arXiv subjects

Chaeyoung Jung

Publications and source records attributed to Chaeyoung Jung.

12 recordsLinked to original sources

arXiv2026

Probing Cross-modal Information Hubs in Audio-Visual LLMs

Audio-visual large language models (AVLLMs) have recently emerged as a powerful architecture capable of jointly reasoning over audio, visual, and textual modalities. In AVLLMs, the bidirectional interaction between audio and video modalities introduces intricate processing dynamics, necessitating a deeper understanding of their internal mechanisms. However, unlike extensively studied text-only or large vision language models, the internal workings of AVLLMs remain largely unexplored. In this paper, we focus on cross-modal information flow between audio and visual modalities in AVLLMs, investigating where information derived from one modality is encoded within the token representations of the other modality. Through an analysis of multiple recent AVLLMs, we uncover two common findings. First, AVLLMs primarily encode integrated audio-visual information in sink tokens. Second, sink tokens do not uniformly hold cross-modal information. Instead, a distinct subset of sink tokens, which we term cross-modal sink tokens, specializes in storing such information. Based on these findings, we further propose a simple training-free hallucination mitigation method by encouraging reliance on integrated cross-modal information within cross-modal sink tokens. Our code is available at https://github.com/kaistmm/crossmodal-hub.

cs.AI↗

arXiv2026

Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs

Omnimodal Large Language Models (Omni-LLMs) incur substantial computational overhead due to the large number of multimodal input tokens they process, making token reduction essential for real-world deployment. Existing Omni-LLM pruning methods typically reduce this cost by selecting tokens that are important for the current query or strongly aligned with cross-modal cues. However, such strategies can discard evidence that falls outside these criteria, even when needed for different questions or for understanding context beyond aligned audio-visual cues. To address this limitation, we reframe Omni-LLM token reduction as preserving broad audio-visual context while removing cross-modal redundancy. We propose ContextGuard, an inference-time token pruning framework built on this principle. ContextGuard predicts coarse visual semantics from audio and prunes video tokens whose coarse semantics are likely recoverable from audio, while retaining additional video tokens to preserve localized visual details that audio alone cannot specify. For further compression, our method merges temporally similar video tokens. The framework requires no downstream LLM fine-tuning and uses only an independently trained lightweight predictor. On Qwen2.5-Omni and Video-SALMONN2+ at 3B and 7B scales across six audio-visual benchmarks, ContextGuard outperforms prior inference-time pruning methods while pruning more tokens. Notably, on Qwen2.5-Omni 7B, ContextGuard achieves full-token-level performance on five of six benchmarks while pruning 55% of input tokens.

cs.CV↗

arXiv2026

FastAV: Efficient Token Pruning for Audio-Visual Large Language Model Inference

In this work, we present FastAV, the first token pruning framework tailored for audio-visual large language models (AV-LLMs). While token pruning has been actively explored in standard large language models (LLMs) and vision-language models (LVLMs), its application to AV-LLMs has received little attention, even though multimodal integration substantially increases their token demands. To address this gap, we introduce a pruning strategy that utilizes attention weights to identify tokens emphasized at different stages and estimates their importance. Building on this analysis, FastAV applies a two-stage pruning strategy: (1) global pruning in intermediate layers to remove broadly less influential tokens, and (2) fine pruning in later layers considering the impact on next token generation. Notably, our method does not rely on full attention maps, which makes it fully compatible with efficient attention mechanisms such as FlashAttention. Extensive experiments demonstrate that FastAV reduces FLOPs by more than 40% on two representative AV-LLMs, while preserving or even improving model performance.

