{"total":209,"rows":[{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623,"area":"mechinterp"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235,"area":"mechinterp"},{"id":"2209.15430","title":"Relative representations enable zero-shot latent space communication","created":"2022-09-30","cited_by_count":191,"area":null},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2302.03025","title":"A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations","created":"2023-02-06","cited_by_count":144,"area":"mechinterp"},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142,"area":null},{"id":"2209.02535","title":"Analyzing Transformers in Embedding Space","created":"2022-09-06","cited_by_count":132,"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":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105,"area":null},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2110.14633","title":"Similarity and Matching of Neural Network Representations","created":"2021-10-27","cited_by_count":78,"area":null},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78,"area":null},{"id":"2206.10044","title":"Identifiability of deep generative models without auxiliary information","created":"2022-06-20","cited_by_count":70,"area":null},{"id":"2205.14258","title":"On the Symmetries of Deep Learning Models and their Internal Representations","created":"2022-05-27","cited_by_count":64,"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":"2307.08286","title":"Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity","created":"2023-07-17","cited_by_count":50,"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":"2501.19361","title":"We're Different, We're the Same: Creative Homogeneity Across LLMs","created":"2025-01-31","cited_by_count":42,"area":null},{"id":"2503.21073","title":"Shared Global and Local Geometry of Language Model Embeddings","created":"2025-03-27","cited_by_count":36,"area":null},{"id":"2402.14167","title":"T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching","created":"2024-02-21","cited_by_count":33,"area":"diffusion"},{"id":"2403.01753","title":"Training-Free Pretrained Model Merging","created":"2024-03-04","cited_by_count":32,"area":null},{"id":"2308.08643","title":"Towards Personalized Federated Learning via Heterogeneous Model Reassembly","created":"2023-08-16","cited_by_count":31,"area":null},{"id":"2502.16282","title":"Understanding the Emergence of Multimodal Representation Alignment","created":"2025-02-22","cited_by_count":31,"area":null},{"id":"2211.12491","title":"ModelDiff: A Framework for Comparing Learning Algorithms","created":"2022-11-22","cited_by_count":30,"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":"2410.06981","title":"Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders","created":"2024-10-09","cited_by_count":27,"area":"mechinterp"},{"id":"2302.06586","title":"Stitchable Neural Networks","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2402.03660","title":"On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm","created":"2024-02-06","cited_by_count":26,"area":null},{"id":"2407.16286","title":"A deeper look at depth pruning of LLMs","created":"2024-07-23","cited_by_count":23,"area":null},{"id":"2307.06966","title":"Layer-wise Linear Mode Connectivity","created":"2023-07-13","cited_by_count":22,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2506.06609","title":"Transferring Linear Features Across Language Models With Model Stitching","created":"2025-06-07","cited_by_count":21,"area":"mechinterp"},{"id":"2306.10460","title":"Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models","created":"2023-06-18","cited_by_count":20,"area":null},{"id":"2406.01583","title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2411.05561","title":"Objective drives the consistency of representational similarity across datasets","created":"2024-11-08","cited_by_count":18,"area":null},{"id":"2110.03501","title":"Pretrained Language Models are Symbolic Mathematics Solvers too!","created":"2021-10-07","cited_by_count":17,"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":"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":"2311.10367","title":"Exploring the Relationship between In-Context Learning and Instruction Tuning","created":"2023-11-17","cited_by_count":14,"area":null},{"id":"2212.04129","title":"Deep Incubation: Training Large Models by Divide-and-Conquering","created":"2022-12-08","cited_by_count":13,"area":null},{"id":"2506.04870","title":"Aligning Multimodal Representations through an Information Bottleneck","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2206.09868","title":"Understanding Robust Learning through the Lens of Representation Similarities","created":"2022-06-20","cited_by_count":12,"area":null},{"id":"2310.14993","title":"Understanding the Inner Workings of Language Models Through Representation Dissimilarity","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2407.08275","title":"Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems","created":"2024-07-11","cited_by_count":12,"area":"rag"},{"id":"2409.19425","title":"Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment","created":"2024-09-28","cited_by_count":12,"area":"mllm"},{"id":"2411.14633","title":"Evaluating Representational Similarity Measures from the Lens of Functional Correspondence","created":"2024-11-21","cited_by_count":12,"area":null},{"id":"2502.05300","title":"Parameter Symmetry Potentially Unifies Deep Learning Theory","created":"2025-02-07","cited_by_count":12,"area":null},{"id":"2206.11939","title":"Measuring