{"list":"other","total":55,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"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":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2403.06764","title":"An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models","created":"2024-03-11","cited_by_count":642},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2403.15388","title":"LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models","created":"2024-03-22","cited_by_count":402},{"id":"2410.04417","title":"SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference","created":"2024-10-06","cited_by_count":391},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"2311.15826","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","created":"2023-11-24","cited_by_count":328},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207},{"id":"2408.15237","title":"The Mamba in the Llama: Distilling and Accelerating Hybrid Models","created":"2024-08-27","cited_by_count":122},{"id":"2503.00540","title":"Streaming Video Question-Answering with In-context Video KV-Cache Retrieval","created":"2025-03-01","cited_by_count":117},{"id":"2404.06564","title":"MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection","created":"2024-04-09","cited_by_count":113},{"id":"2508.14444","title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","created":"2025-08-20","cited_by_count":108},{"id":"2409.02889","title":"LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture","created":"2024-09-04","cited_by_count":102},{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84},{"id":"2506.24044","title":"A Survey on Vision-Language-Action Models for Autonomous Driving","created":"2025-06-30","cited_by_count":72},{"id":"2412.16117","title":"PruneVid: Visual Token Pruning for Efficient Video Large Language Models","created":"2024-12-20","cited_by_count":67},{"id":"2405.14174","title":"Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model","created":"2024-05-23","cited_by_count":62},{"id":"2406.20092","title":"Efficient Large Multi-modal Models via Visual Context Compression","created":"2024-06-28","cited_by_count":46},{"id":"2412.19509","title":"MBQ: Modality-Balanced Quantization for Large Vision-Language Models","created":"2024-12-27","cited_by_count":45},{"id":"2412.09856","title":"LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity","created":"2024-12-13","cited_by_count":43},{"id":"2410.15091","title":"Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion","created":"2024-10-19","cited_by_count":41},{"id":"2412.13180","title":"Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration","created":"2024-12-17","cited_by_count":41},{"id":"2503.11579","title":"Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","created":"2025-03-14","cited_by_count":36},{"id":"2307.03135","title":"Distilling Large Vision-Language Model with Out-of-Distribution Generalizability","created":"2023-07-06","cited_by_count":33},{"id":"2506.21862","title":"LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs","created":"2025-06-27","cited_by_count":26},{"id":"2407.19617","title":"Leveraging Vision Language Models for Specialized Agricultural Tasks","created":"2024-07-29","cited_by_count":25},{"id":"2310.02998","title":"ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models","created":"2023-10-04","cited_by_count":19},{"id":"2507.23362","title":"Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers","created":"2025-07-31","cited_by_count":7},{"id":"2508.17243","title":"CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models","created":"2025-08-24","cited_by_count":3}],"next_cursor":null}