cs.LG↗

arXiv2025

AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding

Hallucination remains a major challenge in multimodal large language models (MLLMs). To address this, various contrastive decoding (CD) methods have been proposed that contrasts original logits with hallucinated logits generated from perturbed inputs. While CD has shown promise in vision-language models (VLMs), it is not well-suited for AV-LLMs, where hallucinations often emerge from both unimodal and cross-modal combinations involving audio, video, and language. These intricate interactions call for a more adaptive and modality-aware decoding strategy. In this paper, we propose Audio-Visual Contrastive Decoding (AVCD)-a novel, training-free decoding framework designed to model trimodal interactions and suppress modality-induced hallucinations in AV-LLMs. Unlike previous CD methods in VLMs that corrupt a fixed modality, AVCD leverages attention distributions to dynamically identify less dominant modalities and applies attentive masking to generate perturbed output logits. To support CD in a trimodal setting, we also reformulate the original CD framework to jointly handle audio, visual, and textual inputs. Finally, to improve efficiency, we introduce entropy-guided adaptive decoding, which selectively skips unnecessary decoding steps based on the model's confidence in its predictions. Extensive experiments demonstrate that AVCD consistently outperforms existing decoding methods. Especially, on the AVHBench dataset, it improves accuracy by 2% for VideoLLaMA2 and 7% for video-SALMONN, demonstrating strong robustness and generalizability. Our code is available at https://github.com/kaistmm/AVCD.

cs.CV↗

arXiv2025

Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models

The goal of this work is to enhance balanced multimodal understanding in audio-visual large language models (AV-LLMs) by addressing modality bias without additional training. In current AV-LLMs, audio and video features are typically processed jointly in the decoder. While this strategy facilitates unified multimodal understanding, it may introduce modality bias, where the model tends to over-rely on one modality due to imbalanced training signals. To mitigate this, we propose Fork-Merge Decoding (FMD), a simple yet effective inference-time strategy that requires no additional training or architectural modifications. FMD first performs modality-specific reasoning by processing audio-only and video-only inputs through the early decoder layers (fork), and then merges the resulting hidden states for joint reasoning in the remaining layers (merge). This separation allows each modality to be emphasized in the early stages while encouraging balanced contributions during integration. We validate our method on three representative AV-LLMs-VideoLLaMA2, video-SALMONN, and Qwen2.5-Omni-using three benchmark datasets. Experimental results show consistent gains in audio, video, and audio-visual reasoning tasks, highlighting the effectiveness of inference-time interventions for robust and efficient multimodal understanding.

cs.CV↗

arXiv2025

InfiniteAudio: Infinite-Length Audio Generation with Consistency

This paper presents InfiniteAudio, a simple yet effective strategy for generating infinite-length audio using diffusion-based text-to-audio methods. Current approaches face memory constraints because the output size increases with input length, making long duration generation challenging. A common workaround is to concatenate short audio segments, but this often leads to inconsistencies due to the lack of shared temporal context. To address this, InfiniteAudio integrates seamlessly into existing pipelines without additional training. It introduces two key techniques: FIFO sampling, a first-in, first-out inference strategy with fixed-size inputs, and curved denoising, which selectively prioritizes key diffusion steps for efficiency. Experiments show that InfiniteAudio achieves comparable or superior performance across all metrics. Audio samples are available on our project page.

eess.AS↗

arXiv2025

SEED: Speaker Embedding Enhancement Diffusion Model

A primary challenge when deploying speaker recognition systems in real-world applications is performance degradation caused by environmental mismatch. We propose a diffusion-based method that takes speaker embeddings extracted from a pre-trained speaker recognition model and generates refined embeddings. For training, our approach progressively adds Gaussian noise to both clean and noisy speaker embeddings extracted from clean and noisy speech, respectively, via forward process of a diffusion model, and then reconstructs them to clean embeddings in the reverse process. While inferencing, all embeddings are regenerated via diffusion process. Our method needs neither speaker label nor any modification to the existing speaker recognition pipeline. Experiments on evaluation sets simulating environment mismatch scenarios show that our method can improve recognition accuracy by up to 19.6% over baseline models while retaining performance on conventional scenarios. We publish our code here https://github.com/kaistmm/seed-pytorch

