5 citations · 10 across the 14 of their papers we have counts for
14 papers
MARS-Sep: Multimodal-Aligned Reinforced Sound Separation
Zihan Zhang, Xize Cheng, Zhennan Jiang +4
Universal sound separation faces a fundamental misalignment: models optimized for low-level signal metrics often produce semantically contaminated outputs, failing to suppress perc…
APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization
Minjie Hong, Zirun Guo, Yan Xia +4
Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data, but they often struggle with complex reasoning. While Reinforcement learning (RL) can boost reaso…
Unleashing the Power of Natural Audio Featuring Multiple Sound Sources
Xize Cheng, Slytherin Wang, Zehan Wang +3
Universal sound separation aims to extract clean audio tracks corresponding to distinct events from mixed audio, which is critical for artificial auditory perception. However, curr…
Towards Transformer-Based Aligned Generation with Self-Coherence Guidance
Shulei Wang, Wang Lin, Hai Huang +8
We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantical…
Speech Watermarking with Discrete Intermediate Representations
Shengpeng Ji, Ziyue Jiang, Jialong Zuo +4
Speech watermarking techniques can proactively mitigate the potential harmful consequences of instant voice cloning techniques. These techniques involve the insertion of signals in…
Classifier-guided Gradient Modulation for Enhanced Multimodal Learning
Zirun Guo, Tao Jin, Jingyuan Chen +1
Multimodal learning has developed very fast in recent years. However, during the multimodal training process, the model tends to rely on only one modality based on which it could l…
OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup
Xize Cheng, Siqi Zheng, Zehan Wang +8
The scaling up has brought tremendous success in the fields of vision and language in recent years. When it comes to audio, however, researchers encounter a major challenge in scal…
Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition
Zirun Guo, Tao Jin, Zhou Zhao
The development of multimodal models has significantly advanced multimodal sentiment analysis and emotion recognition. However, in real-world applications, the presence of various…
Non-confusing Generation of Customized Concepts in Diffusion Models
Wang Lin, Jingyuan Chen, Jiaxin Shi +8
We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in…
FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion
Zehan Wang, Ziang Zhang, Xize Cheng +8
Unified multi-model representation spaces are the foundation of multimodal understanding and generation. However, the billions of model parameters and catastrophic forgetting probl…
Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt
Yongqi Wang, Ruofan Hu, Rongjie Huang +6
Recent singing-voice-synthesis (SVS) methods have achieved remarkable audio quality and naturalness, yet they lack the capability to control the style attributes of the synthesized…
TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation
Xize Cheng, Rongjie Huang, Linjun Li +7
Direct speech-to-speech translation achieves high-quality results through the introduction of discrete units obtained from self-supervised learning. This approach circumvents delay…
Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers
Haifeng Huang, Yilun Chen, Zehan Wang +8
Recent advancements in 3D Large Language Models (LLMs) have demonstrated promising capabilities for 3D scene understanding. However, previous methods exhibit deficiencies in genera…
Extending Multi-modal Contrastive Representations
Zehan Wang, Ziang Zhang, Luping Liu +4
Multi-modal contrastive representation (MCR) of more than three modalities is critical in multi-modal learning. Although recent methods showcase impressive achievements, the high d…