Zobrazeno 1 - 10
of 1 958
pro vyhledávání: '"A. Kumaraguru"'
Autor:
Wijesiriwardene, Thilini, Wickramarachchi, Ruwan, Vennam, Sreeram, Jain, Vinija, Chadha, Aman, Das, Amitava, Kumaraguru, Ponnurangam, Sheth, Amit
Making analogies is fundamental to cognition. Proportional analogies, which consist of four terms, are often used to assess linguistic and cognitive abilities. For instance, completing analogies like "Oxygen is to Gas as is to " requir
Externí odkaz:
http://arxiv.org/abs/2412.00869
Autor:
Kolipaka, Varshita, Sinha, Akshit, Mishra, Debangan, Kumar, Sumit, Arun, Arvindh, Goel, Shashwat, Kumaraguru, Ponnurangam
Graph Neural Networks (GNNs) are increasingly being used for a variety of ML applications on graph data. Because graph data does not follow the independently and identically distributed (i.i.d.) assumption, adversarial manipulations or incorrect data
Externí odkaz:
http://arxiv.org/abs/2412.00789
Thinking Tokens (TT) have been proposed as an unsupervised method to facilitate reasoning in language models. However, despite their conceptual appeal, our findings show that TTs marginally improves performance and consistently underperforms compared
Externí odkaz:
http://arxiv.org/abs/2411.11371
Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). In this paper, we propose a novel framework that integrates Knowledge D
Externí odkaz:
http://arxiv.org/abs/2411.12174
We present a method to compress the final linear layer of language models, reducing memory usage by up to 3.4x without significant performance loss. By grouping tokens based on Byte Pair Encoding (BPE) merges, we prevent materialization of the memory
Externí odkaz:
http://arxiv.org/abs/2411.06371
Autor:
Joshi, Swarang, Mavani, Siddharth, Alex, Joel, Negi, Arnav, Mishra, Rahul, Kumaraguru, Ponnurangam
Misinformation undermines individual knowledge and affects broader societal narratives. Despite growing interest in the research community in multi-modal misinformation detection, existing methods exhibit limitations in capturing semantic cues, key r
Externí odkaz:
http://arxiv.org/abs/2410.15517
Autor:
Kumaru, Neha, Gupta, Garvit, Mongia, Shreyas, Singh, Shubham, Kumaraguru, Ponnurangam, Buduru, Arun Balaji
The use of Social media to share content is on a constant rise. One of the capsize effect of information sharing on Social media includes the spread of sensitive information on the public domain. With the digital gadget market becoming highly competi
Externí odkaz:
http://arxiv.org/abs/2409.04880
Autor:
Balappanawar, Ishwar B, Chamoli, Ashmit, Wickramarachchi, Ruwan, Mishra, Aditya, Kumaraguru, Ponnurangam, Sheth, Amit P.
Distracted driving is a leading cause of road accidents globally. Identification of distracted driving involves reliably detecting and classifying various forms of driver distraction (e.g., texting, eating, or using in-car devices) from in-vehicle ca
Externí odkaz:
http://arxiv.org/abs/2408.16621
Most existing Question Answering Datasets (QuADs) primarily focus on factoid-based short-context Question Answering (QA) in high-resource languages. However, the scope of such datasets for low-resource languages remains limited, with only a few works
Externí odkaz:
http://arxiv.org/abs/2408.10604
Autor:
Kavathekar, Ishan, Rani, Anku, Chamoli, Ashmit, Kumaraguru, Ponnurangam, Sheth, Amit, Das, Amitava
The widespread adoption of Large Language Models (LLMs) and awareness around multilingual LLMs have raised concerns regarding the potential risks and repercussions linked to the misapplication of AI-generated text, necessitating increased vigilance.
Externí odkaz:
http://arxiv.org/abs/2407.15694