相关论文: Detecting and Mitigating Insertion Hallucination i…

Large Vision-Language Models (LVLMs) with discrete image tokenizers unify multimodal representations by encoding visual inputs into a finite set of tokens. Despite their effectiveness, we find that these models still hallucinate…

While large language models have transformed how we interact with AI systems, they have a critical weakness: they confidently state false information that sounds entirely plausible. This "hallucination" problem has become a major barrier to…

Generative AI increasingly supports scientific inference, from protein structure prediction to weather forecasting. Yet its distinctive failure mode, hallucination, raises epistemic alarm bells. I argue that this failure mode can be…

The widespread adoption of large language and vision models in real-world applications has made urgent the need to address hallucinations -- instances where models produce incorrect or nonsensical outputs. These errors can propagate…

Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated content contradicting visual inputs. Existing hallucination mitigation methods either incur…

Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonly known as ``hallucination''. In this work, we propose a…

While large vision-language models (LVLMs) have demonstrated impressive capabilities in interpreting multi-modal contexts, they invariably suffer from object hallucinations (OH). We introduce HALC, a novel decoding algorithm designed to…

Empowered by the large-scale pretrained language models, existing dialogue systems have demonstrated impressive performance conducting fluent and natural-sounding conversations. However, they are still plagued by the hallucination problem,…

As generative AI systems become competent and democratized in science, business, and government, deeper insight into their failure modes now poses an acute need. The occasional volatility in their behavior, such as the propensity of…

Multimodal large language models achieve strong performance across diverse tasks but remain prone to hallucinations, where outputs are not grounded in visual inputs. This issue can be attributed to two main biases: text-visual bias, the…

While video-to-audio generation has achieved remarkable progress in semantic and temporal alignment, most existing studies focus solely on these aspects, paying limited attention to the spatial perception and immersive quality of the…

Visual hallucination (VH) means that a multi-modal LLM (MLLM) imagines incorrect details about an image in visual question answering. Existing studies find VH instances only in existing image datasets, which results in biased understanding…

Recent advances in latent diffusion-based generative models for portrait image animation, such as Hallo, have achieved impressive results in short-duration video synthesis. In this paper, we present updates to Hallo, introducing several…

Hallucination remains a major challenge for the safe and trustworthy deployment of large language models (LLMs) in factual content generation. Prior work has explored confidence estimation as an effective approach to hallucination…

Despite remarkable progress in image quality and prompt fidelity, text-to-image (T2I) diffusion models continue to exhibit persistent "hallucinations", where generated content subtly or significantly diverges from the intended prompt…

Faithfulness hallucinations in VQA occur when vision-language models produce fluent yet visually ungrounded answers, severely undermining their reliability in safety-critical applications. Existing detection methods mainly fall into two…

Diffusion models have significantly advanced generative AI, but they encounter difficulties when generating complex combinations of multiple objects. As the final result heavily depends on the initial seed, accurately ensuring the desired…

Generative AI (GenAI) is driving the intelligence of wireless communications. Due to data limitations, random generation, and dynamic environments, GenAI may generate channel information or optimization strategies that violate physical laws…

Large Vision-Language Models (LVLMs) have shown remarkable performance on a wide range of vision-language tasks. Despite this progress, they are still prone to hallucination, generating responses that are inconsistent with visual content.…

This work introduces a new task, text-conditioned selective video-to-audio (V2A) generation, which produces only the user-intended sound from a multi-object video. This capability is especially crucial in multimedia production, where audio…