eess.AS↗

arXiv2025

From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech

The objective of this study is to generate high-quality speech from silent talking face videos, a task also known as video-to-speech synthesis. A significant challenge in video-to-speech synthesis lies in the substantial modality gap between silent video and multi-faceted speech. In this paper, we propose a novel video-to-speech system that effectively bridges this modality gap, significantly enhancing the quality of synthesized speech. This is achieved by learning of hierarchical representations from video to speech. Specifically, we gradually transform silent video into acoustic feature spaces through three sequential stages -- content, timbre, and prosody modeling. In each stage, we align visual factors -- lip movements, face identity, and facial expressions -- with corresponding acoustic counterparts to ensure the seamless transformation. Additionally, to generate realistic and coherent speech from the visual representations, we employ a flow matching model that estimates direct trajectories from a simple prior distribution to the target speech distribution. Extensive experiments demonstrate that our method achieves exceptional generation quality comparable to real utterances, outperforming existing methods by a significant margin.

eess.AS↗

arXiv2024

VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis

We present VoiceDiT, a multi-modal generative model for producing environment-aware speech and audio from text and visual prompts. While aligning speech with text is crucial for intelligible speech, achieving this alignment in noisy conditions remains a significant and underexplored challenge in the field. To address this, we present a novel audio generation pipeline named VoiceDiT. This pipeline includes three key components: (1) the creation of a large-scale synthetic speech dataset for pre-training and a refined real-world speech dataset for fine-tuning, (2) the Dual-DiT, a model designed to efficiently preserve aligned speech information while accurately reflecting environmental conditions, and (3) a diffusion-based Image-to-Audio Translator that allows the model to bridge the gap between audio and image, facilitating the generation of environmental sound that aligns with the multi-modal prompts. Extensive experimental results demonstrate that VoiceDiT outperforms previous models on real-world datasets, showcasing significant improvements in both audio quality and modality integration.

eess.AS↗

arXiv2024

FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching

This work proposes an efficient method to enhance the quality of corrupted speech signals by leveraging both acoustic and visual cues. While existing diffusion-based approaches have demonstrated remarkable quality, their applicability is limited by slow inference speeds and computational complexity. To address this issue, we present FlowAVSE which enhances the inference speed and reduces the number of learnable parameters without degrading the output quality. In particular, we employ a conditional flow matching algorithm that enables the generation of high-quality speech in a single sampling step. Moreover, we increase efficiency by optimizing the underlying U-net architecture of diffusion-based systems. Our experiments demonstrate that FlowAVSE achieves 22 times faster inference speed and reduces the model size by half while maintaining the output quality. The demo page is available at: https://cyongong.github.io/FlowAVSE.github.io/

eess.AS↗

arXiv2023

Seeing Through the Conversation: Audio-Visual Speech Separation based on Diffusion Model

The objective of this work is to extract target speaker's voice from a mixture of voices using visual cues. Existing works on audio-visual speech separation have demonstrated their performance with promising intelligibility, but maintaining naturalness remains a challenge. To address this issue, we propose AVDiffuSS, an audio-visual speech separation model based on a diffusion mechanism known for its capability in generating natural samples. For an effective fusion of the two modalities for diffusion, we also propose a cross-attention-based feature fusion mechanism. This mechanism is specifically tailored for the speech domain to integrate the phonetic information from audio-visual correspondence in speech generation. In this way, the fusion process maintains the high temporal resolution of the features, without excessive computational requirements. We demonstrate that the proposed framework achieves state-of-the-art results on two benchmarks, including VoxCeleb2 and LRS3, producing speech with notably better naturalness.

eess.AS↗

arXiv2023

TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning

The goal of this work is Active Speaker Detection (ASD), a task to determine whether a person is speaking or not in a series of video frames. Previous works have dealt with the task by exploring network architectures while learning effective representations has been less explored. In this work, we propose TalkNCE, a novel talk-aware contrastive loss. The loss is only applied to part of the full segments where a person on the screen is actually speaking. This encourages the model to learn effective representations through the natural correspondence of speech and facial movements. Our loss can be jointly optimized with the existing objectives for training ASD models without the need for additional supervision or training data. The experiments demonstrate that our loss can be easily integrated into the existing ASD frameworks, improving their performance. Our method achieves state-of-the-art performances on AVA-ActiveSpeaker and ASW datasets.

cs.CV↗