{"list":"other","total":57,"rows":[{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"2303.13516","title":"Ablating Concepts in Text-to-Image Diffusion Models","created":"2023-03-23","cited_by_count":317},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"2302.11552","title":"Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC","created":"2023-02-22","cited_by_count":220},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102},{"id":"2212.10015","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","created":"2022-12-20","cited_by_count":97},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88},{"id":"1902.07181","title":"Measuring Compositionality in Representation Learning","created":"2019-02-19","cited_by_count":84},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75},{"id":"2111.03042","title":"Unsupervised Learning of Compositional Energy Concepts","created":"2021-11-04","cited_by_count":71},{"id":"2212.09095","title":"Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale","created":"2022-12-18","cited_by_count":64},{"id":"2307.05596","title":"Compositional Generalization from First Principles","created":"2023-07-10","cited_by_count":64},{"id":"2107.08221","title":"Visual Representation Learning Does Not Generalize Strongly Within the Same Domain","created":"2021-07-17","cited_by_count":61},{"id":"2408.14339","title":"ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty","created":"2024-08-26","cited_by_count":61},{"id":"2208.00005","title":"Testing Relational Understanding in Text-Guided Image Generation","created":"2022-07-29","cited_by_count":59},{"id":"2512.16853","title":"GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation","created":"2025-12-18","cited_by_count":52},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44},{"id":"2505.00661","title":"On the generalization of language models from in-context learning and finetuning: a controlled study","created":"2025-05-01","cited_by_count":40},{"id":"2210.03044","title":"Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?","created":"2022-10-06","cited_by_count":38},{"id":"1807.09810","title":"Coreset-Based Neural Network Compression","created":"2018-07-25","cited_by_count":27},{"id":"2303.02141","title":"Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!","created":"2023-03-03","cited_by_count":27},{"id":"2210.02412","title":"Why Random Pruning Is All We Need to Start Sparse","created":"2022-10-05","cited_by_count":26},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26},{"id":"2505.11581","title":"Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis","created":"2025-05-16","cited_by_count":22},{"id":"2305.18383","title":"A Three-regime Model of Network Pruning","created":"2023-05-28","cited_by_count":15},{"id":"2507.02550","title":"Position: A Theory of Deep Learning Must Include Compositional Sparsity","created":"2025-07-03","cited_by_count":14},{"id":"2101.11911","title":"The Role of Syntactic Planning in Compositional Image Captioning","created":"2021-01-28","cited_by_count":12},{"id":"2208.08195","title":"Benchmarking Compositionality with Formal Languages","created":"2022-08-17","cited_by_count":12},{"id":"2211.05077","title":"Prompting Large Pre-trained Vision-Language Models For Compositional Concept Learning","created":"2022-11-09","cited_by_count":12},{"id":"2512.17875","title":"Visually Prompted Benchmarks Are Surprisingly Fragile","created":"2025-12-19","cited_by_count":7},{"id":"2511.11438","title":"VP-Bench: A Comprehensive Benchmark for Visual Prompting in Multimodal Large Language Models","created":"2025-11-14","cited_by_count":5},{"id":"2207.02518","title":"Compositional Generalization in Grounded Language Learning via Induced Model Sparsity","created":"2022-07-06","cited_by_count":4}],"next_cursor":null}