Representational Robustness of Neural Networks Through Shared Invariances","created":"2022-06-23","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":"2510.13454","title":"Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator","created":"2025-10-15","cited_by_count":11,"area":null},{"id":"2205.08399","title":"How do Variational Autoencoders Learn? Insights from Representational Similarity","created":"2022-05-17","cited_by_count":10,"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":"2303.11277","title":"Model Stitching: Looking For Functional Similarity Between Representations","created":"2023-03-20","cited_by_count":10,"area":null},{"id":"2306.08590","title":"Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning","created":"2023-06-14","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":"2505.12387","title":"Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2602.15382","title":"The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems","created":"2026-02-17","cited_by_count":9,"area":"lr"},{"id":"2303.00721","title":"Bootstrapping Parallel Anchors for Relative Representations","created":"2023-03-01","cited_by_count":8,"area":null},{"id":"2307.00154","title":"Stitched ViTs are Flexible Vision Backbones","created":"2023-06-30","cited_by_count":8,"area":null},{"id":"2111.11165","title":"Graph-Based Similarity of Neural Network Representations","created":"2021-11-22","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":"2506.00653","title":"Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2601.04765","title":"Differential syntactic and semantic encoding in LLMs","created":"2026-01-08","cited_by_count":7,"area":null},{"id":"2606.22019","title":"Channel Location Constrains the Auditability of Subliminal Learning","created":"2026-06-20","cited_by_count":7,"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":"2509.19453","title":"The Platonic Universe: Do Foundation Models See the Same Sky?","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2605.18632","title":"Position: Weight Space Should Be a First-Class Generative AI Modality","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2412.11299","title":"How not to Stitch Representations to Measure Similarity: Task Loss Matching versus Direct Matching","created":"2024-12-15","cited_by_count":5,"area":null},{"id":"2512.04695","title":"TRINITY: An Evolved LLM Coordinator","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2207.08486","title":"Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications","created":"2022-07-18","cited_by_count":4,"area":null},{"id":"2311.17352","title":"Efficient Stitchable Task Adaptation","created":"2023-11-29","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":"2410.08255","title":"Investigating Representation Universality: Case Study on Genealogical Representations","created":"2024-10-10","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":"2506.05826","title":"Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning","created":"2025-06-06","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":"2510.03186","title":"Superposition disentanglement of neural representations reveals hidden alignment","created":"2025-10-03","cited_by_count":4,"area":"mechinterp"},{"id":"2603.18908","title":"Ventriloquist LLMs: Linear Alignment of Late-Stage Representations","created":"2026-03-19","cited_by_count":4,"area":null},{"id":"2606.03280","title":"A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting","created":"2026-06-02","cited_by_count":4,"area":null},{"id":"2606.21228","title":"Sakana Fugu Technical Report","created":"2026-06-19","cited_by_count":4,"area":"agents"},{"id":"2304.10767","title":"How good are variational autoencoders at transfer learning?","created":"2023-04-21","cited_by_count":3,"area":null},{"id":"2406.02329","title":"On Affine Homotopy between Language Encoders","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2501.06164","title":"Model Alignment Search","created":"2025-01-10","cited_by_count":3,"area":"alignment"},{"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":"2505.17769","title":"Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models","created":"2025-05-23","cited_by_count":3,"area":"mechinterp"},{"id":"2507.04448","title":"Transfer Learning in Infinite Width Feature Learning Networks","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2510.01706","title":"Representational Alignment Across Model Layers and Brain Regions with Multi-Level Optimal Transport","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2603.21786","title":"The Universal Normal Embedding","created":"2026-03-23","cited_by_count":3,"area":"diffusion"},{"id":"2211.07697","title":"Do Neural Networks Trained with Topological Features Learn Different Internal Representations?","created":"2022-11-14","cited_by_count":2,"area":null},{"id":"2301.01947","title":"StitchNet: Composing Neural Networks from Pre-Trained Fragments","created":"2023-01-05","cited_by_count":2,"area":null},{"id":"2302.02181","title":"Model Stitching and Visualization How GAN Generators can Invert Networks in Real-Time","created":"2023-02-04","cited_by_count":2,"area":null},{"id":"2302.11380","title":"Stress and Adaptation: Applying Anna Karenina Principle in Deep Learning for Image Classification","created":"2023-02-22","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":"2404.12917","title":"R3L: Relative Representations for Reinforcement Learning","created":"2024-04-19","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}