131 citations · 137 across the 9 of their papers we have counts for
10 papers
Beyond Episodic Evaluation: Memory Architectural Bottlenecks in Sequential Embodied Question Answering
Zikui Cai, Kaushal Janga, Tan Dat Dao +15
Embodied question answering (EQA) is traditionally evaluated under an episodic formulation, where agents solve each task independently and reset internal state between episodes. Ho…
Image Generation with a Sphere Encoder
Kaiyu Yue, Menglin Jia, Ji Hou +1
We introduce the Sphere Encoder, an efficient generative framework capable of producing images in a single forward pass and competing with many-step diffusion models using fewer th…
Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
Ang Li, Charles Wang, Deqing Fu +9
Humans often use visual aids, for example diagrams or sketches, when solving complex problems. Training multimodal models to do the same, known as Visual Chain of Thought (Visual C…
Zero-Shot Vision Encoder Grafting via LLM Surrogates
Kaiyu Yue, Vasu Singla, Menglin Jia +6
Vision language models (VLMs) typically pair a modestly sized vision encoder with a large language model (LLM), e.g., Llama-70B, making the decoder the primary computational burden…
From Pixels to Prose: A Large Dataset of Dense Image Captions
Vasu Singla, Kaiyu Yue, Sukriti Paul +7
Training large vision-language models requires extensive, high-quality image-text pairs. Existing web-scraped datasets, however, are noisy and lack detailed image descriptions. To…
Object Recognition as Next Token Prediction
Kaiyu Yue, Bor-Chun Chen, Jonas Geiping +3
We present an approach to pose object recognition as next token prediction. The idea is to apply a language decoder that auto-regressively predicts the text tokens from image embed…
Visible Feature Guidance for Crowd Pedestrian Detection
Zhida Huang, Kaiyu Yue, Jiangfan Deng +1
Heavy occlusion and dense gathering in crowd scene make pedestrian detection become a challenging problem, because it's difficult to guess a precise full bounding box according to…
Matching Guided Distillation
Kaiyu Yue, Jiangfan Deng, Feng Zhou
Feature distillation is an effective way to improve the performance for a smaller student model, which has fewer parameters and lower computation cost compared to the larger teache…
Compact Generalized Non-local Network
Kaiyu Yue, Ming Sun, Yuchen Yuan +3
The non-local module is designed for capturing long-range spatio-temporal dependencies in images and videos. Although having shown excellent performance, it lacks the mechanism to…
Fine-grained Video Categorization with Redundancy Reduction Attention
Chen Zhu, Xiao Tan, Feng Zhou +4
For fine-grained categorization tasks, videos could serve as a better source than static images as videos have a higher chance of containing discriminative patterns. Nevertheless,…