13 citations · 15 across the 16 of their papers we have counts for
7 papers · 1 filter
MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages
Yexing Du, Kaiyuan Liu, Youcheng Pan +7
Multimodal Large Language Models (MLLMs) have achieved great success in Speech-to-Text Translation (S2TT) tasks. However, current research is constrained by two key challenges: lan…
Did Models Learn Sufficiently? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation
Yannan Chen, Ruoyu Chen, Wei Wang +6
Current visual models often make predictions based on a limited set of discriminative visual cues. As a result, they may become unreliable when the distribution shifts or when thes…
VoxelFormer: Parameter-Efficient Multi-Subject Visual Decoding from fMRI
Chenqian Le, Yilin Zhao, Nikasadat Emami +4
Recent advances in fMRI-based visual decoding have enabled compelling reconstructions of perceived images. However, most approaches rely on subject-specific training, limiting scal…
CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models
Qiming Li, Zekai Ye, Xiaocheng Feng +8
Although Large Vision-Language Models (LVLMs) have demonstrated powerful capabilities in interpreting visual information, they frequently produce content that deviates from visual…
NormDirection: Restoring the Missing Query Norm in Vision Linear Attention
Weikang Meng, Yadan Luo, Liangyu Huo +4
Linear attention mitigates the quadratic complexity of softmax attention but suffers from a critical loss of expressiveness. We identify two primary causes: (1) The normalization o…
FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation
Fan Yang, Yousong Zhu, Xin Li +6
Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling, enabling both accurate content understandin…
Prototype Perturbation for Relaxing Alignment Constraints in Backward-Compatible Learning
Zikun Zhou, Yushuai Sun, Wenjie Pei +2
The traditional paradigm to update retrieval models requires re-computing the embeddings of the gallery data, a time-consuming and computationally intensive process known as backfi…