{"total":116,"rows":[{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238,"area":null},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237,"area":null},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203,"area":null},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"area":null},{"id":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147,"area":null},{"id":"2205.00541","title":"COUCH: Towards Controllable Human-Chair Interactions","created":"2022-05-01","cited_by_count":135,"area":null},{"id":"2302.00883","title":"Synthesizing Physical Character-Scene Interactions","created":"2023-02-02","cited_by_count":104,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2107.11317","title":"Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives","created":"2021-07-23","cited_by_count":50,"area":null},{"id":"2312.08985","title":"OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers","created":"2023-12-14","cited_by_count":47,"area":null},{"id":"2405.00467","title":"Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing","created":"2024-05-01","cited_by_count":46,"area":null},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2407.10834","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","created":"2024-07-15","cited_by_count":41,"area":null},{"id":"2105.08489","title":"Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising","created":"2021-05-18","cited_by_count":39,"area":null},{"id":"2403.07508","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","created":"2024-03-12","cited_by_count":36,"area":null},{"id":"2106.15434","title":"Zoo-Tuning: Adaptive Transfer from a Zoo of Models","created":"2021-06-29","cited_by_count":35,"area":null},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"id":"2302.13750","title":"MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition","created":"2023-02-27","cited_by_count":31,"area":null},{"id":"2203.12856","title":"Beyond Fixation: Dynamic Window Visual Transformer","created":"2022-03-24","cited_by_count":28,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2404.16030","title":"MoDE: CLIP Data Experts via Clustering","created":"2024-04-24","cited_by_count":22,"area":null},{"id":"2311.09580","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","created":"2023-11-16","cited_by_count":21,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2106.09563","title":"On Anytime Learning at Macroscale","created":"2021-06-17","cited_by_count":20,"area":null},{"id":"2307.02321","title":"MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers","created":"2023-07-05","cited_by_count":20,"area":null},{"id":"2110.03360","title":"Sparse MoEs meet Efficient Ensembles","created":"2021-10-07","cited_by_count":19,"area":null},{"id":"2208.02894","title":"Redesigning Multi-Scale Neural Network for Crowd Counting","created":"2022-08-04","cited_by_count":17,"area":null},{"id":"2103.15622","title":"Graph Classification by Mixture of Diverse Experts","created":"2021-03-29","cited_by_count":16,"area":null},{"id":"2306.03445","title":"MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition","created":"2023-06-06","cited_by_count":15,"area":null},{"id":"2410.02200","title":"Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts","created":"2024-10-03","cited_by_count":15,"area":null},{"id":"2302.02609","title":"Improving Domain Generalization with Domain Relations","created":"2023-02-06","cited_by_count":14,"area":null},{"id":"2203.07413","title":"Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learning","created":"2022-03-14","cited_by_count":11,"area":null},{"id":"2208.09432","title":"Federated Select: A Primitive for Communication- and Memory-Efficient Federated Learning","created":"2022-08-19","cited_by_count":11,"area":null},{"id":"2310.11031","title":"Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters","created":"2023-10-17","cited_by_count":11,"area":null},{"id":"2405.20237","title":"Training-efficient density quantum machine learning","created":"2024-05-30","cited_by_count":11,"area":null},{"id":"2410.13006","title":"LLM Chain Ensembles for Scalable and Accurate Data Annotation","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2112.02624","title":"Dynamic Token Normalization Improves Vision Transformers","created":"2021-12-05","cited_by_count":10,"area":null},{"id":"2210.13005","title":"Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2311.01075","title":"Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2403.10616","title":"DiPaCo: Distributed Path Composition","created":"2024-03-15","cited_by_count":10,"area":null},{"id":"2407.09946","title":"Low-Rank Interconnected Adaptation across Layers","created":"2024-07-13","cited_by_count":10,"area":null},{"id":"2508.05038","title":"HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID","created":"2025-08-07","cited_by_count":10,"area":null},{"id":"2408.02306","title":"Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization","created":"2024-08-05","cited_by_count":7,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2412.18177","title":"Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2102.08688","title":"Switch Spaces: Learning Product Spaces with Sparse Gating","created":"2021-02-17","cited_by_count":6,"area":null},{"id":"2203.05028","title":"Dynamic Instance Domain Adaptation","created":"2022-03-09","cited_by_count":6,"area":null},{"id":"2407.13511","title":"Can Open-Source LLMs Compete with Commercial Models? Exploring the Few-Shot Performance of Current GPT Models in Biomedical Tasks","created":"2024-07-18","cited_by_count":6,"area":null},{"id":"2108.06167","title":"Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback","created":"2021-08-13","cited_by_count":5,"area":null},{"id":"2206.03726","title":"Hub-Pathway: Transfer Learning from A Hub of Pre-trained Models","created":"2022-06-08","cited_by_count":5,"area":null},{"id":"2308.08915","title":"Beyond Sharing: Conflict-Aware Multivariate Time Series Anomaly Detection","created":"2023-08-17","cited_by_count":5,"area":null},{"id":"2403.10568","title":"MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion","created":"2024-03-14","cited_by_count":5,"area":null},{"id":"2406.04914","title":"Submodular Framework for Structured-Sparse Optimal Transport","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2408.12803","title":"Multi-Treatment