{"list":"other","total":79,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"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":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2404.00456","title":"QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs","created":"2024-03-30","cited_by_count":634},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471},{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414},{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"1906.04721","title":"Data-Free Quantization Through Weight Equalization and Bias Correction","created":"2019-06-11","cited_by_count":336},{"id":"1812.00101","title":"DVC: An End-to-end Deep Video Compression Framework","created":"2018-11-30","cited_by_count":332},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"2203.10886","title":"ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding","created":"2022-03-21","cited_by_count":301},{"id":"2402.17762","title":"Massive Activations in Large Language Models","created":"2024-02-27","cited_by_count":294},{"id":"2403.07378","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","created":"2024-03-12","cited_by_count":243},{"id":"2401.06118","title":"Extreme Compression of Large Language Models via Additive Quantization","created":"2024-01-11","cited_by_count":232},{"id":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211},{"id":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195},{"id":"2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","created":"2024-11-19","cited_by_count":182},{"id":"2312.05821","title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","created":"2023-12-10","cited_by_count":169},{"id":"1901.08276","title":"Traditional and Heavy-Tailed Self Regularization in Neural Network Models","created":"2019-01-24","cited_by_count":105},{"id":"2304.02633","title":"HNeRV: A Hybrid Neural Representation for Videos","created":"2023-04-05","cited_by_count":100},{"id":"2301.11189","title":"Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models","created":"2023-01-26","cited_by_count":94},{"id":"2403.14123","title":"AI and Memory Wall","created":"2024-03-21","cited_by_count":92},{"id":"2406.11235","title":"QTIP: Quantization with Trellises and Incoherence Processing","created":"2024-06-17","cited_by_count":91},{"id":"2402.10631","title":"BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation","created":"2024-02-16","cited_by_count":84},{"id":"2502.20762","title":"Towards Practical Real-Time Neural Video Compression","created":"2025-02-28","cited_by_count":80},{"id":"2202.06533","title":"An Introduction to Neural Data Compression","created":"2022-02-14","cited_by_count":79},{"id":"2503.12340","title":"SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression","created":"2025-03-16","cited_by_count":67},{"id":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61},{"id":"2310.16387","title":"Frequency-Aware Transformer for Learned Image Compression","created":"2023-10-25","cited_by_count":58},{"id":"2312.02753","title":"C3: High-performance and low-complexity neural compression from a single image or video","created":"2023-12-05","cited_by_count":55},{"id":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48},{"id":"2312.07950","title":"CBQ: Cross-Block Quantization for Large Language Models","created":"2023-12-13","cited_by_count":34},{"id":"2502.06415","title":"Systematic Outliers in Large Language Models","created":"2025-02-10","cited_by_count":33},{"id":"2112.06334","title":"DPICT: Deep Progressive Image Compression Using Trit-Planes","created":"2021-12-12","cited_by_count":25},{"id":"2102.02913","title":"Progressive Neural Image Compression with Nested Quantization and Latent Ordering","created":"2021-02-04","cited_by_count":24},{"id":"2303.05715","title":"Context-Based Trit-Plane Coding for Progressive Image Compression","created":"2023-03-10","cited_by_count":21},{"id":"2209.09244","title":"Flexible Neural Image Compression via Code Editing","created":"2022-09-19","cited_by_count":20},{"id":"2405.16817","title":"Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model","created":"2024-05-27","cited_by_count":17},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16},{"id":"2407.12397","title":"Mamba-PTQ: Outlier Channels in Recurrent Large Language Models","created":"2024-07-17","cited_by_count":15},{"id":"2508.14090","title":"DLLMQuant: Quantizing Diffusion-based Large Language Models","created":"2025-08-14","cited_by_count":11},{"id":"2108.00065","title":"Model Preserving Compression for Neural Networks","created":"2021-07-30","cited_by_count":9},{"id":"2410.10714","title":"SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators","created":"2024-10-14","cited_by_count":4},{"id":"2305.20000","title":"Memory-Centric Computing","created":"2023-05-31","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":"2401.17789","title":"Robustly overfitting latents for flexible neural image compression","created":"2024-01-31","cited_by_count":2},{"id":"2302.04045","title":"Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models","created":"2023-02-08","cited_by_count":1},{"id":"2405.20973","title":"LCQ: Low-Rank Codebook based Quantization for Large Language Models","created":"2024-05-31","cited_by_count":1},{"id":"2408.14513","title":"Variational autoencoder-based neural network model compression","created":"2024-08-25","cited_by_count":1}],"next_cursor":null}