{"total":89,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396,"area":null},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668,"area":null},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411,"area":null},{"id":"2302.10724","title":"ChatGPT: Jack of all trades, master of none","created":"2023-02-21","cited_by_count":204,"area":null},{"id":"2210.12353","title":"Leveraging Large Language Models for Multiple Choice Question Answering","created":"2022-10-22","cited_by_count":203,"area":null},{"id":"2303.16854","title":"AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators","created":"2023-03-29","cited_by_count":172,"area":null},{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2303.09752","title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","created":"2023-03-17","cited_by_count":84,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57,"area":null},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2212.09811","title":"Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model","created":"2022-12-19","cited_by_count":36,"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":"2404.15381","title":"Advances and Open Challenges in Federated Foundation Models","created":"2024-04-23","cited_by_count":36,"area":null},{"id":"2503.09543","title":"PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs","created":"2025-03-12","cited_by_count":35,"area":null},{"id":"2405.00361","title":"AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts","created":"2024-05-01","cited_by_count":34,"area":null},{"id":"2306.16793","title":"Benchmarking Large Language Model Capabilities for Conditional Generation","created":"2023-06-29","cited_by_count":29,"area":null},{"id":"2507.13812","title":"SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing","created":"2025-07-18","cited_by_count":26,"area":null},{"id":"2301.10936","title":"PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation","created":"2023-01-26","cited_by_count":25,"area":null},{"id":"2212.01853","title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","created":"2022-12-04","cited_by_count":24,"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":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2411.02335","title":"Sparsing Law: Towards Large Language Models with Greater Activation Sparsity","created":"2024-11-04","cited_by_count":22,"area":null},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2501.02086","title":"Instruction-Following Pruning for Large Language Models","created":"2025-01-03","cited_by_count":17,"area":null},{"id":"2405.09592","title":"A Survey of Generative Techniques for Spatial-Temporal Data Mining","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2406.12311","title":"Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2502.19227","title":"Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systems","created":"2025-02-26","cited_by_count":14,"area":null},{"id":"2505.23811","title":"LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions","created":"2025-05-27","cited_by_count":12,"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":"2302.10360","title":"Optical Transformers","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2312.02520","title":"Towards More Unified In-context Visual Understanding","created":"2023-12-05","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":"2408.09856","title":"TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition","created":"2024-08-19","cited_by_count":10,"area":null},{"id":"2505.06892","title":"Learning Soft Sparse Shapes for Efficient Time-Series Classification","created":"2025-05-11","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":"2508.19609","title":"FinCast: A Foundation Model for Financial Time-Series Forecasting","created":"2025-08-27","cited_by_count":10,"area":null},{"id":"2407.09111","title":"Inference Optimization of Foundation Models on AI Accelerators","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2502.04700","title":"EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference","created":"2025-02-07","cited_by_count":9,"area":null},{"id":"2508.04153","title":"ICM-Fusion: In-Context Meta-Optimized LoRA Fusion for Multi-Task Adaptation","created":"2025-08-06","cited_by_count":9,"area":null},{"id":"2212.04257","title":"Momentum Calibration for Text Generation","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2403.08281","title":"Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models","created":"2024-03-13","cited_by_count":7,"area":null},{"id":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","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":"2412.20875","title":"Attention Is All You Need For Mixture-of-Depths Routing","created":"2024-12-30","cited_by_count":7,"area":null},{"id":"2507.09937","title":"Memorization Sinks: Isolating Memorization during LLM Training","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2405.18897","title":"MLAE: Masked LoRA Experts for Visual Parameter-Efficient Fine-Tuning","created":"2024-05-29","cited_by_count":6,"area":null},{"id":"2409.13931","title":"On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists","created":"2024-09-20","cited_by_count":6,"area":null},{"id":"2504.14519","title":"SlimPipe: Memory-Thrifty and Efficient Pipeline Parallelism for Long-Context LLM Training","created":"2025-04-20","cited_by_count":6,"area":null},{"id":"2502.12325","title":"From Dense to Dynamic: Token-Difficulty Driven MoEfication of Pre-Trained LLMs","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2410.03553","title":"Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2506.11389","title":"Curriculum-Guided Layer Scaling for Language Model Pretraining","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2506.20752","title":"Characterization and Mitigation of Training Instabilities in Microscaling Formats","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2603.15389","title":"When Does Sparsity Mitigate the Curse of Depth in LLMs","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2311.06647","title":"Robust Text Classification: Analyzing Prototype-Based Networks","created":"2023-11-11","cited_by_count":3,"area":null},{"id":"2405.09596","title":"Enhancing Maritime Trajectory Forecasting via H3 Index and Causal Language Modelling (CLM)","created":"2024-05-15","cited_by_count":3,"area":null},{"id":"2506.18923","title":"Mix-of-Language-Experts Architecture for Multilingual Programming","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2509.19230","title":"DevFD: Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces","created":"2025-09-23","cited_by_count":3,"area":null},{"id":"2405.17139","title":"Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2412.02735","title":"CPP-UT-Bench: Can LLMs Write Complex Unit Tests in C++?","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2507.21567","title":"RelMap: Enhancing Online Map Construction with Class-Aware Spatial Relation and Semantic Priors","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2512.16134","title":"Staggered Batch Scheduling: Co-optimizing Time-to-First-Token and Throughput for High-Efficiency LLM Inference","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2602.02400","title":"An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.10526","title":"Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosis","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2312.14400","title":"Unveiling Backbone Effects in CLIP: Exploring Representational Synergies and Variances","created":"2023-12-22","cited_by_count":1,"area":null},{"id":"2505.23844","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2508.13482","title":"Cross-Cancer Knowledge Transfer in WSI-based Prognosis Prediction","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2601.00847","title":"You Only Need Your Transformer 25% of the Time: Meaning-First Execution for Eliminating Unnecessary Inference","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2606.05957","title":"Dead Directions: Geometric Singular Learning","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.20911","title":"Latent Personal Memory: Represent personal memory as dynamic soft prompts","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2305.03232","title":"Neuromodulation Gated Transformer","created":"2023-05-05","cited_by_count":0,"area":null},{"id":"2408.09752","title":"A Unified Framework for Iris Anti-Spoofing: Introducing Iris Anti-Spoofing Cross-Domain-Testing Protocol and Masked-MoE Method","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2602.05026","title":"Laws of Learning Dynamics and the Core of Learners","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.16247","title":"Joint-Centric Dual Contrastive Alignment with Structure-Preserving and Information-Balanced Regularization","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.17228","title":"Revisiting Auxiliary Losses for Conditional Depth Routing: An Empirical Study","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.06240","title":"Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.28961","title":"Dynamics of Stochastic Momentum with Sparse Updates in High Dimensions","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.04888","title":"HD-DinoMoE: A Class-Aware Hierarchical Dual Mixture-of-Experts Network for Scleral Anomaly Segmentation in Complex Acquisition Scenarios","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.31397","title":"Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.27286","title":"MM-Spectrum: Multimodal Multi-spectral Molecular Structural Elucidation with a Stable MoE Framework","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.03880","title":"Xiaomi-TabLDM: A Tabular Foundation Model Technical Report","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.32141","title":"REALM: Regime-Switching, Explainable, and Activation-Induced Linear Models","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36193","title":"Physical Cross-Modal Masked Autoencoding for Seismic-to-Well Representation Learning","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}