17 accepted papers
In endoscopic submucosal dissection, endoscopic forceps is subject to stringent requirements regarding flexibility, miniaturization, and mechanical performance. However, most existing endoscopic forceps suffer from insufficient clamping force and limited opening angle. In this letter, we analyze the
Large language models (LLMs) have been widely deployed across numerous fields. Reinforcement Learning from Human Feedback (RLHF) leverages reward models (RMs) as proxies for human preferences to align LLM behaviors with human values, making the accuracy, reliability, and interpretability of RMs crit
Personalized image preference assessment aims to evaluate an individual user's image preferences by relying only on a small set of reference images as prior information. Existing methods mainly focus on general preference assessment, training models with large-scale data to tackle well-defined task…
Text-to-image generation has advanced rapidly, yet it still struggles to capture the nuanced user preferences. Existing approaches typically rely on multimodal large language models to infer user preferences, but the derived prompts or latent codes rarely reflect them faithfully, leading to suboptim
Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. In scalable applications, fine-tuning-based methods are time-consuming to precisely erase multipl…
Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have failed to evolve in parallel. This study reveals that human preference reward models fine-tuned based on CLIP and BLIP arch…
Large Vision-Language Models (LVLMs) are susceptible to hallucinations, where generated responses seem semantically plausible yet exhibit little or no relevance to the input image. Previous studies reveal that this issue primarily stems from LVLMs' over-reliance on language priors while disregarding…
This work explores sequential model editing in large language models (LLMs), a critical task that involves modifying internal knowledge within LLMs continuously through multi-round editing, each incorporating updates or corrections to adjust the model’s outputs without the need for costly retraining…
Process-driven dialogue systems, which operate under strict predefined process constraints, are essential in customer service and equipment maintenance scenarios. Although Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, they still struggle to solve these strict…
Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demonstrated promise in this domain by extracting interpretable and monosemantic features. However, prior works primarily focu
Nowadays, gastrointestinal cancer has widely impacted people's health worldwide due to its high mortality rate. Early treatment of gastrointestinal cancer by endoscopic procedure can greatly increase survival rates of patients. Nevertheless, current flexible endoscopic instruments lack of degree of
Endoscopic robot has garnered significant attention for its ability to offer auxiliary traction and precise maneuverability. However, the low stiffness of its insertion tube makes it susceptible to deformation, which poses great challenges for precise control. Existing variable stiffness technologie
Existing sentiment analysis models have achieved great advances with the help of sufficient sentiment annotations. Unfortunately, many languages do not have sufficient sentiment corpus. To this end, recent studies have proposed cross-lingual sentiment analysis to transfer sentiment analysis models f…
Fine-tuning pre-trained models for downstream tasks is mainstream in deep learning. However, the pre-trained models are limited to be fine-tuned by data from a specific modality. For example, as a visual model, DenseNet cannot directly take the textual data as its input. Hence, although the large pr…
Videos flow as the mixture of language, acoustic, and vision modalities. A thorough video understanding needs to fuse time-series data of different modalities for prediction. Due to the variable receiving frequency for sequences from each modality, there usually exists inherent asynchrony across the…
Exploiting photo-realistic synthetic data to train semantic segmentation models has received increasing attention over the past years. However, the domain mismatch between synthetic and real images will cause a significant performance drop when the model trained with synthetic images is directly app…
This paper investigates the physical layer security for a buffer-aided cooperative cognitive radio network in the presence of an eavesdropper, wherein the relay is equipped with a buffer so that it can store packets received from secondary source. Multiple primary users (PUs) locate in the transmiss…