5 papers
ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations
Junke Wang, Xiao Wang, Jiacheng Pan +16
This paper introduces ARM, a discrete representation-based AutoRegressive Model that unifies image understanding, generation, and editing within a next-token prediction framework.…
BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion
Shaobin Zhuang, Yuang Ai, Jiaming Han +7
Autoregressive language models generate text one token at a time, yet natural language is inherently structured in multi-token units, including phrases, n-grams, and collocations t…
BaFTA: Backprop-Free Test-Time Adaptation For Zero-Shot Vision-Language Models
Xuefeng Hu, Ke Zhang, Min Sun +3
Large-scale pretrained vision-language models like CLIP have demonstrated remarkable zero-shot image classification capabilities across diverse domains. To enhance CLIP's performan…
Large Language Models are Good Prompt Learners for Low-Shot Image Classification
Zhaoheng Zheng, Jingmin Wei, Xuefeng Hu +2
Low-shot image classification, where training images are limited or inaccessible, has benefited from recent progress on pre-trained vision-language (VL) models with strong generali…
Efficient Feature Distillation for Zero-shot Annotation Object Detection
Zhuoming Liu, Xuefeng Hu, Ram Nevatia
We propose a new setting for detecting unseen objects called Zero-shot Annotation object Detection (ZAD). It expands the zero-shot object detection setting by allowing the novel ob…