{"total":103,"rows":[{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807,"area":"lr"},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"area":null},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744,"area":null},{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457,"area":null},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182,"area":null},{"id":"2401.00448","title":"Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws","created":"2023-12-31","cited_by_count":159,"area":null},{"id":"2402.14848","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","created":"2024-02-19","cited_by_count":152,"area":"lr"},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"area":null},{"id":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","cited_by_count":118,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2403.15796","title":"Understanding Emergent Abilities of Language Models from the Loss Perspective","created":"2024-03-23","cited_by_count":94,"area":null},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"area":null},{"id":"2212.09803","title":"Training Trajectories of Language Models Across Scales","created":"2022-12-19","cited_by_count":81,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2208.00748","title":"Efficient Long-Text Understanding with Short-Text Models","created":"2022-08-01","cited_by_count":71,"area":null},{"id":"2210.12843","title":"Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification","created":"2022-10-23","cited_by_count":65,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2405.16039","title":"MoEUT: Mixture-of-Experts Universal Transformers","created":"2024-05-25","cited_by_count":59,"area":"moe"},{"id":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57,"area":null},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2405.14591","title":"Base of RoPE Bounds Context Length","created":"2024-05-23","cited_by_count":52,"area":null},{"id":"2410.23179","title":"Does equivariance matter at scale?","created":"2024-10-30","cited_by_count":52,"area":null},{"id":"2306.17759","title":"The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit","created":"2023-06-30","cited_by_count":47,"area":null},{"id":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","created":"2024-04-12","cited_by_count":46,"area":null},{"id":"2208.04347","title":"Investigating Efficiently Extending Transformers for Long Input Summarization","created":"2022-08-08","cited_by_count":43,"area":null},{"id":"2502.17578","title":"How Do Large Language Monkeys Get Their Power (Laws)?","created":"2025-02-24","cited_by_count":43,"area":"safety"},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2411.05735","title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2310.07096","title":"Sparse Universal Transformer","created":"2023-10-11","cited_by_count":32,"area":"moe"},{"id":"2403.05812","title":"Algorithmic progress in language models","created":"2024-03-09","cited_by_count":31,"area":null},{"id":"2404.10308","title":"Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs","created":"2024-04-16","cited_by_count":30,"area":null},{"id":"2208.12852","title":"What Do NLP Researchers Believe? Results of the NLP Community Metasurvey","created":"2022-08-26","cited_by_count":28,"area":null},{"id":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"area":null},{"id":"2311.16789","title":"A Survey of the Evolution of Language Model-Based Dialogue Systems: Data, Task and Models","created":"2023-11-28","cited_by_count":23,"area":null},{"id":"2301.13195","title":"Adaptive Computation with Elastic Input Sequence","created":"2023-01-30","cited_by_count":22,"area":null},{"id":"2404.09173","title":"TransformerFAM: Feedback attention is working memory","created":"2024-04-14","cited_by_count":22,"area":null},{"id":"2502.07827","title":"Implicit Language Models are RNNs: Balancing Parallelization and Expressivity","created":"2025-02-10","cited_by_count":22,"area":"lr"},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22,"area":null},{"id":"2209.10052","title":"Adapting Pretrained Text-to-Text Models for Long Text Sequences","created":"2022-09-21","cited_by_count":21,"area":null},{"id":"2212.06121","title":"In Defense of Cross-Encoders for Zero-Shot Retrieval","created":"2022-12-12","cited_by_count":21,"area":null},{"id":"2309.01172","title":"FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs","created":"2023-09-03","cited_by_count":20,"area":null},{"id":"2409.04267","title":"An overview of domain-specific foundation model: key technologies, applications and challenges","created":"2024-09-06","cited_by_count":19,"area":null},{"id":"2404.03134","title":"Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?","created":"2024-04-04","cited_by_count":17,"area":"lr"},{"id":"2407.02118","title":"Breaking Language Barriers: Cross-Lingual Continual Pre-Training at Scale","created":"2024-07-02","cited_by_count":15,"area":null},{"id":"2210.05043","title":"Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling","created":"2022-10-10","cited_by_count":14,"area":null},{"id":"2305.19370","title":"Blockwise Parallel Transformer for Large Context Models","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2311.15156","title":"xTrimoGene: An Efficient and Scalable Representation Learner for Single-Cell RNA-Seq Data","created":"2023-11-26","cited_by_count":12,"area":null},{"id":"2302.06117","title":"The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2406.14508","title":"Evidence of a log scaling law for political persuasion with large language