{"list":"other","total":74,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268},{"id":"2402.12875","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","created":"2024-02-20","cited_by_count":260},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185},{"id":"2306.06687","title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","created":"2023-06-11","cited_by_count":169},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"2404.07771","title":"An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization","created":"2024-04-11","cited_by_count":73},{"id":"2311.12631","title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","created":"2023-11-21","cited_by_count":61},{"id":"2308.16890","title":"TouchStone: Evaluating Vision-Language Models by Language Models","created":"2023-08-31","cited_by_count":55},{"id":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51},{"id":"2410.08633","title":"Transformers Provably Solve Parity Efficiently with Chain of Thought","created":"2024-10-11","cited_by_count":50},{"id":"2406.10210","title":"Make It Count: Text-to-Image Generation with an Accurate Number of Objects","created":"2024-06-14","cited_by_count":47},{"id":"2405.19592","title":"Why Larger Language Models Do In-context Learning Differently?","created":"2024-05-30","cited_by_count":45},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44},{"id":"2211.12112","title":"Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark","created":"2022-11-22","cited_by_count":41},{"id":"2402.04520","title":"On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis","created":"2024-02-07","cited_by_count":41},{"id":"2407.01079","title":"On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)","created":"2024-07-01","cited_by_count":40},{"id":"2505.00337","title":"T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation","created":"2025-05-01","cited_by_count":39},{"id":"2406.03136","title":"Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models","created":"2024-06-05","cited_by_count":31},{"id":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30},{"id":"2303.04613","title":"The Descriptive Complexity of Graph Neural Networks","created":"2023-03-08","cited_by_count":26},{"id":"2411.07602","title":"Circuit Complexity Bounds for RoPE-based Transformer Architecture","created":"2024-11-12","cited_by_count":26},{"id":"2411.16525","title":"Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency","created":"2024-11-25","cited_by_count":22},{"id":"2411.17522","title":"On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality","created":"2024-11-26","cited_by_count":22},{"id":"2406.08164","title":"ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs","created":"2024-06-12","cited_by_count":21},{"id":"2412.06148","title":"The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity","created":"2024-12-09","cited_by_count":21},{"id":"2507.18107","title":"T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation","created":"2025-07-24","cited_by_count":19},{"id":"2501.04377","title":"On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis","created":"2025-01-08","cited_by_count":14},{"id":"2501.06444","title":"On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective","created":"2025-01-11","cited_by_count":14},{"id":"2412.17316","title":"RoPE Attention Can Be Trained in Almost Linear Time","created":"2024-12-23","cited_by_count":13},{"id":"2412.18040","title":"Theoretical Constraints on the Expressive Power of $\\mathsf{RoPE}$-based Tensor Attention Transformers","created":"2024-12-23","cited_by_count":12},{"id":"2503.04459","title":"Question-Aware Gaussian Experts for Audio-Visual Question Answering","created":"2025-03-06","cited_by_count":12},{"id":"2503.06884","title":"Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Help","created":"2025-03-10","cited_by_count":12},{"id":"2501.04299","title":"Circuit Complexity Bounds for Visual Autoregressive Model","created":"2025-01-08","cited_by_count":10},{"id":"2502.16490","title":"On Computational Limits of FlowAR Models: Expressivity and Efficiency","created":"2025-02-23","cited_by_count":10},{"id":"2504.04051","title":"Can You Count to Nine? A Human Evaluation Benchmark for Counting Limits in Modern Text-to-Video Models","created":"2025-04-05","cited_by_count":10},{"id":"2505.04946","title":"T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models","created":"2025-05-08","cited_by_count":10},{"id":"2409.15035","title":"Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP","created":"2024-09-23","cited_by_count":9},{"id":"2412.05562","title":"Modern Hopfield Networks Require Chain-of-Thought to Solve $\\mathsf{NC}^1$-Hard Problems","created":"2024-12-07","cited_by_count":9},{"id":"2412.18940","title":"Amuse: Human-AI Collaborative Songwriting with Multimodal Inspirations","created":"2024-12-25","cited_by_count":9},{"id":"2505.11892","title":"Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform","created":"2025-05-17","cited_by_count":9},{"id":"2507.17699","title":"Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations","created":"2025-07-23","cited_by_count":9},{"id":"2504.04702","title":"Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent","created":"2025-04-07","cited_by_count":8},{"id":"2504.19901","title":"Attention Mechanism, Max-Affine Partition, and Universal Approximation","created":"2025-04-28","cited_by_count":7},{"id":"2505.16284","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","created":"2025-05-22","cited_by_count":7},{"id":"2411.16549","title":"In-Context Deep Learning via Transformer Models","created":"2024-11-25","cited_by_count":6},{"id":"2508.07102","title":"Towards High-Order Mean Flow Generative Models: Feasibility, Expressivity, and Provably Efficient Criteria","created":"2025-08-09","cited_by_count":5},{"id":"2406.17777","title":"Text-Animator: Controllable Visual Text Video Generation","created":"2024-06-25","cited_by_count":4},{"id":"2505.19531","title":"Minimalist Softmax Attention Provably Learns Constrained Boolean Functions","created":"2025-05-26","cited_by_count":4},{"id":"2508.13214","title":"Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice Questions","created":"2025-08-16","cited_by_count":4},{"id":"2508.17550","title":"In-Context Algorithm Emulation in Fixed-Weight Transformers","created":"2025-08-24","cited_by_count":4},{"id":"2410.01308","title":"How Hard Is It for Message-Passing GNNs to Simulate One Weisfeiler-Lehman Color-Refinement Step?","created":"2024-10-02","cited_by_count":2}],"next_cursor":null}