Zobrazeno 1 - 10
of 17 397
pro vyhledávání: '"Ma Jing"'
Large multimodal models (LMMs) with advanced video analysis capabilities have recently garnered significant attention. However, most evaluations rely on traditional methods like multiple-choice questions in benchmarks such as VideoMME and LongVideoBe
Externí odkaz:
http://arxiv.org/abs/2411.13281
Geometric shape features have been widely used as strong predictors for image classification. Nevertheless, most existing classifiers such as deep neural networks (DNNs) directly leverage the statistical correlations between these shape features and
Externí odkaz:
http://arxiv.org/abs/2411.12201
Clinical rationales play a pivotal role in accurate disease diagnosis; however, many models predominantly use discriminative methods and overlook the importance of generating supportive rationales. Rationale distillation is a process that transfers k
Externí odkaz:
http://arxiv.org/abs/2411.07611
The advanced role-playing capabilities of Large Language Models (LLMs) have paved the way for developing Role-Playing Agents (RPAs). However, existing benchmarks, such as HPD, which incorporates manually scored character relationships into the contex
Externí odkaz:
http://arxiv.org/abs/2411.07965
Let Zn denote the additive group of residue classes modulo n. Let c(l,m,n) denote the number of cyclic subgroups of Zl *Zm *Zn. For any x > 1, we consider the asymptotic behavior of D3c(x):= \sum_{lmn\leq x} c(l,m,n), obtain an asymptotic formula by
Externí odkaz:
http://arxiv.org/abs/2411.06126
The proliferation of Internet memes in the age of social media necessitates effective identification of harmful ones. Due to the dynamic nature of memes, existing data-driven models may struggle in low-resource scenarios where only a few labeled exam
Externí odkaz:
http://arxiv.org/abs/2411.05383
Autor:
He, Yinhan, Zheng, Wendy, Zhu, Yaochen, Ma, Jing, Mishra, Saumitra, Raman, Natraj, Liu, Ninghao, Li, Jundong
Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. However, most GNNs are black-box models that lack explanations. One strategy to explain GNNs is through counterfactual explanation, which aims to find minimum
Externí odkaz:
http://arxiv.org/abs/2410.19978
The impressive performance of proprietary LLMs like GPT4 in code generation has led to a trend to replicate these capabilities in open-source models through knowledge distillation (e.g. Code Evol-Instruct). However, these efforts often neglect the cr
Externí odkaz:
http://arxiv.org/abs/2410.00558
Autor:
Ma, Jing
Graph machine learning (GML) has been successfully applied across a wide range of tasks. Nonetheless, GML faces significant challenges in generalizing over out-of-distribution (OOD) data, which raises concerns about its wider applicability. Recent ad
Externí odkaz:
http://arxiv.org/abs/2409.09858
Autor:
Ma, Jing
Causal inference has been a pivotal challenge across diverse domains such as medicine and economics, demanding a complicated integration of human knowledge, mathematical reasoning, and data mining capabilities. Recent advancements in natural language
Externí odkaz:
http://arxiv.org/abs/2409.09822