8 accepted papers
Since high-fidelity reference images are difficult to obtain in real underwater scenes, most deep models trained by synthetic paired data cannot match real-world data exactly. In this paper, we propose an unsupervised training framework for underwater image enhancement (UIE) by leveraging an iterati
The development of bio-inspired jellyfish robots holds significant benefits for autonomous aquatic systems due to jellyfish’s efficient water jet propulsion. However, the current design of jellyfish robots still faces challenges in balancing high biological fidelity with the demands of lightweight, …
Despite their impressive capacities, Large language models (LLMs) often struggle with the hallucination issue of generating inaccurate or fabricated content even when they possess correct knowledge. In this paper, we extend the exploration of the correlation between hidden-state prediction changes a…
Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially biased outputs. Recent studies have mainly addressed this problem by prompting LLMs to behave ethically, but this approach…
As the capabilities of diffusion-based audio generation models advance, intellectual property protection for both generated audio and model weights becomes important. However, current audio watermarking methods mainly integrate separate encode and decode modules to watermark the generated audio, whi…
Existing NAS methods for semantic segmentation typically apply uniform optimization to all candidate networks (paths) within a one-shot supernet. However, the concurrent existence of both promising and suboptimal paths often results in inefficient weight updates and gradient conflicts. This issue is…
Machine unlearning provides users with the right to remove their privacy data from a well-trained model. Existing approaches of machine unlearning mainly focus on exploring data removing within supervised learning (SL) tasks. However, weakly supervised learning (WSL) is more applicable to real-world…
Predicting human motion behavior in a crowd is important for many applications, ranging from the natural navigation of autonomous vehicles to intelligent security systems of video surveillance. All the previous works model and predict the trajectory with a single resolution, which is relatively inef…