{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"2308.12032","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","created":"2023-08-23","cited_by_count":307},{"id":"2205.12615","title":"Autoformalization with Large Language Models","created":"2022-05-25","cited_by_count":263},{"id":"1809.02176","title":"Multi-Adversarial Domain Adaptation","created":"2018-09-04","cited_by_count":196},{"id":"2505.17685","title":"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving","created":"2025-05-23","cited_by_count":166},{"id":"2309.14616","title":"NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space","created":"2023-09-26","cited_by_count":90},{"id":"2509.22548","title":"JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation","created":"2025-09-26","cited_by_count":89},{"id":"2409.03444","title":"Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities","created":"2024-09-05","cited_by_count":69},{"id":"2309.13567","title":"MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models","created":"2023-09-24","cited_by_count":63},{"id":"2307.06290","title":"Instruction Mining: Instruction Data Selection for Tuning Large Language Models","created":"2023-07-12","cited_by_count":58},{"id":"2402.05932","title":"Driving Everywhere with Large Language Model Policy Adaptation","created":"2024-02-08","cited_by_count":53},{"id":"2403.07384","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","created":"2024-03-12","cited_by_count":44},{"id":"2402.15061","title":"Fine-tuning Large Language Models for Domain-specific Machine Translation","created":"2024-02-23","cited_by_count":43},{"id":"2412.01615","title":"OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking","created":"2024-12-02","cited_by_count":35},{"id":"2404.18465","title":"M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework","created":"2024-04-29","cited_by_count":32},{"id":"2505.12079","title":"SepPrune: Structured Pruning for Efficient Deep Speech Separation","created":"2025-05-17","cited_by_count":31},{"id":"2402.05140","title":"Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains","created":"2024-02-06","cited_by_count":30},{"id":"2407.15051","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","created":"2024-07-21","cited_by_count":30},{"id":"2410.10877","title":"Improving Data Efficiency via Curating LLM-Driven Rating Systems","created":"2024-10-09","cited_by_count":29},{"id":"2505.18581","title":"Removal of Hallucination on Hallucination: Debate-Augmented RAG","created":"2025-05-24","cited_by_count":29},{"id":"2111.12485","title":"Understanding the Dynamics of DNNs Using Graph Modularity","created":"2021-11-24","cited_by_count":26},{"id":"2403.19443","title":"Mixed Preference Optimization: Reinforcement Learning with Data Selection and Better Reference Model","created":"2024-03-28","cited_by_count":25},{"id":"2410.05578","title":"Swift Sampler: Efficient Learning of Sampler by 10 Parameters","created":"2024-10-08","cited_by_count":25},{"id":"2509.10377","title":"Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs","created":"2025-09-12","cited_by_count":25},{"id":"2305.01146","title":"RadAdapt: Radiology Report Summarization via Lightweight Domain Adaptation of Large Language Models","created":"2023-05-02","cited_by_count":24},{"id":"2302.08269","title":"SyreaNet: A Physically Guided Underwater Image Enhancement Framework Integrating Synthetic and Real Images","created":"2023-02-16","cited_by_count":23},{"id":"2310.08910","title":"Scalarization for Multi-Task and Multi-Domain Learning at Scale","created":"2023-10-13","cited_by_count":19},{"id":"2406.07929","title":"A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models","created":"2024-06-12","cited_by_count":18},{"id":"2409.03320","title":"YOLO-PPA based Efficient Traffic Sign Detection for Cruise Control in Autonomous Driving","created":"2024-09-05","cited_by_count":16},{"id":"2503.17551","title":"Audio-Enhanced Vision-Language Modeling with Latent Space Broadening for High Quality Data Expansion","created":"2025-03-21","cited_by_count":15},{"id":"2509.00039","title":"AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models","created":"2025-08-23","cited_by_count":14},{"id":"2509.20251","title":"4D Driving Scene Generation With Stereo Forcing","created":"2025-09-24","cited_by_count":8},{"id":"2509.23316","title":"C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection","created":"2025-09-27","cited_by_count":5},{"id":"2510.16677","title":"Renaissance of RNNs in Streaming Clinical Time Series: Compact Recurrence Remains Competitive with Transformers","created":"2025-10-19","cited_by_count":5},{"id":"2510.17520","title":"Curiosity Meets Cooperation: A Game-Theoretic Approach to Long-Tail Multi-Label Learning","created":"2025-10-20","cited_by_count":4},{"id":"2507.19742","title":"DOA: A Degeneracy Optimization Agent with Adaptive Pose Compensation Capability based on Deep Reinforcement Learning","created":"2025-07-26","cited_by_count":3},{"id":"2510.10025","title":"Lightweight Baselines for Medical Abstract Classification: DistilBERT with Cross-Entropy as a Strong Default","created":"2025-10-11","cited_by_count":3},{"id":"2412.17942","title":"Contrato360 2.0: A Document and Database-Driven Question-Answer System using Large Language Models and Agents","created":"2024-12-23","cited_by_count":1}],"next_cursor":null}