Pengchuan Zhang

TLDR: Token-Level Detective Reward Model for Large Vision Language Models ICLR 2025 BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation CVPR 2024 Evaluating Text-to-Visual Generation with Image-to-Text Generation ECCV 2024 Learning Video Context as Interleaved Multimodal Sequences ECCV 2024 Revisiting the Role of Language Priors in Vision-Language Models ICML 2024 Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality EMNLP 2023 Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding CVPR 2023 DIME-FM : DIstilling Multimodal and Efficient Foundation Models ICCV 2023 EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone ICCV 2023 Parameter-Efficient Model Adaptation for Vision Transformers AAAI 2023 UniVTG: Towards Unified Video-Language Temporal Grounding ICCV 2023 3DB: A Framework for Debugging Computer Vision Models NeurIPS 2022 An Empirical Study of Training End-to-End Vision-and-Language Transformers CVPR 2022 Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone NeurIPS 2022 Efficient Self-supervised Vision Transformers for Representation Learning ICLR 2022 ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models NeurIPS 2022 GLIPv2: Unifying Localization and Vision-Language Understanding NeurIPS 2022 Grounded Language-Image Pre-Training CVPR 2022 K-LITE: Learning Transferable Visual Models with External Knowledge NeurIPS 2022 Missingness Bias in Model Debugging ICLR 2022 RegionCLIP: Region-Based Language-Image Pretraining CVPR 2022 Unified Contrastive Learning in Image-Text-Label Space CVPR 2022 Dynamic DETR: End-to-End Object Detection With Dynamic Attention ICCV 2021 Focal Attention for Long-Range Interactions in Vision Transformers NeurIPS 2021 Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference ICML 2021 Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding ICCV 2021 Object-Centric Image Generation from Layouts AAAI 2021 VinVL: Revisiting Visual Representations in Vision-Language Models CVPR 2021 Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks ECCV 2020 A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks NeurIPS 2019 Object-Driven Text-To-Image Synthesis via Adversarial Training CVPR 2019 Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers NeurIPS 2019 RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications AAAI 2019 TIGEr: Text-to-Image Grounding for Image Caption Evaluation EMNLP 2019 Towards Coherent and Cohesive Long-form Text Generation NAACL 2019 Understanding the Role of Momentum in Stochastic Gradient Methods NeurIPS 2019 Using Statistics to Automate Stochastic Optimization NeurIPS 2019 AttnGAN: Fine-Grained Text to Image Generation With Attentional Generative Adversarial Networks CVPR 2018 On the Discrimination-Generalization Tradeoff in GANs ICLR 2018 Turbo Learning for CaptionBot and DrawingBot NeurIPS 2018