{"list":"other","total":87,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559},{"id":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"2205.05198","title":"Reducing Activation Recomputation in Large Transformer Models","created":"2022-05-10","cited_by_count":302},{"id":"2504.21801","title":"DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition","created":"2025-04-30","cited_by_count":287},{"id":"2502.12067","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","created":"2025-02-17","cited_by_count":249},{"id":"1707.04585","title":"The Reversible Residual Network: Backpropagation Without Storing Activations","created":"2017-07-14","cited_by_count":217},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214},{"id":"2310.06201","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","created":"2023-10-09","cited_by_count":189},{"id":"2110.07577","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","created":"2021-10-14","cited_by_count":162},{"id":"2004.02105","title":"Unsupervised Domain Clusters in Pretrained Language Models","created":"2020-04-05","cited_by_count":160},{"id":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150},{"id":"2309.05444","title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","created":"2023-09-11","cited_by_count":150},{"id":"2109.05687","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","created":"2021-09-13","cited_by_count":146},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141},{"id":"2210.17451","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-10-31","cited_by_count":137},{"id":"2308.03303","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","created":"2023-08-07","cited_by_count":137},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135},{"id":"2404.11999","title":"Token-level Direct Preference Optimization","created":"2024-04-18","cited_by_count":135},{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114},{"id":"1910.02653","title":"Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization","created":"2019-10-07","cited_by_count":91},{"id":"2411.19943","title":"Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability","created":"2024-11-29","cited_by_count":83},{"id":"2304.08442","title":"The MiniPile Challenge for Data-Efficient Language Models","created":"2023-04-17","cited_by_count":75},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70},{"id":"2305.16742","title":"Parameter-Efficient Fine-Tuning without Introducing New Latency","created":"2023-05-26","cited_by_count":59},{"id":"1906.03728","title":"The Generalization-Stability Tradeoff In Neural Network Pruning","created":"2019-06-09","cited_by_count":54},{"id":"2506.02867","title":"Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning","created":"2025-06-03","cited_by_count":51},{"id":"2006.09616","title":"Dynamic Tensor Rematerialization","created":"2020-06-17","cited_by_count":46},{"id":"2203.13240","title":"Token Dropping for Efficient BERT Pretraining","created":"2022-03-24","cited_by_count":42},{"id":"2502.00987","title":"RandLoRA: Full-rank parameter-efficient fine-tuning of large models","created":"2025-02-03","cited_by_count":35},{"id":"2401.12902","title":"Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?","created":"2024-01-23","cited_by_count":31},{"id":"2411.01327","title":"Visual Fourier Prompt Tuning","created":"2024-11-02","cited_by_count":30},{"id":"2205.01541","title":"Efficient Fine-Tuning of BERT Models on the Edge","created":"2022-05-03","cited_by_count":29},{"id":"2306.00477","title":"Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning","created":"2023-06-01","cited_by_count":26},{"id":"2401.16405","title":"Scaling Sparse Fine-Tuning to Large Language Models","created":"2024-01-29","cited_by_count":26},{"id":"2305.16597","title":"Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models","created":"2023-05-26","cited_by_count":25},{"id":"2211.10801","title":"Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training","created":"2022-11-19","cited_by_count":24},{"id":"2403.02178","title":"Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models","created":"2024-03-04","cited_by_count":20},{"id":"1901.11150","title":"Memory-Efficient Adaptive Optimization","created":"2019-01-30","cited_by_count":19},{"id":"2206.07382","title":"Sparse Structure Search for Parameter-Efficient Tuning","created":"2022-06-15","cited_by_count":17},{"id":"2409.15657","title":"M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning","created":"2024-09-24","cited_by_count":16},{"id":"2412.02685","title":"T-REG: Preference Optimization with Token-Level Reward Regularization","created":"2024-12-03","cited_by_count":13},{"id":"2510.04028","title":"The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View","created":"2025-10-05","cited_by_count":13},{"id":"2503.14640","title":"Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformer","created":"2025-03-18","cited_by_count":12},{"id":"2503.00723","title":"Re-Imagining Multimodal Instruction Tuning: A Representation View","created":"2025-03-02","cited_by_count":9},{"id":"2401.04339","title":"Memory-Efficient Fine-Tuning for Quantized Diffusion Model","created":"2024-01-09","cited_by_count":8},{"id":"2405.15525","title":"Sparse Matrix in Large Language Model Fine-tuning","created":"2024-05-24","cited_by_count":8},{"id":"2410.09982","title":"Self-Data Distillation for Recovering Quality in Pruned Large Language Models","created":"2024-10-13","cited_by_count":8},{"id":"2510.16670","title":"All You Need is One: Capsule Prompt Tuning with a Single Vector","created":"2025-10-19","cited_by_count":8},{"id":"2305.18513","title":"SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics","created":"2023-05-29","cited_by_count":5},{"id":"2403.09904","title":"FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models","created":"2024-03-14","cited_by_count":5},{"id":"2509.00996","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","created":"2025-08-31","cited_by_count":5},{"id":"2406.08816","title":"ToSA: Token Selective Attention for Efficient Vision Transformers","created":"2024-06-13","cited_by_count":4},{"id":"2501.18824","title":"Memory-Efficient Fine-Tuning of Transformers via Token Selection","created":"2025-01-31","cited_by_count":4},{"id":"2401.04105","title":"Dr$^2$Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning","created":"2024-01-08","cited_by_count":3},{"id":"2405.13155","title":"ReALLM: A general framework for LLM compression and fine-tuning","created":"2024-05-21","cited_by_count":3},{"id":"2509.17276","title":"Probabilistic Token Alignment for Large Language Model Fusion","created":"2025-09-21","cited_by_count":3},{"id":"2406.08756","title":"Optimizing Large Model Training through Overlapped Activation Recomputation","created":"2024-06-13","cited_by_count":2},{"id":"2502.00311","title":"Sparse Gradient Compression for Fine-Tuning Large Language Models","created":"2025-02-01","cited_by_count":2},{"id":"2502.07846","title":"Memory Analysis on the Training Course of DeepSeek Models","created":"2025-02-11","cited_by_count":1}],"next_cursor":null}