{"total":40,"rows":[{"id":"2307.03917","title":"On decoder-only architecture for speech-to-text and large language model integration","created":"2023-07-08","cited_by_count":145,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2401.07333","title":"ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering","created":"2024-01-14","cited_by_count":50,"area":null},{"id":"2412.02975","title":"Theoretical limitations of multi-layer Transformer","created":"2024-12-04","cited_by_count":45,"area":null},{"id":"2305.13225","title":"Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance","created":"2023-05-22","cited_by_count":33,"area":null},{"id":"2401.13912","title":"A Survey of Deep Learning and Foundation Models for Time Series Forecasting","created":"2024-01-25","cited_by_count":33,"area":null},{"id":"2309.08573","title":"Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models","created":"2023-09-15","cited_by_count":18,"area":null},{"id":"2512.14856","title":"T5Gemma 2: Seeing, Reading, and Understanding Longer","created":"2025-12-16","cited_by_count":17,"area":null},{"id":"2310.18208","title":"ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models","created":"2023-10-27","cited_by_count":15,"area":null},{"id":"2407.05388","title":"Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis","created":"2024-07-07","cited_by_count":12,"area":null},{"id":"2406.03878","title":"Decoder-only Streaming Transformer for Simultaneous Translation","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2312.03248","title":"Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning","created":"2023-12-06","cited_by_count":8,"area":null},{"id":"2505.13499","title":"Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency","created":"2025-05-16","cited_by_count":8,"area":null},{"id":"2309.10706","title":"OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch","created":"2023-09-19","cited_by_count":7,"area":null},{"id":"2403.04080","title":"Transformers and Language Models in Form Understanding: A Comprehensive Review of Scanned Document Analysis","created":"2024-03-06","cited_by_count":6,"area":null},{"id":"2402.00350","title":"On the Challenges of Fuzzing Techniques via Large Language Models","created":"2024-02-01","cited_by_count":4,"area":null},{"id":"2406.15752","title":"TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers","created":"2024-06-22","cited_by_count":4,"area":null},{"id":"2408.09777","title":"Summarizing long regulatory documents with a multi-step pipeline","created":"2024-08-19","cited_by_count":4,"area":null},{"id":"2409.15051","title":"Scaling Laws of Decoder-Only Models on the Multilingual Machine Translation Task","created":"2024-09-23","cited_by_count":4,"area":null},{"id":"2510.26622","title":"Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2311.12820","title":"MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation","created":"2023-09-26","cited_by_count":3,"area":null},{"id":"2410.20856","title":"Strada-LLM: Graph LLM for traffic prediction","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2507.13318","title":"HapticCap: A Multimodal Dataset and Task for Understanding User Experience of Vibration Haptic Signals","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2311.02205","title":"An Introduction to Natural Language Processing Techniques and Framework for Clinical Implementation in Radiation Oncology","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2312.02125","title":"TPPoet: Transformer-Based Persian Poem Generation using Minimal Data and Advanced Decoding Techniques","created":"2023-12-04","cited_by_count":2,"area":null},{"id":"2403.13112","title":"Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2406.09140","title":"Investigating the translation capabilities of Large Language Models trained on parallel data only","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2407.08978","title":"Towards Chapter-to-Chapter Context-Aware Literary Translation via Large Language Models","created":"2024-07-12","cited_by_count":2,"area":null},{"id":"2411.03287","title":"The Future of Intelligent Healthcare: A Systematic Analysis and Discussion on the Integration and Impact of Robots Using Large Language Models for Healthcare","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2311.02333","title":"Understanding the Natural Language of DNA using Encoder-Decoder Foundation Models with Byte-level Precision","created":"2023-11-04","cited_by_count":1,"area":null},{"id":"2501.03038","title":"Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2503.21613","title":"Evaluating book summaries from internal knowledge in Large Language Models: a cross-model and semantic consistency approach","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2309.08347","title":"Reward Engineering for Generating Semi-structured Explanation","created":"2023-09-15","cited_by_count":0,"area":null},{"id":"2410.12601","title":"CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2504.00339","title":"VNJPTranslate: A comprehensive pipeline for Vietnamese-Japanese translation","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2507.13043","title":"The Power of Architecture: Deep Dive into Transformer Architectures for Long-Term Time Series Forecasting","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2510.10179","title":"LLMs are All You Need? Improving Fuzz Testing for MOJO with Large Language Models","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2601.07930","title":"Transformer-Based Approach for Automated Functional Group Replacement in Chemical Compounds","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.10926","title":"Selecting Language Models for Social Science: Start Small, Start Open, and Validate","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2606.14960","title":"Leveraging Physiological Signals to Predict Exam Outcomes with Machine Learning","created":"2026-06-12","cited_by_count":0,"area":null}],"next_cursor":null}