{"total":132,"rows":[{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715,"area":null},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661,"area":null},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343,"area":null},{"id":"2301.10343","title":"ClimaX: A foundation model for weather and climate","created":"2023-01-24","cited_by_count":337,"area":null},{"id":"2310.00149","title":"One for All: Towards Training One Graph Model for All Classification Tasks","created":"2023-09-29","cited_by_count":243,"area":null},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221,"area":null},{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197,"area":null},{"id":"2207.08799","title":"Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit","created":"2022-07-18","cited_by_count":187,"area":null},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2206.13517","title":"ProGen2: Exploring the Boundaries of Protein Language Models","created":"2022-06-27","cited_by_count":159,"area":null},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"area":null},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144,"area":null},{"id":"2310.09751","title":"UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting","created":"2023-10-15","cited_by_count":144,"area":null},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143,"area":null},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142,"area":null},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131,"area":null},{"id":"2205.14459","title":"CyCLIP: Cyclic Contrastive Language-Image Pretraining","created":"2022-05-28","cited_by_count":127,"area":null},{"id":"2207.04179","title":"Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling","created":"2022-07-09","cited_by_count":127,"area":null},{"id":"2204.07258","title":"Causal Transformer for Estimating Counterfactual Outcomes","created":"2022-04-14","cited_by_count":123,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2106.06047","title":"Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning","created":"2021-06-10","cited_by_count":111,"area":null},{"id":"2203.10833","title":"Hyperbolic Vision Transformers: Combining Improvements in Metric Learning","created":"2022-03-21","cited_by_count":111,"area":null},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2104.08771","title":"Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation","created":"2021-04-18","cited_by_count":74,"area":null},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72,"area":null},{"id":"2411.04986","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","created":"2024-11-07","cited_by_count":69,"area":null},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65,"area":null},{"id":"2202.10629","title":"Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning","created":"2022-02-22","cited_by_count":64,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2402.03182","title":"Empowering Time Series Analysis with Large Language Models: A Survey","created":"2024-02-05","cited_by_count":60,"area":null},{"id":"2402.16132","title":"LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting","created":"2024-02-25","cited_by_count":59,"area":null},{"id":"2210.12530","title":"LMPriors: Pre-Trained Language Models as Task-Specific Priors","created":"2022-10-22","cited_by_count":56,"area":null},{"id":"2202.01338","title":"Regression Transformer: Concurrent sequence regression and generation for molecular language modeling","created":"2022-02-01","cited_by_count":50,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2308.01544","title":"Multimodal Neurons in Pretrained Text-Only Transformers","created":"2023-08-03","cited_by_count":49,"area":null},{"id":"2106.04180","title":"Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models","created":"2021-06-08","cited_by_count":41,"area":null},{"id":"2108.01682","title":"Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation","created":"2021-08-03","cited_by_count":41,"area":null},{"id":"2202.02691","title":"TTS-GAN: A Transformer-based Time-Series Generative Adversarial Network","created":"2022-02-06","cited_by_count":41,"area":null},{"id":"2308.10897","title":"Can Language Models Learn to Listen?","created":"2023-08-21","cited_by_count":40,"area":null},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","cited_by_count":39,"area":null},{"id":"2309.06236","title":"The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models","created":"2023-09-12","cited_by_count":34,"area":null},{"id":"2209.13900","title":"Disentangling Transfer in Continual Reinforcement Learning","created":"2022-09-28","cited_by_count":33,"area":null},{"id":"2401.14192","title":"How Can Large Language Models Understand Spatial-Temporal Data?","created":"2024-01-25","cited_by_count":33,"area":null},{"id":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32,"area":null},{"id":"2207.12661","title":"Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training","created":"2022-07-26","cited_by_count":32,"area":null},{"id":"2203.01311","title":"High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning","created":"2022-03-02","cited_by_count":31,"area":null},{"id":"2111.05498","title":"Attention Approximates Sparse Distributed Memory","created":"2021-11-10","cited_by_count":29,"area":null},{"id":"2302.00902","title":"Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment","created":"2023-02-02","cited_by_count":29,"area":null},{"id":"2203.10326","title":"Pretraining with Artificial Language: Studying Transferable Knowledge in Language Models","created":"2022-03-19","cited_by_count":28,"area":null},{"id":"2305.11598","title":"Introspective Tips: Large Language Model for In-Context Decision Making","created":"2023-05-19","cited_by_count":28,"area":null},{"id":"2306.06688","title":"Language Versatilists vs. Specialists: An Empirical Revisiting on Multilingual Transfer Ability","created":"2023-06-11","cited_by_count":27,"area":null},{"id":"2202.10583","title":"MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned","created":"2022-02-17","cited_by_count":26,"area":null},{"id":"2211.09778","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","created":"2022-11-17","cited_by_count":26,"area":null},{"id":"2403.02221","title":"TPLLM: