Zobrazeno 1 - 10
of 4 209
pro vyhledávání: '"Chen Jingjing"'
Large pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated excellent zero-shot generalizability across various downstream tasks. However, recent studies have shown that the inference performance of CLIP can be greatly degraded by
Externí odkaz:
http://arxiv.org/abs/2411.13136
Fine-tuning multimodal large language models (MLLMs) presents significant challenges, including a reliance on high-level visual features that limits fine-grained detail comprehension, and data conflicts that arise from task complexity. To address the
Externí odkaz:
http://arxiv.org/abs/2411.12787
Given the potential applications of generating recipes from food images, this area has garnered significant attention from researchers in recent years. Existing works for recipe generation primarily utilize a two-stage training method, first generati
Externí odkaz:
http://arxiv.org/abs/2411.08715
Open-set single-source domain generalization aims to use a single-source domain to learn a robust model that can be generalized to unknown target domains with both domain shifts and label shifts. The scarcity of the source domain and the unknown data
Externí odkaz:
http://arxiv.org/abs/2411.02920
Accurate short-term forecasts of passenger flow in metro systems under delay conditions are crucial for emergency response and service recovery, which pose significant challenges and are currently under-researched. Due to the rare occurrence of delay
Externí odkaz:
http://arxiv.org/abs/2410.15111
Autor:
Chen, Jingjing, Afzelius, Mikael
Long-duration and efficient quantum memories for photons are key components of quantum repeater and network applications. To achieve long duration storage in atomic systems, a short-lived optical coherence can be mapped into a long-lived spin coheren
Externí odkaz:
http://arxiv.org/abs/2410.14551
Data is crucial for robotic manipulation, as it underpins the development of robotic systems for complex tasks. While high-quality, diverse datasets enhance the performance and adaptability of robotic manipulation policies, collecting extensive exper
Externí odkaz:
http://arxiv.org/abs/2409.19917
DelayPTC-LLM: Metro Passenger Travel Choice Prediction under Train Delays with Large Language Models
Train delays can propagate rapidly throughout the Urban Rail Transit (URT) network under networked operation conditions, posing significant challenges to operational departments. Accurately predicting passenger travel choices under train delays can p
Externí odkaz:
http://arxiv.org/abs/2410.00052
Recently, Multimodal Large Language Models (MLLMs) have sparked great research interests owing to their exceptional content-reasoning and instruction-following capabilities. To effectively instruct an MLLM, in addition to conventional language expres
Externí odkaz:
http://arxiv.org/abs/2409.16723