaretti, Riccardo Rende +3Representational Similarity Analysis Cross-Modal Representation Learning
Scuola Internazionale Superiore di Studi Avanzati (SISSA) · Universitat Pompeu Fabra (UPF) · Catalan Institute of Research and Advanced Studies (ICREA) and Universitat Pompeu Fabra (UPF)

Oct 20, 2026J/K move · Enter open · S save

Assessing Representation Semantics Under Language Pretraining in Fine-Grained Classification

Md Raisul Kibria, Sébastien Lafond

Faculty of Science and Engineering, Åbo Akademi University, Turku, 20500, Finland

Visual Representation Learning Semantic Representation Learning Fine-Grained Image Classification Explainable Image Classification

Open paper AskPDF arXiv

Understanding how supervision signals shape semantic visual representations remains challenging, particularly in fine-grained, low-data settings. Standard evaluations of vision models rely on downstream accuracy, which often fails to capture structural differences in learned representations. We propose a compact explainability-driven framework for comparing encoders trained with classification-only and caption-generation supervision on CUB-200. Using a controlled two-stage protocol in which both encoders are ultimately optimized for the same classification task, we enable a direct comparison of the resulting representations. Saliency maps are generated using attention rollout and gradient-weighted rollout and evaluated with five metrics covering faithfulness (positive and negative perturbation) and localization (keypoint emphasis, background attribution, and Earth Mover's Distance). Across random seeds and explanation methods, caption supervision yields representations that are more sensitive to the removal of salient regions, better aligned with annotated object parts, and less reliant on background regions, whereas classification supervision produces representations that are slightly more robust to the removal of low-saliency regions. An ablation study on the Oxford-IIIT Pet dataset shows consistent trends across key metrics. These results demonstrate that the proposed framework makes supervision-induced representational differences observable and quantifiable beyond downstream accuracy alone. More broadly, it provides a systematic basis for assessing learned representations and comparing alternative training and transfer-learning strategies.