Zobrazeno 1 - 10
of 1 634
pro vyhledávání: '"MA Huimin"'
Large language models (LLMs) have demonstrated limitations in handling combinatorial optimization problems involving long-range reasoning, partially due to causal hallucinations and huge search space. As for causal hallucinations, i.e., the inconsist
Externí odkaz:
http://arxiv.org/abs/2410.01696
In this paper, we utilize information-theoretic metrics like matrix entropy and mutual information to analyze supervised learning. We explore the information content of data representations and classification head weights and their information interp
Externí odkaz:
http://arxiv.org/abs/2409.16767
Chain-based reasoning methods like chain of thought (CoT) play a rising role in solving reasoning tasks for large language models (LLMs). However, the causal illusions between \textit{a step of reasoning} and \textit{corresponding state transitions}
Externí odkaz:
http://arxiv.org/abs/2409.17174
Directed grey-box fuzzing (DGF) aims to discover vulnerabilities in specific code areas efficiently. Distance metric, which is used to measure the quality of seed in DGF, is a crucial factor in affecting the fuzzing performance. Despite distance metr
Externí odkaz:
http://arxiv.org/abs/2409.12701
Micro-expressions are involuntary facial movements that cannot be consciously controlled, conveying subtle cues with substantial real-world applications. The analysis of micro-expressions generally involves two main tasks: spotting micro-expression i
Externí odkaz:
http://arxiv.org/abs/2409.09707
In the domain of Camouflaged Object Segmentation (COS), despite continuous improvements in segmentation performance, the underlying mechanisms of effective camouflage remain poorly understood, akin to a black box. To address this gap, we present the
Externí odkaz:
http://arxiv.org/abs/2408.12086
In this paper, we use matrix information theory as an analytical tool to analyze the dynamics of the information interplay between data representations and classification head vectors in the supervised learning process. Specifically, inspired by the
Externí odkaz:
http://arxiv.org/abs/2406.03999
Modern diffusion-based image generative models have made significant progress and become promising to enrich training data for the object detection task. However, the generation quality and the controllability for complex scenes containing multi-clas
Externí odkaz:
http://arxiv.org/abs/2405.15199
Remote photoplethysmography (rPPG) is a non-contact method for detecting physiological signals from facial videos, holding great potential in various applications such as healthcare, affective computing, and anti-spoofing. Existing deep learning meth
Externí odkaz:
http://arxiv.org/abs/2404.06483
Large-scale text-to-image diffusion models have achieved great success in synthesizing high-quality and diverse images given target text prompts. Despite the revolutionary image generation ability, current state-of-the-art models still struggle to de
Externí odkaz:
http://arxiv.org/abs/2403.16954