models","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2411.07474","title":"Controlled Evaluation of Syntactic Knowledge in Multilingual Language Models","created":"2024-11-12","cited_by_count":10,"area":null},{"id":"2411.16035","title":"Predicting Emergent Capabilities by Finetuning","created":"2024-11-25","cited_by_count":10,"area":null},{"id":"2502.07503","title":"Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2301.12525","title":"Composer's Assistant: An Interactive Transformer for Multi-Track MIDI Infilling","created":"2023-01-29","cited_by_count":9,"area":null},{"id":"2308.13191","title":"Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers","created":"2023-08-25","cited_by_count":9,"area":null},{"id":"2411.13055","title":"Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2506.04598","title":"Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets","created":"2025-06-05","cited_by_count":8,"area":null},{"id":"2510.00537","title":"Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2605.20670","title":"LT2: Linear-Time Looped Transformers","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2209.14969","title":"Transfer Learning with Pretrained Remote Sensing Transformers","created":"2022-09-28","cited_by_count":6,"area":null},{"id":"2511.21622","title":"On the Origin of Algorithmic Progress in AI","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2601.03764","title":"Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model","created":"2026-01-07","cited_by_count":6,"area":null},{"id":"2402.00976","title":"Investigating Recurrent Transformers with Dynamic Halt","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2407.21058","title":"Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT","created":"2024-07-25","cited_by_count":5,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2311.03233","title":"Navigating Scaling Laws: Compute Optimality in Adaptive Model Training","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2404.18933","title":"Learning Low-Rank Feature for Thorax Disease Classification","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2407.01601","title":"Unveiling and Controlling Anomalous Attention Distribution in Transformers","created":"2024-06-26","cited_by_count":4,"area":null},{"id":"2505.20132","title":"Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks","created":"2025-05-26","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":"2606.24998","title":"Internal Data Repetition Destroys Language Models","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2208.13197","title":"IDP-PGFE: An Interpretable Disruption Predictor based on Physics-Guided Feature Extraction","created":"2022-08-28","cited_by_count":3,"area":null},{"id":"2311.08487","title":"Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective","created":"2023-11-14","cited_by_count":3,"area":"alignment"},{"id":"2408.15244","title":"Misrepresented Technological Solutions in Imagined Futures: The Origins and Dangers of AI Hype in the Research Community","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2504.13219","title":"Scaling Laws for Data-Efficient Visual Transfer Learning","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2306.06852","title":"Rethink DARTS Search Space and Renovate a New Benchmark","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2402.17008","title":"Benchmarking LLMs on the Semantic Overlap Summarization Task","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2410.12025","title":"Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2607.17624","title":"Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2207.12547","title":"The BUTTER Zone: An Empirical Study of Training Dynamics in Fully Connected Neural Networks","created":"2022-07-25","cited_by_count":1,"area":null},{"id":"2308.12420","title":"Evolution of ESG-focused DLT Research: An NLP Analysis of the Literature","created":"2023-08-23","cited_by_count":1,"area":null},{"id":"2309.10563","title":"A Hierarchical Neural Framework for Classification and its Explanation in Large Unstructured Legal Documents","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2310.10102","title":"KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2403.02436","title":"How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers","created":"2024-03-04","cited_by_count":1,"area":"moe"},{"id":"2410.11444","title":"A Theoretical Survey on Foundation Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2411.01030","title":"Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2506.08978","title":"Propositional Logic for Probing Generalization in Neural Networks","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2509.12679","title":"Large Language Model Scaling Laws for Neural Quantum States in Quantum Chemistry","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2603.16985","title":"Integrating Inductive Biases in Transformers via Distillation for Financial Time Series Forecasting","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2605.17276","title":"How Do Electrocardiogram Models Scale?","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2310.02044","title":"How Physics and Background Attributes Impact Video Transformers in Robotic Manipulation: A Case Study on Planar Pushing","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2509.00509","title":"Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation","created":"2025-08-30","cited_by_count":0,"area":null},{"id":"2608.09703","title":"Matryoshka Language Model Suites","created":"2026-08-10","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}