{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221},{"id":"1511.07543","title":"Convergent Learning: Do different neural networks learn the same representations?","created":"2015-11-24","cited_by_count":220},{"id":"2209.15430","title":"Relative representations enable zero-shot latent space communication","created":"2022-09-30","cited_by_count":191},{"id":"1805.11222","title":"Unsupervised Alignment of Embeddings with Wasserstein Procrustes","created":"2018-05-29","cited_by_count":97},{"id":"2003.11942","title":"Towards Backward-Compatible Representation Learning","created":"2020-03-26","cited_by_count":75},{"id":"2011.09161","title":"Positive-Congruent Training: Towards Regression-Free Model Updates","created":"2020-11-18","cited_by_count":57},{"id":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","cited_by_count":57},{"id":"2311.00664","title":"Latent Space Translation via Semantic Alignment","created":"2023-11-01","cited_by_count":52},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45},{"id":"2405.00571","title":"Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval","created":"2024-05-01","cited_by_count":44},{"id":"2502.04263","title":"Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion","created":"2025-02-06","cited_by_count":43},{"id":"2108.01958","title":"Learning Compatible Embeddings","created":"2021-08-04","cited_by_count":37},{"id":"2103.15632","title":"Regular Polytope Networks","created":"2021-03-29","cited_by_count":24},{"id":"2203.01583","title":"Towards Universal Backward-Compatible Representation Learning","created":"2022-03-03","cited_by_count":21},{"id":"2112.02805","title":"Forward Compatible Training for Large-Scale Embedding Retrieval Systems","created":"2021-12-06","cited_by_count":19},{"id":"2602.24012","title":"InfoNCE Induces Gaussian Distribution","created":"2026-02-27","cited_by_count":16},{"id":"2604.18572","title":"Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale","created":"2026-04-20","cited_by_count":16},{"id":"2407.09435","title":"MUSCLE: A Model Update Strategy for Compatible LLM Evolution","created":"2024-07-12","cited_by_count":15},{"id":"2111.07632","title":"CoReS: Compatible Representations via Stationarity","created":"2021-11-15","cited_by_count":14},{"id":"2410.15035","title":"Improving General Text Embedding Model: Tackling Task Conflict and Data Imbalance through Model Merging","created":"2024-10-19","cited_by_count":14},{"id":"2411.18607","title":"Task Arithmetic Through The Lens Of One-Shot Federated Learning","created":"2024-11-27","cited_by_count":12},{"id":"2108.03372","title":"Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation","created":"2021-08-07","cited_by_count":8},{"id":"2211.03989","title":"$BT^2$: Backward-compatible Training with Basis Transformation","created":"2022-11-08","cited_by_count":8},{"id":"2308.11512","title":"L^2R: Lifelong Learning for First-stage Retrieval with Backward-Compatible Representations","created":"2023-08-22","cited_by_count":8},{"id":"2405.02581","title":"Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements","created":"2024-05-04","cited_by_count":8},{"id":"2509.16664","title":"$\\boldsymbol{\\lambda}$-Orthogonality Regularization for Compatible Representation Learning","created":"2025-09-20","cited_by_count":8},{"id":"2009.09590","title":"Generalized Clustering and Multi-Manifold Learning with Geometric Structure Preservation","created":"2020-09-21","cited_by_count":7},{"id":"2303.04766","title":"FastFill: Efficient Compatible Model Update","created":"2023-03-08","cited_by_count":7},{"id":"2211.09032","title":"CL2R: Compatible Lifelong Learning Representations","created":"2022-11-16","cited_by_count":6},{"id":"2301.03767","title":"Metric Compatible Training for Online Backfilling in Large-Scale Retrieval","created":"2023-01-10","cited_by_count":6},{"id":"2210.06954","title":"Darwinian Model Upgrades: Model Evolving with Selective Compatibility","created":"2022-10-13","cited_by_count":5},{"id":"2602.06205","title":"Multi-Way Representation Alignment","created":"2026-02-05","cited_by_count":5},{"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},{"id":"2602.17584","title":"Canonicalizing Multimodal Contrastive Representation Learning","created":"2026-02-19","cited_by_count":4},{"id":"2408.08793","title":"Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer","created":"2024-08-16","cited_by_count":3},{"id":"2511.08322","title":"Mitigating Negative Flips via Margin Preserving Training","created":"2025-11-11","cited_by_count":3},{"id":"2603.19862","title":"IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment","created":"2026-03-20","cited_by_count":3},{"id":"2503.14824","title":"Prototype Perturbation for Relaxing Alignment Constraints in Backward-Compatible Learning","created":"2025-03-19","cited_by_count":2},{"id":"2606.12488","title":"A Stationary (and Therefore Compatible) Representation is All You Need","created":"2026-06-10","cited_by_count":1}],"next_cursor":null}