Multi-Task Uplift Modeling for Enhancing User Growth","created":"2024-08-23","cited_by_count":5,"area":null},{"id":"2504.05342","title":"MASS: MoErging through Adaptive Subspace Selection","created":"2025-04-06","cited_by_count":5,"area":null},{"id":"2504.15380","title":"Plug-and-Play Versatile Compressed Video Enhancement","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2601.04715","title":"On the Holistic Approach for Detecting Human Image Forgery","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2308.16567","title":"ScrollNet: Dynamic Weight Importance for Continual Learning","created":"2023-08-31","cited_by_count":4,"area":null},{"id":"2503.01470","title":"Position: Ensuring mutual privacy is necessary for effective external evaluation of proprietary AI systems","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2603.22198","title":"Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learning","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2303.11247","title":"Memorization Capacity of Neural Networks with Conditional Computation","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2310.01154","title":"Modularity in Deep Learning: A Survey","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2501.18596","title":"DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2502.02818","title":"TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardware","created":"2025-02-05","cited_by_count":3,"area":null},{"id":"2510.15595","title":"FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2512.00384","title":"Efficient and Programmable Exploration of Synthesizable Chemical Space","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2211.15544","title":"Automatically Extracting Information in Medical Dialogue: Expert System And Attention for Labelling","created":"2022-11-28","cited_by_count":2,"area":null},{"id":"2312.03292","title":"Enhancing Molecular Property Prediction via Mixture of Collaborative Experts","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2405.20684","title":"Joint Embeddings for Graph Instruction Tuning","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2410.10267","title":"big.LITTLE Vision Transformer for Efficient Visual Recognition","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2505.22360","title":"Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2510.04331","title":"DoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks","created":"2025-10-05","cited_by_count":2,"area":null},{"id":"2602.23113","title":"Learning Physical Operators using Neural Operators","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2105.06679","title":"Dynamic Multi-Branch Layers for On-Device Neural Machine Translation","created":"2021-05-14","cited_by_count":1,"area":null},{"id":"2108.04658","title":"U-Net-and-a-half: Convolutional network for biomedical image segmentation using multiple expert-driven annotations","created":"2021-08-10","cited_by_count":1,"area":null},{"id":"2112.13747","title":"MOEF: Modeling Occasion Evolution in Frequency Domain for Promotion-Aware Click-Through Rate Prediction","created":"2021-12-27","cited_by_count":1,"area":null},{"id":"2210.15056","title":"UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification","created":"2022-10-26","cited_by_count":1,"area":null},{"id":"2302.11078","title":"Learning Mixture Structure on Multi-Source Time Series for Probabilistic Forecasting","created":"2023-02-22","cited_by_count":1,"area":null},{"id":"2303.08028","title":"EdgeServe: A Streaming System for Decentralized Model Serving","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2406.01825","title":"Reliable OOD Virtual Screening with Extrapolatory Pseudo-Label Matching","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2501.00317","title":"Spatio-Temporal Multi-Subgraph GCN for 3D Human Motion Prediction","created":"2024-12-31","cited_by_count":1,"area":null},{"id":"2508.21394","title":"AI Compute Architecture and Evolution Trends","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2509.07704","title":"SEEC: Segmentation-Assisted Multi-Entropy Models for Learned Lossless Image Compression","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2107.02450","title":"End-To-End Data-Dependent Routing in Multi-Path Neural Networks","created":"2021-07-06","cited_by_count":0,"area":null},{"id":"2202.11877","title":"A Unified Framework for Campaign Performance Forecasting in Online Display Advertising","created":"2022-02-24","cited_by_count":0,"area":null},{"id":"2204.05101","title":"On the Adaptation to Concept Drift for CTR Prediction","created":"2022-04-01","cited_by_count":0,"area":null},{"id":"2211.05488","title":"ClassPruning: Speed Up Image Restoration Networks by Dynamic N:M Pruning","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2211.06163","title":"Dual Complementary Dynamic Convolution for Image Recognition","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2307.15858","title":"Multi-output Headed Ensembles for Product Item Classification","created":"2023-07-29","cited_by_count":0,"area":null},{"id":"2309.17048","title":"On Continuity of Robust and Accurate Classifiers","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2312.03734","title":"Conditional Prompt Tuning for Multimodal Fusion","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2404.08887","title":"Countering Mainstream Bias via End-to-End Adaptive Local Learning","created":"2024-04-13","cited_by_count":0,"area":null},{"id":"2406.11886","title":"Financial Assets Dependency Prediction Utilizing Spatiotemporal Patterns","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2407.08341","title":"Adaptive Deep Iris Feature Extractor at Arbitrary Resolutions","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2410.04833","title":"Multimodal Fusion Strategies for Mapping Biophysical Landscape Features","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2411.18254","title":"Active partitioning: inverting the paradigm of active learning","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2412.05126","title":"Skewed Neuronal Heterogeneity Enhances Efficiency On Various Computing Systems","created":"2024-12-06","cited_by_count":0,"area":null},{"id":"2412.14328","title":"Semantic Role Labeling of NomBank Partitives","created":"2024-12-18","cited_by_count":0,"area":null}],"next_cursor":"100"}