A Traffic Prediction Framework Based on Pretrained Large Language Models","created":"2024-03-04","cited_by_count":23,"area":null},{"id":"2210.06475","title":"Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models","created":"2022-10-13","cited_by_count":22,"area":null},{"id":"2110.08525","title":"The Power of Prompt Tuning for Low-Resource Semantic Parsing","created":"2021-10-16","cited_by_count":21,"area":null},{"id":"2206.13676","title":"TTS-CGAN: A Transformer Time-Series Conditional GAN for Biosignal Data Augmentation","created":"2022-06-28","cited_by_count":21,"area":null},{"id":"2210.04964","title":"Generating Executable Action Plans with Environmentally-Aware Language Models","created":"2022-10-10","cited_by_count":21,"area":null},{"id":"2209.14389","title":"Downstream Datasets Make Surprisingly Good Pretraining Corpora","created":"2022-09-28","cited_by_count":20,"area":null},{"id":"2107.13530","title":"An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learning","created":"2021-07-26","cited_by_count":19,"area":null},{"id":"2203.13344","title":"Linking Emergent and Natural Languages via Corpus Transfer","created":"2022-03-24","cited_by_count":19,"area":null},{"id":"2205.05535","title":"Clinical Prompt Learning with Frozen Language Models","created":"2022-05-11","cited_by_count":19,"area":null},{"id":"2308.05938","title":"FoodSAM: Any Food Segmentation","created":"2023-08-11","cited_by_count":19,"area":null},{"id":"2204.07554","title":"Efficient Architecture Search for Diverse Tasks","created":"2022-04-15","cited_by_count":18,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","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":"2104.07639","title":"Robust Optimization for Multilingual Translation with Imbalanced Data","created":"2021-04-15","cited_by_count":15,"area":null},{"id":"2203.04911","title":"DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering","created":"2022-03-09","cited_by_count":15,"area":null},{"id":"2109.07348","title":"Cross-lingual Transfer of Monolingual Models","created":"2021-09-15","cited_by_count":14,"area":null},{"id":"2309.13192","title":"Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation","created":"2023-09-22","cited_by_count":12,"area":null},{"id":"2410.07018","title":"Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization","created":"2024-10-09","cited_by_count":12,"area":null},{"id":"2502.19402","title":"General Intelligence Requires Reward-based Pretraining","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2207.12842","title":"Unsupervised Domain Adaptation for Video Transformers in Action Recognition","created":"2022-07-26","cited_by_count":10,"area":null},{"id":"2209.09433","title":"Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings","created":"2022-09-20","cited_by_count":10,"area":null},{"id":"2302.10360","title":"Optical Transformers","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2307.04231","title":"Mx2M: Masked Cross-Modality Modeling in Domain Adaptation for 3D Semantic Segmentation","created":"2023-07-09","cited_by_count":10,"area":null},{"id":"2312.14378","title":"Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification","created":"2023-12-22","cited_by_count":10,"area":null},{"id":"2109.05522","title":"TEASEL: A Transformer-Based Speech-Prefixed Language Model","created":"2021-09-12","cited_by_count":8,"area":null},{"id":"2110.06990","title":"Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers","created":"2021-10-13","cited_by_count":8,"area":null},{"id":"2308.05326","title":"OpenProteinSet: Training data for structural biology at scale","created":"2023-08-10","cited_by_count":8,"area":null},{"id":"2310.17784","title":"Data-Centric Financial Large Language Models","created":"2023-10-07","cited_by_count":8,"area":null},{"id":"2201.02692","title":"Improved Input Reprogramming for GAN Conditioning","created":"2022-01-07","cited_by_count":7,"area":null},{"id":"2205.00222","title":"StorSeismic: A new paradigm in deep learning for seismic processing","created":"2022-04-30","cited_by_count":7,"area":null},{"id":"2301.13338","title":"Continuous Spatiotemporal Transformers","created":"2023-01-31","cited_by_count":7,"area":null},{"id":"2312.04709","title":"How to guess a gradient","created":"2023-12-07","cited_by_count":7,"area":null},{"id":"2405.15813","title":"From CNNs to Transformers in Multimodal Human Action Recognition: A Survey","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2508.04251","title":"T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion","created":"2025-08-06","cited_by_count":7,"area":null},{"id":"2103.14886","title":"Generalization over different cellular automata rules learned by a deep feed-forward neural network","created":"2021-03-27","cited_by_count":6,"area":null},{"id":"2107.12460","title":"Don't Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers","created":"2021-07-26","cited_by_count":6,"area":null},{"id":"2302.08374","title":"Efficiency 360: Efficient Vision Transformers","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2502.17475","title":"ECG-Expert-QA: A Benchmark for Evaluating Medical Large Language Models in Heart Disease Diagnosis","created":"2025-02-16","cited_by_count":6,"area":null},{"id":"2109.01942","title":"On the ability of monolingual models to learn language-agnostic representations","created":"2021-09-04","cited_by_count":5,"area":null},{"id":"2109.15101","title":"Compositional generalization in semantic parsing with pretrained transformers","created":"2021-09-30","cited_by_count":5,"area":null},{"id":"2308.11464","title":"Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning","created":"2023-08-22","cited_by_count":5,"area":null},{"id":"2211.05044","title":"What is Wrong with Language Models that Can Not Tell a Story?","created":"2022-11-09","cited_by_count":4,"area":null},{"id":"2305.14243","title":"Training Transitive and Commutative Multimodal Transformers with LoReTTa","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2603.08707","title":"Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting","created":"2026-03-09","cited_by_count":4,"area":null}],"next_cursor":"100"}