{"list":"other","total":93,"rows":[{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"2112.13890","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","created":"2021-12-27","cited_by_count":167},{"id":"1810.12440","title":"TallyQA: Answering Complex Counting Questions","created":"2018-10-29","cited_by_count":153},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136},{"id":"2305.12821","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","created":"2023-05-22","cited_by_count":133},{"id":"2504.19854","title":"NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks","created":"2025-04-28","cited_by_count":127},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126},{"id":"2211.08416","title":"Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment","created":"2022-11-15","cited_by_count":108},{"id":"2312.06550","title":"LLM360: Towards Fully Transparent Open-Source LLMs","created":"2023-12-11","cited_by_count":104},{"id":"2210.10047","title":"From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data","created":"2022-10-18","cited_by_count":103},{"id":"2209.08959","title":"Latent Plans for Task-Agnostic Offline Reinforcement Learning","created":"2022-09-19","cited_by_count":81},{"id":"2210.11435","title":"Learning and Retrieval from Prior Data for Skill-based Imitation Learning","created":"2022-10-20","cited_by_count":77},{"id":"2306.14447","title":"RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools","created":"2023-06-26","cited_by_count":76},{"id":"2501.19201","title":"Efficient Reasoning with Hidden Thinking","created":"2025-01-31","cited_by_count":75},{"id":"2309.14320","title":"MUTEX: Learning Unified Policies from Multimodal Task Specifications","created":"2023-09-25","cited_by_count":70},{"id":"2403.07918","title":"On the Societal Impact of Open Foundation Models","created":"2024-02-27","cited_by_count":65},{"id":"2307.08927","title":"Multi-Stage Cable Routing through Hierarchical Imitation Learning","created":"2023-07-18","cited_by_count":60},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56},{"id":"2306.17237","title":"HYDRA: Hybrid Robot Actions for Imitation Learning","created":"2023-06-29","cited_by_count":55},{"id":"2306.10007","title":"Robot Learning with Sensorimotor Pre-training","created":"2023-06-16","cited_by_count":51},{"id":"2312.04549","title":"PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play","created":"2023-12-07","cited_by_count":50},{"id":"2408.12570","title":"Jamba-1.5: Hybrid Transformer-Mamba Models at Scale","created":"2024-08-22","cited_by_count":50},{"id":"2306.00942","title":"Train Offline, Test Online: A Real Robot Learning Benchmark","created":"2023-06-01","cited_by_count":47},{"id":"2412.12444","title":"LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers","created":"2024-12-17","cited_by_count":37},{"id":"2108.08910","title":"Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search","created":"2021-08-18","cited_by_count":34},{"id":"2206.01198","title":"Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization","created":"2022-06-02","cited_by_count":32},{"id":"2409.18962","title":"Exploring Token Pruning in Vision State Space Models","created":"2024-09-27","cited_by_count":28},{"id":"2011.02398","title":"A Modular Robotic Arm Control Stack for Research: Franka-Interface and FrankaPy","created":"2020-11-04","cited_by_count":25},{"id":"2412.12441","title":"Numerical Pruning for Efficient Autoregressive Models","created":"2024-12-17","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":"2207.12577","title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution","created":"2022-07-25","cited_by_count":20},{"id":"2410.15567","title":"Pruning Foundation Models for High Accuracy without Retraining","created":"2024-10-21","cited_by_count":20},{"id":"2406.07929","title":"A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models","created":"2024-06-12","cited_by_count":18},{"id":"2505.18399","title":"Taming Diffusion for Dataset Distillation with High Representativeness","created":"2025-05-23","cited_by_count":18},{"id":"2103.07679","title":"OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding","created":"2021-03-13","cited_by_count":16},{"id":"2402.16424","title":"COMAE: COMprehensive Attribute Exploration for Zero-shot Hashing","created":"2024-02-26","cited_by_count":16},{"id":"2410.14725","title":"Rethinking Token Reduction for State Space Models","created":"2024-10-16","cited_by_count":15},{"id":"2409.17372","title":"Search for Efficient Large Language Models","created":"2024-09-25","cited_by_count":14},{"id":"2411.01171","title":"Fast and Memory-Efficient Video Diffusion Using Streamlined Inference","created":"2024-11-02","cited_by_count":14},{"id":"2403.10799","title":"Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment","created":"2024-03-16","cited_by_count":13},{"id":"2505.14709","title":"FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge","created":"2025-05-17","cited_by_count":10},{"id":"2403.10760","title":"CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects","created":"2024-03-16","cited_by_count":8},{"id":"2501.04066","title":"Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detection","created":"2025-01-07","cited_by_count":8},{"id":"2503.16709","title":"QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge","created":"2025-03-20","cited_by_count":8},{"id":"2401.14502","title":"MResT: Multi-Resolution Sensing for Real-Time Control with Vision-Language Models","created":"2024-01-25","cited_by_count":5},{"id":"2505.23844","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","created":"2025-05-28","cited_by_count":1}],"next_cursor":null}