14 accepted papers
Machine unlearning has emerged as a promising approach to remove specific knowledge from large language models (LLMs), especially for safety-critical applications. However, existing representation-based methods lack guidance for selecting representation locations to unlearn (RMU), thus lacking preci
Large language models (LLMs) have demonstrated remarkable capabilities across a variety of domains. However, their applications in cryptography, which serve as a foundational pillar of cybersecurity, remain largely unexplored. To address this gap, we build \textbf{AICrypto}, a comprehensive benchmar…
Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and category-relevant information, limiting both generalization and rapid adapt
The Segment Anything Model 2 (SAM2) has emerged as a foundation model for universal segmentation. Owing to its generalizable visual representations, SAM2 has been successfully applied to various downstream tasks. However, extending SAM2 to the RGB-D video salient object detection (RGB-D VSOD) task e
Recently segment anything model (SAM) has attracted widespread concerns, and it is often treated as a vision foundation model for universal segmentation. Some researchers have attempted to directly apply the foundation model to the RGB-D video salient object detection (RGB-D VSOD) task, which often
Motion expression video segmentation aims to segment objects based on input motion descriptions. Compared with traditional referring video object segmentation, it focuses on motion and multi-object expressions and is more challenging. Previous works achieved it by simply injecting text information i…
Temporal Knowledge Graphs (TKGs) are being widely explored to predict the future for they record multi-relational knowledge and the happening time of real-life facts. Existing works learn sequential patterns to infer the future from past facts in TKGs for predictions. Although achieving promising re…
Temporal Knowledge Graphs (TKGs) represent real-life facts using entities, relational types, and timestamps where relational types state the semantic scenario of facts. Current methods learn embeddings by merging facts of multiple types (e.g. sport and family) for predictions. Such embeddings associ…
With the rapid advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Prior research has exposed VLMs’ vulnerability to jailbreak attacks, where carefully crafted inputs can lead the model to produce content that violates ethical and…
Temporal Knowledge Graph (TKG) reasoning aims to predict facts at specific query timestamps using historical data. The main challenge is accurately modeling historical information for future queries. Previous approaches have primarily focused on global patterns and recent trends, but often overlooke…
The recent imaging technology Quad Bayer CFA brings better imaging PSNR and higher visual quality compared to traditional Bayer CFA, but also serious challenges for demosaicing and denoising during the ISP pipeline. In this paper, we propose a novel dual encoder network, namely DRNet, to achieve joi…
Knowledge graph completion (KGC) aims to infer missing information in incomplete knowledge graphs (KGs). Most previous works only consider the transductive scenario where entities are existing in KGs, which cannot work effectively for the inductive scenario containing emerging entities. Recently som…
Image captioning is a challenging computer vision task, which aims to generate a natural language description of an image. Most recent researches follow the encoder-decoder framework which depends heavily on the previous generated words for the current prediction. Such methods can not effectively ta…
Joint extraction of entities and relations is an important task in natural language processing (NLP), which aims to capture all relational triplets from plain texts. This is a big challenge due to some of the triplets extracted from one sentence may have overlapping entities. Most existing methods p…