2 citations · 5 across the 17 of their papers we have counts for
19 papers
Locality Matters for Training-Free Audio Token Compression in Audio-Language Models
Jiale Luo, Xiaoyu Liang, Haoji Hu
Audio-language models (ALMs) are increasingly used for audio captioning, question answering, and open-ended audio understanding, but their inference cost remains high when audio in…
D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation
Wenjie Zheng, Haoji Hu, Jiali Lu +2
Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing studies mainly focus on image clas…
Q Cache: Visual Attention is Valuable in Less than Half of Decode Layers for Multimodal Large Language Model
Jiedong Zhuang, Lu Lu, Ming Dai +4
Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual to…
Learn Before Represent: Bridging Generative and Contrastive Learning for Domain-Specific LLM Embeddings
Xiaoyu Liang, Yuchen Peng, Jiale Luo +3
Large Language Models (LLMs) adapted via contrastive learning excel in general representation learning but struggle in vertical domains like chemistry and law, primarily due to a l…
SemanticGen: Video Generation in Semantic Space
Jianhong Bai, Xiaoshi Wu, Xintao Wang +9
State-of-the-art video generative models typically learn the distribution of video latents in the VAE space and map them to pixels using a VAE decoder. While this approach can gene…
Training-Free Multi-View Extension of IC-Light for Textual Position-Aware Scene Relighting
Jiangnan Ye, Jiedong Zhuang, Lianrui Mu +5
We introduce GS-Light, an efficient, textual position-aware pipeline for text-guided relighting of 3D scenes represented via Gaussian Splatting (3DGS). GS-Light implements a traini…
No Pixel Left Behind: A Detail-Preserving Architecture for Robust High-Resolution AI-Generated Image Detection
Lianrui Mu, Zou Xingze, Jianhong Bai +7
The rapid growth of high-resolution, meticulously crafted AI-generated images poses a significant challenge to existing detection methods, which are often trained and evaluated on…
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
Jianhong Bai, Menghan Xia, Xiao Fu +8
Camera control has been actively studied in text or image conditioned video generation tasks. However, altering camera trajectories of a given video remains under-explored, despite…
Dynamic Token Reduction during Generation for Vision Language Models
Xiaoyu Liang, Chaofeng Guan, Jiaying Lu +3
Vision-Language Models (VLMs) have achieved notable success in multimodal tasks but face practical limitations due to the quadratic complexity of decoder attention mechanisms and a…
ST: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming
Jiedong Zhuang, Lu Lu, Ming Dai +4
Multimodal large language models (MLLMs) enhance their perceptual capabilities by integrating visual and textual information. However, processing the massive number of visual token…
SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
Jianhong Bai, Menghan Xia, Xintao Wang +6
Recent advancements in video diffusion models have shown exceptional abilities in simulating real-world dynamics and maintaining 3D consistency. This progress inspires us to invest…
Identity-Preserving Pose-Guided Character Animation via Facial Landmarks Transformation
Lianrui Mu, Xingze Zhou, Wenjie Zheng +2
Creating realistic pose-guided image-to-video character animations while preserving facial identity remains challenging, especially in complex and dynamic scenarios such as dancing…
Mitigating Hallucination in Visual-Language Models via Re-Balancing Contrastive Decoding
Xiaoyu Liang, Jiayuan Yu, Lianrui Mu +7
Although Visual-Language Models (VLMs) have shown impressive capabilities in tasks like visual question answering and image captioning, they still struggle with hallucinations. Ana…
FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance
Jiedong Zhuang, Jiaqi Hu, Lianrui Mu +4
CLIP has achieved impressive zero-shot performance after pre-training on a large-scale dataset consisting of paired image-text data. Previous works have utilized CLIP by incorporat…
UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing
Jianhong Bai, Tianyu He, Yuchi Wang +4
Recent advances in text-guided video editing have showcased promising results in appearance editing (e.g., stylization). However, video motion editing in the temporal dimension (e.…
TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing
Lianrui Mu, Jianhong Bai, Xiaoxuan He +5
Enhancing the domain generalization performance of Face Anti-Spoofing (FAS) techniques has emerged as a research focus. Existing methods are dedicated to extracting domain-invarian…
Unified Medical Image Pre-training in Language-Guided Common Semantic Space
Xiaoxuan He, Yifan Yang, Xinyang Jiang +6
Vision-Language Pre-training (VLP) has shown the merits of analysing medical images, by leveraging the semantic congruence between medical images and their corresponding reports. I…
Robustness-Guided Image Synthesis for Data-Free Quantization
Jianhong Bai, Yuchen Yang, Huanpeng Chu +7
Quantization has emerged as a promising direction for model compression. Recently, data-free quantization has been widely studied as a promising method to avoid privacy concerns, w…
Towards Distribution-Agnostic Generalized Category Discovery
Jianhong Bai, Zuozhu Liu, Hualiang Wang +7
Data imbalance and open-ended distribution are two intrinsic characteristics of the real visual world. Though encouraging progress has been made in tackling each challenge separate…