{"total":160,"rows":[{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302,"area":null},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86,"area":null},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79,"area":null},{"id":"2404.12715","title":"Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration","created":"2024-04-19","cited_by_count":67,"area":null},{"id":"2305.06386","title":"Text-To-Concept (and Back) via Cross-Model Alignment","created":"2023-05-10","cited_by_count":64,"area":null},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2311.00664","title":"Latent Space Translation via Semantic Alignment","created":"2023-11-01","cited_by_count":52,"area":null},{"id":"2409.14623","title":"From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks","created":"2024-09-22","cited_by_count":49,"area":null},{"id":"2210.01738","title":"ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training","created":"2022-10-04","cited_by_count":47,"area":null},{"id":"2401.05224","title":"Do Vision and Language Encoders Represent the World Similarly?","created":"2024-01-10","cited_by_count":44,"area":null},{"id":"2412.04616","title":"Assessing and Learning Alignment of Unimodal Vision and Language Models","created":"2024-12-05","cited_by_count":32,"area":null},{"id":"2402.18496","title":"Language Models Represent Beliefs of Self and Others","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2409.02772","title":"Unifying Causal Representation Learning with the Invariance Principle","created":"2024-09-04","cited_by_count":31,"area":null},{"id":"2410.21869","title":"Cross-Entropy Is All You Need To Invert the Data Generating Process","created":"2024-10-29","cited_by_count":31,"area":null},{"id":"2402.09236","title":"Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models","created":"2024-02-14","cited_by_count":29,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2508.02546","title":"What are you sinking? A geometric approach on attention sink","created":"2025-08-04","cited_by_count":28,"area":null},{"id":"2301.11990","title":"Alignment with human representations supports robust few-shot learning","created":"2023-01-27","cited_by_count":25,"area":null},{"id":"2312.08550","title":"Harmonics of Learning: Universal Fourier Features Emerge in Invariant Networks","created":"2023-12-13","cited_by_count":23,"area":null},{"id":"2310.01211","title":"From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication","created":"2023-10-02","cited_by_count":21,"area":null},{"id":"2510.22042","title":"Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Models","created":"2025-10-24","cited_by_count":18,"area":null},{"id":"2402.16828","title":"Training Neural Networks from Scratch with Parallel Low-Rank Adapters","created":"2024-02-26","cited_by_count":17,"area":null},{"id":"2510.00296","title":"Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT","created":"2025-09-30","cited_by_count":17,"area":null},{"id":"2601.06123","title":"Latent Space Communication via K-V Cache Alignment","created":"2026-01-04","cited_by_count":17,"area":null},{"id":"2506.16895","title":"With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You","created":"2025-06-20","cited_by_count":16,"area":null},{"id":"2604.18572","title":"Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale","created":"2026-04-20","cited_by_count":16,"area":null},{"id":"2406.03631","title":"Discovering Bias in Latent Space: An Unsupervised Debiasing Approach","created":"2024-06-05","cited_by_count":15,"area":null},{"id":"2503.24129","title":"It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data","created":"2025-03-31","cited_by_count":14,"area":null},{"id":"2406.03280","title":"FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion","created":"2024-06-05","cited_by_count":13,"area":null},{"id":"2503.08980","title":"I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?","created":"2025-03-12","cited_by_count":13,"area":null},{"id":"2410.07610","title":"CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features","created":"2024-10-10","cited_by_count":12,"area":null},{"id":"2403.16986","title":"Dynamic Relative Representations for Goal-Oriented Semantic Communications","created":"2024-03-25","cited_by_count":11,"area":null},{"id":"2506.03523","title":"TokAlign: Efficient Vocabulary Adaptation via Token Alignment","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2510.05184","title":"Representation Potentials of Foundation Models for Multimodal Alignment: A Survey","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2302.08913","title":"Referential communication in heterogeneous communities of pre-trained visual deep networks","created":"2023-02-04","cited_by_count":10,"area":null},{"id":"2406.15057","title":"Latent Space Translation via Inverse Relative Projection","created":"2024-06-21","cited_by_count":10,"area":null},{"id":"2504.13101","title":"Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2303.00721","title":"Bootstrapping Parallel Anchors for Relative Representations","created":"2023-03-01","cited_by_count":8,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2505.22785","title":"Navigating the Latent Space Dynamics of Neural Models","created":"2025-05-28","cited_by_count":8,"area":null},{"id":"2509.16664","title":"$\\boldsymbol{\\lambda}$-Orthogonality Regularization for Compatible Representation Learning","created":"2025-09-20","cited_by_count":8,"area":null},{"id":"2309.09982","title":"Introspective Deep Metric Learning","created":"2023-09-11","cited_by_count":7,"area":null},{"id":"2310.01691","title":"Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models","created":"2023-10-02","cited_by_count":7,"area":null},{"id":"2411.19719","title":"Relative Representations of Latent Spaces enable Efficient Semantic Channel Equalization","created":"2024-11-29","cited_by_count":7,"area":null},{"id":"2505.17101","title":"A quantitative analysis of semantic information in deep representations of text and images","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2307.00316","title":"SHARCS: Shared Concept Space for Explainable Multimodal Learning","created":"2023-07-01","cited_by_count":6,"area":null},{"id":"2312.02730","title":"Towards Measuring Representational Similarity of Large Language Models","created":"2023-12-05","cited_by_count":6,"area":null},{"id":"2411.00246","title":"ResiDual Transformer Alignment with Spectral