5 accepted papers
Dynamic obstacle avoidance is a challenging problem in robotic control, with many algorithms developed to balance efficiency and real-time performance. Existing resolved-rate motion control (RRMC) methods formulate obstacle avoidance as a quadratic programming (QP) problem. However, the lack of dire
Long-context large language models (LLMs) have achieved remarkable advancements, driven by techniques like Rotary Position Embedding (RoPE) (Su et al., 2023) and its extensions (Chen et al., 2023; Liu et al., 2024c; Peng et al., 2023). By adjusting RoPE parameters and incorporating training data wit…
Image aesthetic assessment is an important issue in multimedia, but most existing studies employ supervised learning methods that rely on large-scale annotated data. However, aesthetic scoring annotations are difficult to obtain in large quantities. Therefore, this paper explores zero-shot image aes…
LLMs acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax. To investigate alignment tax, we conducted experiments with existing RLHF algor…
Previous researches of sketches often considered sketches in pixel format and leveraged CNN based models in the sketch understanding. Fundamentally, a sketch is stored as a sequence of data points, a vector format representation, rather than the photo-realistic image of pixels. SketchRNN studied a g…