1 citations · 3 across the 12 of their papers we have counts for
13 papers
Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher
Shiyi Zhang, Mushui Liu, Yunze Tong +8
On-policy distillation (OPD), which leverages a pre-trained, specialized teacher model to provide dense supervisory signals, has achieved significant success in Large Language Mode…
CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
Fangtai Wu, Hailong Guo, Shijie Huang +7
Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Adaptation (LoRA). As the number…
MedVeriSeg: Teaching LISA-Like Medical Segmentation Models to Verify Query Validity Without Extra Training
Qinyue Tong, Xiaozhen Wang, Ziqian Lu +3
Despite recent progress in text-prompt-based medical image segmentation, existing LISA-like MLLM-based methods typically generate masks regardless of whether the target specified i…
DCoAR: Deep Concept Injection into Unified Autoregressive Models for Personalized Text-to-Image Generation
Fangtai Wu, Mushui Liu, Weijie He +2
The unified autoregressive (AR) model excels at multimodal understanding and generation. However, its full potential in the domain of customized image generation has yet to be full…
DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation
Weijie He, Mushui Liu, Yunlong Yu +2
Compositional text-to-video generation, which requires synthesizing dynamic scenes with multiple interacting entities and precise spatial-temporal relationships, remains a critical…
CustomVideoX: 3D Reference Attention Driven Dynamic Adaptation for Zero-Shot Customized Video Diffusion Transformers
D. She, Mushui Liu, Jingxuan Pang +9
Customized generation has achieved significant progress in image synthesis, yet personalized video generation remains challenging due to temporal inconsistencies and quality degrad…
RestorerID: Towards Tuning-Free Face Restoration with ID Preservation
Jiacheng Ying, Mushui Liu, Zhe Wu +7
Blind face restoration has made great progress in producing high-quality and lifelike images. Yet it remains challenging to preserve the ID information especially when the degradat…
Hybrid Mask Generation for Infrared Small Target Detection with Single-Point Supervision
Weijie He, Mushui Liu, Yunlong Yu
Single-frame infrared small target (SIRST) detection poses a significant challenge due to the requirement to discern minute targets amidst complex infrared background clutter. In t…
Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition
Bozheng Li, Mushui Liu, Gaoang Wang +1
In this paper, we propose a novel Temporal Sequence-Aware Model (TSAM) for few-shot action recognition (FSAR), which incorporates a sequential perceiver adapter into the pre-traini…
Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning
Mushui Liu, Fangtai Wu, Bozheng Li +3
Few-shot learning (FSL) aims to recognize new concepts using a limited number of visual samples. Existing approaches attempt to incorporate semantic information into the limited vi…
OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning
Mushui Liu, Bozheng Li, Yunlong Yu
Recent Vision-Language Models (VLMs) \textit{e.g.} CLIP have made great progress in video recognition. Despite the improvement brought by the strong visual backbone in extracting s…
Fully Fine-tuned CLIP Models are Efficient Few-Shot Learners
Mushui Liu, Bozheng Li, Yunlong Yu
Prompt tuning, which involves training a small set of parameters, effectively enhances the pre-trained Vision-Language Models (VLMs) to downstream tasks. However, they often come a…
SYNC-CLIP: Synthetic Data Make CLIP Generalize Better in Data-Limited Scenarios
Mushui Liu, Weijie He, Ziqian Lu +1
Prompt learning is a powerful technique for transferring Vision-Language Models (VLMs) such as CLIP to downstream tasks. However, the prompt-based methods that are fine-tuned solel…