Decomposition","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2502.18710","title":"Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts","created":"2025-02-26","cited_by_count":6,"area":null},{"id":"2503.05283","title":"Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces","created":"2025-03-07","cited_by_count":6,"area":null},{"id":"2602.12952","title":"Transporting Task Vectors across Different Architectures without Training","created":"2026-02-13","cited_by_count":6,"area":null},{"id":"2305.15483","title":"Weakly Supervised Vision-and-Language Pre-training with Relative Representations","created":"2023-05-24","cited_by_count":5,"area":null},{"id":"2402.01514","title":"Mapping the Multiverse of Latent Representations","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2410.05021","title":"DEPT: Decoupled Embeddings for Pre-training Language Models","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2507.16680","title":"Latent Space Alignment for AI-Native MIMO Semantic Communications","created":"2025-07-22","cited_by_count":5,"area":null},{"id":"2602.06205","title":"Multi-Way Representation Alignment","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2406.15812","title":"Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations","created":"2024-06-22","cited_by_count":4,"area":null},{"id":"2409.10967","title":"Relative Representations: Topological and Geometric Perspectives","created":"2024-09-17","cited_by_count":4,"area":null},{"id":"2410.20035","title":"Training the Untrainable: Introducing Inductive Bias via Representational Alignment","created":"2024-10-26","cited_by_count":4,"area":null},{"id":"2505.19675","title":"Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2506.01599","title":"Connecting Neural Models Latent Geometries with Relative Geodesic Representations","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2506.03784","title":"When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2510.02348","title":"mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2512.03248","title":"Learning Network Sheaves for AI-native Semantic Communication","created":"2025-12-02","cited_by_count":4,"area":null},{"id":"2512.05657","title":"Over-the-Air Semantic Alignment with Stacked Intelligent Metasurfaces","created":"2025-12-05","cited_by_count":4,"area":null},{"id":"2604.04496","title":"The Indra Representation Hypothesis for Multimodal Alignment","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2304.00173","title":"Lego-Features: Exporting modular encoder features for streaming and deliberation ASR","created":"2023-03-31","cited_by_count":3,"area":null},{"id":"2310.12994","title":"Dimensions of Disagreement: Unpacking Divergence and Misalignment in Cognitive Science and Artificial Intelligence","created":"2023-10-03","cited_by_count":3,"area":null},{"id":"2402.16858","title":"Pragmatic Goal-Oriented Communications under Semantic-Effectiveness Channel Errors","created":"2024-01-19","cited_by_count":3,"area":null},{"id":"2405.20085","title":"Soft Partitioning of Latent Space for Semantic Channel Equalization","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2410.04941","title":"TOAST: Transformer Optimization using Adaptive and Simple Transformations","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2502.13757","title":"Identifying Metric Structures of Deep Latent Variable Models","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2505.13899","title":"Causes and Consequences of Representational Similarity in Machine Learning Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2511.06516","title":"You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations","created":"2025-11-09","cited_by_count":3,"area":null},{"id":"2305.19294","title":"Investigating the Effects of Fairness Interventions Using Pointwise Representational Similarity","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2310.00672","title":"GeRA: Label-Efficient Geometrically Regularized Alignment","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2401.04821","title":"MoSECroT: Model Stitching with Static Word Embeddings for Crosslingual Zero-shot Transfer","created":"2024-01-09","cited_by_count":2,"area":null},{"id":"2406.13507","title":"Scalable unsupervised alignment of general metric and non-metric structures","created":"2024-06-19","cited_by_count":2,"area":null},{"id":"2410.04525","title":"Out-of-Distribution Detection with Relative Angles","created":"2024-10-06","cited_by_count":2,"area":null},{"id":"2501.15758","title":"Distributional Surgery for Language Model Activations","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2503.11280","title":"High-Dimensional Interlingual Representations of Large Language Models","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2504.17025","title":"Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation","created":"2025-04-23","cited_by_count":2,"area":null},{"id":"2504.19327","title":"DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding","created":"2025-04-27","cited_by_count":2,"area":null},{"id":"2507.16450","title":"RIS-aided Latent Space Alignment for Semantic Channel Equalization","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2507.17456","title":"Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2508.03649","title":"Cross-Model Semantics in Representation Learning","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2510.04674","title":"Semantic Channel Equalization Strategies for Deep Joint Source-Channel Coding","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2511.05064","title":"Order-Level Attention Similarity Across Language Models: A Latent Commonality","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2601.21568","title":"Bridging Functional and Representational Similarity via Usable Information","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2601.21621","title":"Similarity of Processing Steps in Vision Model Representations","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2604.06017","title":"Toward Aristotelian Medical Representations: Backpropagation-Free Layer-wise Analysis for Interpretable Generalized Metric Learning on MedMNIST","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2605.19999","title":"LLM Benchmark Datasets Should Be Contamination-Resistant","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2607.20379","title":"Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2210.13179","title":"A simple probabilistic neural network for machine understanding","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2402.19339","title":"Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification","created":"2024-02-29","cited_by_count":1,"area":null}],"next_cursor":"100"}