Divakar Yadav

Divakar Yadav, Jalpa Desai, Arun Kumar Yadav

One of the most pressing issues that have arisen due to the rapid growth of the Internet is known as information overloading. Simplifying the relevant information in the form of a summary will assist many people because the material on any topic is plentiful on the Internet. Manually summarising massive amounts of text is quite challenging for humans. So, it has increased the need for more complex and powerful summarizers. Researchers have been trying to improve approaches for creating summaries since the 1950s, such that the machine-generated summary matches the human-created summary. This study provides a detailed state-of-the-art analysis of text summarization concepts such as summarization approaches, techniques used, standard datasets, evaluation metrics and future scopes for research. The most commonly accepted approaches are extractive and abstractive, studied in detail in this work. Evaluating the summary and increasing the development of reusable resources and infrastructure aids in comparing and replicating findings, adding competition to improve the outcomes. Different evaluation methods of generated summaries are also discussed in this study. Finally, at the end of this study, several challenges and research opportunities related to text summarization research are mentioned that may be useful for potential researchers working in this area.

Vishal Kuber, Divakar Yadav, Arun Kr Yadav

Designing robust and accurate prediction models has been a viable research area since a long time. While proponents of a well-functioning market predictors believe that it is difficult to accurately predict market prices but many scholars disagree. Robust and accurate prediction systems will not only be helpful to the businesses but also to the individuals in making their financial investments. This paper presents an LSTM model with two different input approaches for predicting the short-term stock prices of two Indian companies, Reliance Industries and Infosys Ltd. Ten years of historic data (2012-2021) is taken from the yahoo finance website to carry out analysis of proposed approaches. In the first approach, closing prices of two selected companies are directly applied on univariate LSTM model. For the approach second, technical indicators values are calculated from the closing prices and then collectively applied on Multivariate LSTM model. Short term market behaviour for upcoming days is evaluated. Experimental outcomes revel that approach one is useful to determine the future trend but multivariate LSTM model with technical indicators found to be useful in accurately predicting the future price behaviours.

Deepak Kumar, Divakar Yadav, Yash Patel

We present a single-GPU (H100, bf16) evaluation of GPT-OSS-20B (Mixture-of-Experts; 20.9B total, approx. 3.61B active) against dense baselines Qwen3-32B and Yi-34B across multiple dimensions. We measure true time-to-first-token (TTFT), full-decode throughput (TPOT), end-to-end latency percentiles, peak VRAM with past key values (PKV) held, and energy via a consistent nvidia-smi-based sampler. At a 2048-token context with 64-token decode, GPT-OSS-20B delivers higher decode throughput and tokens per Joule than dense baselines Qwen3-32B and Yi-34B, while substantially reducing peak VRAM and energy per 1000 generated tokens; its TTFT is higher due to MoE routing overhead. With only 17.3% of parameters active (3.61B of 20.9B), GPT-OSS-20B provides about 31.8% higher decode throughput and 25.8% lower energy per 1000 generated tokens than Qwen3-32B at 2048/64, while using 31.7% less peak VRAM. Normalized by active parameters, GPT-OSS-20B shows markedly stronger per-active-parameter efficiency (APE), underscoring MoE's deployment advantages. We do not evaluate accuracy; this is a deployment-focused study. We release code and consolidated results to enable replication and extension.