Related papers: PRISM: Probability Reallocation with In-Span Maski…
Based on the success of large-scale visual foundation models like CLIP in various downstream tasks, this paper initially attempts to explore their impact on Long-Tailed Semi-Supervised Learning (LTSSL) by employing the foundation model with…
Regressing 3D rotations of objects from 2D images is a crucial yet challenging task, with broad applications in autonomous driving, virtual reality, and robotic control. Existing rotation regression models often rely on large amounts of…
Hallucination, where models generate fluent text unsupported by visual evidence, remains a major flaw in vision-language models and is particularly critical in sign language translation (SLT). In SLT, meaning depends on precise grounding in…
Despite showing increasingly human-like abilities, large language models (LLMs) often struggle with factual inaccuracies, i.e. "hallucinations", even when they hold relevant knowledge. To address these hallucinations, current approaches…
Vision Language Models (VLMs) are becoming increasingly integral to multimedia understanding; however, they often struggle with domain-specific video classification tasks, particularly in cases with limited data. This stems from a critical…
Hallucination in large language models (LLMs) has been widely studied in recent years, with progress in both detection and mitigation aimed at improving truthfulness. Yet, a critical side effect remains largely overlooked: enhancing…
Large Language Models suffer from hallucination, generating plausible yet factually incorrect content. Current mitigation strategies focus on post-generation correction, which is computationally expensive and fails to prevent unreliable…
Training object detection models usually requires instance-level annotations, such as the positions and labels of all objects present in each image. Such supervision is unfortunately not always available and, more often, only image-level…
Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical. Interestingly, we discover a counter-intuitive trade-off phenomenon that enhancing an LLM's privacy awareness through Supervised Fine-Tuning (SFT)…
Confidence alone is often misleading in hyperspectral image classification, as models tend to mistake high predictive scores for correctness while lacking awareness of uncertainty. This leads to confirmation bias, especially under sparse…
Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the…
Large Language Models (LLMs) often struggle to align their responses with objective facts, resulting in the issue of factual hallucinations, which can be difficult to detect and mislead users without relevant knowledge. Although…
Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs). Standard approaches treat the LLM as the policy and apply RL directly over the full vocabulary space. However, this…
Contrastive Language-Image Pre-training (CLIP) is a widely used multimodal model that aligns text and image representations through large-scale training. While it performs strongly on zero-shot and few-shot tasks, its robustness to…
As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for…
Automatic detection of speaker confidence is critical for adaptive computing but remains constrained by limited labelled data and the subjectivity of paralinguistic annotations. This paper proposes a semi-supervised hybrid framework that…
Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assumed to improve factual correctness. However, how the parameter-efficient fine-tuning methods affect…
Hallucination, the generation of factually incorrect content, is a growing challenge in Large Language Models (LLMs). Existing detection and mitigation methods are often isolated and insufficient for domain-specific needs, lacking a…
Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer…
Large language models (LLMs) have demonstrated remarkable performance in text generation and knowledge-intensive question answering. Nevertheless, they are prone to producing hallucinated content, which severely undermines their reliability…