Zobrazeno 1 - 10
of 4 360
pro vyhledávání: '"A. Vosoughi"'
In the field of vision-language contrastive learning, models such as CLIP capitalize on matched image-caption pairs as positive examples and leverage within-batch non-matching pairs as negatives. This approach has led to remarkable outcomes in zero-s
Externí odkaz:
http://arxiv.org/abs/2407.01408
Autor:
Guo, Xiaobo, Vosoughi, Soroush
Large Language Models (LLMs) have shown remarkable capabilities in zero-shot learning applications, generating responses to queries using only pre-training information without the need for additional fine-tuning. This represents a significant departu
Externí odkaz:
http://arxiv.org/abs/2406.15981
LLM-as-a-Judge offers a promising alternative to human judges across various tasks, yet inherent biases, particularly position bias - a systematic preference for answers based on their position in the prompt - compromise its effectiveness. Our study
Externí odkaz:
http://arxiv.org/abs/2406.07791
Autor:
Guo, Xiaobo, Vosoughi, Soroush
The rapid proliferation of online content necessitates effective summarization methods, among which dynamic aspect-based summarization stands out. Unlike its traditional counterpart, which assumes a fixed set of known aspects, this approach adapts to
Externí odkaz:
http://arxiv.org/abs/2406.03479
Mental manipulation, a significant form of abuse in interpersonal conversations, presents a challenge to identify due to its context-dependent and often subtle nature. The detection of manipulative language is essential for protecting potential victi
Externí odkaz:
http://arxiv.org/abs/2405.16584
Autor:
Vladimirova, Anastasiia, Arregui, Guillermo, Lepeshov, Sergei, Rosiek, Christian Anker, Lahijani, Babak Vosoughi, Stobbe, Søren
We present a theoretical study on photonic topological crystals whose symmetry is governed by quantum valley-Hall topological insulators and whose propagating edge modes are strongly confined due to bowtie geometries. Dielectric bowtie structures exp
Externí odkaz:
http://arxiv.org/abs/2404.05721
The capability of intelligent models to extrapolate and comprehend changes in object states is a crucial yet demanding aspect of AI research, particularly through the lens of human interaction in real-world settings. This task involves describing com
Externí odkaz:
http://arxiv.org/abs/2402.17128
Autor:
Guo, Xiaobo, Vosoughi, Soroush
Aspect-based summarization has seen significant advancements, especially in structured text. Yet, summarizing disordered, large-scale texts, like those found in social media and customer feedback, remains a significant challenge. Current research lar
Externí odkaz:
http://arxiv.org/abs/2402.10554
Conventional audio classification relied on predefined classes, lacking the ability to learn from free-form text. Recent methods unlock learning joint audio-text embeddings from raw audio-text pairs describing audio in natural language. Despite recen
Externí odkaz:
http://arxiv.org/abs/2401.04935
Autor:
Tang, Yunlong, Bi, Jing, Xu, Siting, Song, Luchuan, Liang, Susan, Wang, Teng, Zhang, Daoan, An, Jie, Lin, Jingyang, Zhu, Rongyi, Vosoughi, Ali, Huang, Chao, Zhang, Zeliang, Liu, Pinxin, Feng, Mingqian, Zheng, Feng, Zhang, Jianguo, Luo, Ping, Luo, Jiebo, Xu, Chenliang
With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly. Given the remarkable capabilities of large language models (LLMs) in langua
Externí odkaz:
http://arxiv.org/abs/2312.17432