Zobrazeno 1 - 10
of 7 515
pro vyhledávání: '"P. Bajpai"'
Autor:
Bajpai, Ashutosh, Chakraborty, Tanmoy
The unwavering disparity in labeled resources between resource-rich languages and those considered low-resource remains a significant impediment for Large Language Models (LLMs). Recent strides in cross-lingual in-context learning (X-ICL), mainly thr
Externí odkaz:
http://arxiv.org/abs/2412.08090
Autor:
Weisz, Justin D., Kumar, Shraddha, Muller, Michael, Browne, Karen-Ellen, Goldberg, Arielle, Heintze, Ellice, Bajpai, Shagun
AI assistants are being created to help software engineers conduct a variety of coding-related tasks, such as writing, documenting, and testing code. We describe the use of the watsonx Code Assistant (WCA), an LLM-powered coding assistant deployed in
Externí odkaz:
http://arxiv.org/abs/2412.06603
Autor:
Sahadevan, Vijayalaxmi, Mario, Sushil, Jaiswal, Yash, Bajpai, Divyanshu, Singh, Vishal, Aggarwal, Hiralal, Suresh, Suhas, Maigur, Manjunath
Ontology-based knowledge graphs (KG) are desirable for effective knowledge management and reuse in various decision making scenarios, including design. Creating and populating extensive KG based on specific ontological models can be highly labour and
Externí odkaz:
http://arxiv.org/abs/2412.05868
In this work, we present a novel variant of the stochastic gradient descent method termed as iteratively regularized stochastic gradient descent (IRSGD) method to solve nonlinear ill-posed problems in Hilbert spaces. Under standard assumptions, we de
Externí odkaz:
http://arxiv.org/abs/2412.02397
Autor:
Imanpour, Nasrin, Bajpai, Shashwat, Ghosh, Subhankar, Sankepally, Sainath Reddy, Borah, Abhilekh, Abdullah, Hasnat Md, Kosaraju, Nishoak, Dixit, Shreyas, Aziz, Ashhar, Biswas, Shwetangshu, Jain, Vinija, Chadha, Aman, Sheth, Amit, Das, Amitava
The proliferation of AI techniques for image generation, coupled with their increasing accessibility, has raised significant concerns about the potential misuse of these images to spread misinformation. Recent AI-generated image detection (AGID) meth
Externí odkaz:
http://arxiv.org/abs/2411.16754
Autor:
Bajpai, Jitendra, Dona, Daniele
We prove a version of Jordan's classification theorem for finite subgroups of $\mathrm{GL}_{n}(K)$ that is at the same time quantitatively explicit, CFSG-free, and valid for arbitrary $K$. This is the first proof to satisfy all three properties at on
Externí odkaz:
http://arxiv.org/abs/2411.11632
Large Language Models (LLMs) have demonstrated strong performance as knowledge repositories, enabling models to understand user queries and generate accurate and context-aware responses. Extensive evaluation setups have corroborated the positive corr
Externí odkaz:
http://arxiv.org/abs/2411.10813
Autor:
Bajpai, Prajeet, Bugeaud, Yann
We establish an effective improvement on the Liouville inequality for approximation to complex non-real algebraic numbers by quadratic complex algebraic numbers.
Comment: To appear in the Canadian Mathematical Bulletin
Comment: To appear in the Canadian Mathematical Bulletin
Externí odkaz:
http://arxiv.org/abs/2411.09570
Autor:
Bajpai, Shrajal, Patra, Lakshmi Kanta
A doubly type-II censored scheme is an important sampling scheme in the life testing experiment and reliability engineering. In the present commutation, we have considered estimating ordered scale parameters of two exponential distributions based on
Externí odkaz:
http://arxiv.org/abs/2411.06888
In the usual statistical inference problem, we estimate an unknown parameter of a statistical model using the information in the random sample. A priori information about the parameter is also known in several real-life situations. One such informati
Externí odkaz:
http://arxiv.org/abs/2411.05487