{"list":"other","total":51,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"id":"1704.07138","title":"Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search","created":"2017-04-24","cited_by_count":237},{"id":"2403.13187","title":"Evolutionary Optimization of Model Merging Recipes","created":"2024-03-19","cited_by_count":208},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"1805.12369","title":"Reinforced Continual Learning","created":"2018-05-31","cited_by_count":186},{"id":"1804.06609","title":"Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation","created":"2018-04-18","cited_by_count":182},{"id":"1910.10088","title":"Gaze360: Physically Unconstrained Gaze Estimation in the Wild","created":"2019-10-22","cited_by_count":174},{"id":"1612.03153","title":"Panoptic Studio: A Massively Multiview System for Social Interaction Capture","created":"2016-12-09","cited_by_count":173},{"id":"1710.00925","title":"Fine-Grained Head Pose Estimation Without Keypoints","created":"2017-10-02","cited_by_count":163},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160},{"id":"2205.12393","title":"Fine-tuned Language Models are Continual Learners","created":"2022-05-24","cited_by_count":156},{"id":"1504.02863","title":"Appearance-Based Gaze Estimation in the Wild","created":"2015-04-11","cited_by_count":153},{"id":"1804.01005","title":"Face Alignment in Full Pose Range: A 3D Total Solution","created":"2018-04-02","cited_by_count":148},{"id":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147},{"id":"2007.15837","title":"ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation","created":"2020-07-31","cited_by_count":141},{"id":"2312.06795","title":"Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks","created":"2023-12-11","cited_by_count":133},{"id":"2403.01244","title":"Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal","created":"2024-03-02","cited_by_count":118},{"id":"2403.19522","title":"Model Stock: All we need is just a few fine-tuned models","created":"2024-03-28","cited_by_count":92},{"id":"2104.05489","title":"Continual Learning for Text Classification with Information Disentanglement Based Regularization","created":"2021-04-12","cited_by_count":86},{"id":"2202.12555","title":"6D Rotation Representation For Unconstrained Head Pose Estimation","created":"2022-02-25","cited_by_count":64},{"id":"2005.10353","title":"WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose","created":"2020-05-20","cited_by_count":47},{"id":"2211.02219","title":"Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models","created":"2022-11-04","cited_by_count":40},{"id":"2308.11509","title":"SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation","created":"2023-08-22","cited_by_count":39},{"id":"2307.16687","title":"DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation","created":"2023-07-31","cited_by_count":36},{"id":"2010.07184","title":"A Vector-based Representation to Enhance Head Pose Estimation","created":"2020-10-14","cited_by_count":35},{"id":"2310.14510","title":"CITB: A Benchmark for Continual Instruction Tuning","created":"2023-10-23","cited_by_count":33},{"id":"1802.02690","title":"Driver Gaze Zone Estimation using Convolutional Neural Networks: A General Framework and Ablative Analysis","created":"2018-02-08","cited_by_count":20},{"id":"2402.15726","title":"CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge","created":"2024-02-24","cited_by_count":16},{"id":"2403.05124","title":"CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model","created":"2024-03-08","cited_by_count":13},{"id":"2110.09243","title":"Leveraging MoCap Data for Human Mesh Recovery","created":"2021-10-18","cited_by_count":12},{"id":"2401.05807","title":"On the representation and methodology for wide and short range head pose estimation","created":"2024-01-11","cited_by_count":12},{"id":"2302.01110","title":"DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Angles","created":"2023-02-02","cited_by_count":6},{"id":"2403.18104","title":"Mathematical Foundation and Corrections for Full Range Head Pose Estimation","created":"2024-03-26","cited_by_count":3}],"next_cursor":null}