15 papers
RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language Models
Zhiping Wu, Dongdong Ren, Yangchengyu Zhou +4
Large vision-language models (VLMs) can be efficiently deployed under stringent memory and latency constraints through post training quantization (PTQ). However, most PTQ methods a…
Adaptive Forensic Feature Refinement via Intrinsic Importance Perception
Jiazhen Yang, Junjun Zheng, Kejia Chen +5
With the rapid development of generative models and multimodal content editing technologies, the key challenge in synthetic image detection (SID) lies in cross-distribution general…
Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models
Yunkai Dang, Yifan Jiang, Yizhu Jiang +3
Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in various perception and reasoning tasks. Despite this success, ensuring their reliability in p…
UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing
Yunkai Dang, Minxin Dai, Yuekun Yang +4
Ultra-high-resolution (UHR) remote sensing imagery couples kilometer-scale context with query-critical evidence that may occupy only a few pixels. Such vast spatial scale leads to…
CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models
Yunkai Dang, Yizhu Jiang, Yifan Jiang +4
Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing approaches typically address…
Understanding and Enforcing Weight Disentanglement in Task Arithmetic
Shangge Liu, Yuehan Yin, Lei Wang +5
Task arithmetic provides an efficient, training-free way to edit pre-trained models, yet lacks a fundamental theoretical explanation for its success. The existing concept of ``weig…
Robust Dataset Distillation by Matching Adversarial Trajectories
Wei Lai, Tianyu Ding, ren dongdong +4
Dataset distillation synthesizes compact datasets that enable models to achieve performance comparable to training on the original large-scale datasets. However, existing distillat…
Distractor-free Generalizable 3D Gaussian Splatting
Yanqi Bao, Jing Liao, Jing Huo +1
We present DGGS, a novel framework that addresses the previously unexplored challenge: (3DGS). It mitigates 3D incons…
3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities
Yanqi Bao, Tianyu Ding, Jing Huo +5
3D Gaussian Splatting (3DGS) has emerged as a prominent technique with the potential to become a mainstream method for 3D representations. It can effectively transform multi-view i…
Training-Free Video Editing via Optical Flow-Enhanced Score Distillation
Lianghan Zhu, Yanqi Bao, Jing Huo +4
The rapid advancement in visual generation, particularly the emergence of pre-trained text-to-image and text-to-video models, has catalyzed growing interest in training-free video…
Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model
Zheng Gu, Shiyuan Yang, Jing Liao +2
Visual In-Context Learning (ICL) has emerged as a promising research area due to its capability to accomplish various tasks with limited example pairs through analogical reasoning.…
ONNXPruner: ONNX-Based General Model Pruning Adapter
Dongdong Ren, Wenbin Li, Tianyu Ding +5
Recent advancements in model pruning have focused on developing new algorithms and improving upon benchmarks. However, the practical application of these algorithms across various…
Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation
Wenxiao Deng, Wenbin Li, Tianyu Ding +5
Dataset distillation has emerged as a promising approach in deep learning, enabling efficient training with small synthetic datasets derived from larger real ones. Particularly, di…
Where and How: Mitigating Confusion in Neural Radiance Fields from Sparse Inputs
Yanqi Bao, Yuxin Li, Jing Huo +4
Neural Radiance Fields from Sparse input} (NeRF-S) have shown great potential in synthesizing novel views with a limited number of observed viewpoints. However, due to the inherent…
InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
Yanqi Bao, Tianyu Ding, Jing Huo +3
Generalizing Neural Radiance Fields (NeRF) to new scenes is a significant challenge that existing approaches struggle to address without extensive modifications to vanilla NeRF fra…