Prateek Yadav

AKS University, Satna | AKSUNI · Computer Science

The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to particular domains. This has enabled the creation of powerful and adaptive routing-based "Model MoErging" methods with the goal of using expert modules to create an aggregate system with improved performance or generaliza...

The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particular domain or task. Model MoErging methods aim to recycle expert models to create an aggregate system with improved performance or generalization. A key component of MoErging methods is the creation of a router t...

Large-scale code generation models such as Codex and CodeT5 have achieved impressive performance. However, libraries are upgraded or deprecated very frequently and re-training large-scale language models is computationally expensive. Therefore, Continual Learning (CL) is an important aspect that remains underexplored in the code domain. In this pap...

Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have led to a proliferation of task-specific fine-tuned models, which typically can only perform a single task and d...

Recent studies have shown promising results on utilizing pre-trained image-language models for video question answering. While these image-language models can efficiently bootstrap the representation learning of video-language models, they typically concatenate uniformly sampled video frames as visual inputs without explicit language-aware, tempora...

Continual Learning (CL) methods mainly focus on avoiding catastrophic forgetting and learning representations that are transferable to new tasks. Recently, Wortsman et al. (2020) proposed a CL method, SupSup, which uses a randomly initialized, fixed base network (model) and finds a supermask for each new task that selectively keeps or removes each...

The importance of water in human life and various other forms of life is a fact that doesn't need any discussion with total safe drinking water with just 0.5% of total water present on earth thus the importance of cleaning of used water becomes an utmost priority for further use and its safe addition to further water life cycle. Mechanical drainage...

Pre-trained sequence-to-sequence language models have led to widespread success in many natural language generation tasks. However, there has been relatively less work on analyzing their ability to generate structured outputs such as graphs. Unlike natural language, graphs have distinct structural and semantic properties in the context of a downstr...

The problem of identifying algorithmic recourse for people affected by machine learning model decisions has received much attention recently. Some recent works model user-incurred cost, which is directly linked to user satisfaction. But they assume a single global cost function that is shared across all users. This is an unrealistic assumption when...

The ongoing search for biodegradable and biocompatible microneedles (MNs) that are strong enough to penetrate skin barriers, easy to prepare, and can be translated for clinical use continues. As such, this review paper is focused upon discussing the key points (e.g., choice polymeric MNs) for the translation of MNs from laboratory to clinical pract...

We focus on a type of linguistic formal reasoning where the goal is to reason over explicit knowledge in the form of natural language facts and rules (Clark et al., 2020). A recent work, named PRover (Saha et al., 2020), performs such reasoning by answering a question and also generating a proof graph that explains the answer. However, compositiona...

Recent commonsense-reasoning tasks are typically discriminative in nature, where a model answers a multiple-choice question for a certain context. Discriminative tasks are limiting because they fail to adequately evaluate the model's ability to reason and explain predictions with underlying commonsense knowledge. They also allow such models to use...

A palladium-catalyzed and norbornene-mediated methodology has been developed for the synthesis of chiral 2-aryl-ferroceneamides from chiral 2-iodo-N,N-diisopropylferrocencarboxamide, iodoarenes, and alkenes using a JohnPhos ligand and potassium carbonate as a base in dimethylformamide at 105°C. The developed three-component coupling protocol allows...

A copper‐catalyzed 8‐aminoquinoline‐directed oxidative cross‐coupling of the C−H bond of ferrocene with sodium arylsulfinates has been achieved. The robust copper catalyst tolerates a range of methyl, tert‐butyl, bromo, chloro, iodo and nitro functional groups in the phenyl ring, and set the stage for the synthesis of substituted ferrocene sulfones...

Go-kart is a simple four-wheeled, small engine, single sealed racing car it is a Go-kart, by definition, no differential. They are usually raced on scaled down tracks, but are sometimes driven as entertainment or as a hobby by non-professionals. Karting is commonly perceived as the stepping shone to the higher and more expensive ranks of motor spor...

In this paper, we developed the pneumatic Can Crusher which is operated by air pressure. The air flow is controlled by a valve which is operated manually. This paper is mainly about generating new concepts of pneumatic can crusher that would make easy and easier to crush the tin and this paper involves the process of designing the crusher manually...

Regional differences in cognitive ability are presented for 33 states and union territories of India. Ability was positively correlated with GDP per capita, literacy and life expectancy and negatively correlated with infant and child mortality, fertility and the percentage of Muslims. Ability was higher in the south than in the north and in states...

Essential communication in this fast moving world is always been a major concern. Although we have messengers like gtalk, Facebook, WhatsApp who are a good source of circulating messages but they kind of deviates us from the imperative purpose of communication. There has been no services available which allows us to store important messages and app...