相关论文: Adaptive vector steering: A training-free, layer-w…

Environmental noises and reverberation have a detrimental effect on the performance of automatic speech recognition (ASR) systems. Multi-condition training of neural network-based acoustic models is used to deal with this problem, but it…

There has been significant research on developing pretrained transformer architectures for multimodal-to-text generation tasks. Albeit performance improvements, such models are frequently overparameterized, hence suffer from hallucination…

Multimodal large language models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet they remain highly susceptible to hallucinations, producing content that is fluent but inconsistent with visual evidence.…

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…

Large Audio Language Models (LALMs) demonstrate impressive general audio understanding, but once deployed, they are static and fail to improve with new real-world audio data. As traditional supervised fine-tuning is costly, we introduce a…

Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a persistent challenge. Although recent agentic approaches incorporate tool use, they often…

Vision Language Models (VLMs) show impressive capabilities in integrating and reasoning with both visual and language data. But these models make mistakes. A common finding -- similar to LLMs -- is their tendency to hallucinate, i.e.,…

Steering methods have emerged as effective and targeted tools for guiding large language models' (LLMs) behavior without modifying their parameters. Multimodal large language models (MLLMs), however, do not currently enjoy the same suite of…

Object hallucination in Large Vision-Language Models (LVLMs) significantly impedes their real-world applicability. As the primary component for accurately interpreting visual information, the choice of visual encoder is pivotal. We…

Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues. The effectiveness of audio-visual learning critically depends on achieving accurate cross-modal alignment…

Large audio-language models (LALMs) enhance traditional large language models by integrating audio perception capabilities, allowing them to tackle audio-related tasks. Previous research has primarily focused on assessing the performance of…

Hallucination has been a significant impediment to the development and application of current Large Vision-Language Models (LVLMs). To mitigate hallucinations, one intuitive and effective way is to directly increase attention weights to…

Automatic speech recognition (ASR) has reached a level of accuracy in recent years, that even outperforms humans in transcribing speech to text. Nevertheless, all current ASR approaches show a certain weakness against ambient noise. To…

We present an approach to Audio-Visual Speech Recognition that builds on a pre-trained Whisper model. To infuse visual information into this audio-only model, we extend it with an AV fusion module and LoRa adapters, one of the most…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, yet they remain susceptible to hallucinations -- generating content that is factually incorrect, unfaithful to provided…

Hallucinations remain a significant challenge in current Generative AI models, undermining trust in AI systems and their reliability. This study investigates how orchestrating multiple specialized Artificial Intelligent Agents can help…

In audio-visual navigation (AVN), an intelligent agent needs to navigate to a constantly sound-making object in complex 3D environments based on its audio and visual perceptions. While existing methods attempt to improve the navigation…

Due to the unidirectional masking mechanism, Decoder-Only models propagate information from left to right. LVLMs (Large Vision-Language Models) follow the same architecture, with visual information gradually integrated into semantic…

Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding.However, hallucination, where the model generates plausible yet incorrect outputs, persists as a significant and under-addressed challenge in…

The Audio-Visual Segmentation (AVS) task aims to segment sounding objects in the visual space using audio cues. However, in this work, it is recognized that previous AVS methods show a heavy reliance on detrimental segmentation preferences…