3 citations · 7 across the 12 of their papers we have counts for
12 papers · 1 filter
Accelerating Controllable Generation via Hybrid-grained Cache
Lin Liu, Huixia Ben, Shuo Wang +4
Controllable generative models have been widely used to improve the realism of synthetic visual content. However, such models must handle control conditions and content generation…
Res-Bench: Benchmarking the Robustness of Multimodal Large Language Models to Dynamic Resolution Input
Chenxu Li, Zhicai Wang, Yuan Sheng +3
Multimodal Large Language Models (MLLMs) increasingly support dynamic image resolutions. However, current evaluation paradigms primarily assess semantic performance, overlooking th…
SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding
Yuan Sheng, Yanbin Hao, Chenxu Li +2
Long video understanding remains challenging due to its complex, diverse, and temporally scattered content. Although video large language models (Video-LLMs) can process videos las…
Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning
Bob Zhang, Haoran Li, Tao Zhang +5
Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instruct…
Accelerating Diffusion Transformer via Gradient-Optimized Cache
Junxiang Qiu, Lin Liu, Shuo Wang +3
Feature caching has emerged as an effective strategy to accelerate diffusion transformer (DiT) sampling through temporal feature reuse. It is a challenging problem since (1) Progre…
Accelerating Diffusion Transformer via Error-Optimized Cache
Junxiang Qiu, Shuo Wang, Jinda Lu +4
Diffusion Transformer (DiT) is a crucial method for content generation. However, it needs a lot of time to sample. Many studies have attempted to use caching to reduce the time con…
Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
Xingyu Zhu, Beier Zhu, Yi Tan +3
Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions. While optimizing prompts on downstream labeled data…
Hand1000: Generating Realistic Hands from Text with Only 1,000 Images
Haozhuo Zhang, Bin Zhu, Yu Cao +1
Text-to-image generation models have achieved remarkable advancements in recent years, aiming to produce realistic images from textual descriptions. However, these models often str…
Selective Vision-Language Subspace Projection for Few-shot CLIP
Xingyu Zhu, Beier Zhu, Yi Tan +3
Vision-language models such as CLIP are capable of mapping the different modality data into a unified feature space, enabling zero/few-shot inference by measuring the similarity of…
Hierarchical Space-Time Attention for Micro-Expression Recognition
Haihong Hao, Shuo Wang, Huixia Ben +3
Micro-expression recognition (MER) aims to recognize the short and subtle facial movements from the Micro-expression (ME) video clips, which reveal real emotions. Recent MER method…
Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
Zhicai Wang, Longhui Wei, Tan Wang +5
Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications. Howe…
Boosting Few-Shot Learning via Attentive Feature Regularization
Xingyu Zhu, Shuo Wang, Jinda Lu +3
Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from differen…