6 citations · 29 across the 30 of their papers we have counts for
13 papers · 1 filter
Score and Distribution Matching Policy: Advanced Accelerated Visuomotor Policies via Matched Distillation
Bofang Jia, Pengxiang Ding, Can Cui +5
Visual-motor policy learning has advanced with architectures like diffusion-based policies, known for modeling complex robotic trajectories. However, their prolonged inference time…
QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning
Xinyang Tong, Pengxiang Ding, Yiguo Fan +9
This paper addresses the inherent inference latency challenges associated with deploying multimodal large language models (MLLM) in quadruped vision-language-action (QUAR-VLA) task…
CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction
Zhefei Gong, Pengxiang Ding, Shangke Lyu +5
In robotic visuomotor policy learning, diffusion-based models have achieved significant success in improving the accuracy of action trajectory generation compared to traditional au…
Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration
Yuhang Han, Xuyang Liu, Zihan Zhang +6
The quadratic complexity of Multimodal Large Language Models (MLLMs) with respect to context length poses significant computational and memory challenges, hindering their real-worl…
Accelerating Diffusion Transformers with Token-wise Feature Caching
Chang Zou, Xuyang Liu, Ting Liu +2
Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching met…
ProFD: Prompt-Guided Feature Disentangling for Occluded Person Re-Identification
Can Cui, Siteng Huang, Wenxuan Song +3
To address the occlusion issues in person Re-Identification (ReID) tasks, many methods have been proposed to extract part features by introducing external spatial information. Howe…
PiTe: Pixel-Temporal Alignment for Large Video-Language Model
Yang Liu, Pengxiang Ding, Siteng Huang +3
Fueled by the Large Language Models (LLMs) wave, Large Visual-Language Models (LVLMs) have emerged as a pivotal advancement, bridging the gap between image and text. However, video…
Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning
Fengyuan Dai, Siteng Huang, Min Zhang +2
To transfer knowledge from seen attribute-object compositions to recognize unseen ones, recent compositional zero-shot learning (CZSL) methods mainly discuss the optimal classifica…
M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension
Xuyang Liu, Ting Liu, Siteng Huang +6
Referring expression comprehension (REC) is a vision-language task to locate a target object in an image based on a language expression. Fully fine-tuning general-purpose pre-train…
DARA: Domain- and Relation-aware Adapters Make Parameter-efficient Tuning for Visual Grounding
Ting Liu, Xuyang Liu, Siteng Huang +5
Visual grounding (VG) is a challenging task to localize an object in an image based on a textual description. Recent surge in the scale of VG models has substantially improved perf…
Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference
Ting Liu, Xuyang Liu, Liangtao Shi +6
Parameter-efficient fine-tuning (PEFT) has emerged as a popular solution for adapting pre-trained Vision Transformer (ViT) models to downstream applications by updating only a smal…
Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
Han Zhao, Min Zhang, Wei Zhao +3
In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success. However, as the foundation model for many downstream…
Prompt-based Distribution Alignment for Unsupervised Domain Adaptation
Shuanghao Bai, Min Zhang, Wanqi Zhou +4
Recently, despite the unprecedented success of large pre-trained visual-language models (VLMs) on a wide range of downstream tasks, the real-world unsupervised domain adaptation (U…