BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Ankur Gupta

Ankur Gupta appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
cond-mat.softphysics.chem-phArtificial IntelligenceApplicationsComputation and LanguageComputer VisionCryptography and SecurityMachine LearningMultiagent SystemsMultimediaSocial and Information Networks

Catalog footprint

What is connected

8works
11topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

8 published item(s)

preprint2026arXiv

Switchcraft: AI Model Router for Agentic Tool Calling

Agentic AI systems that invoke external tools are powerful but costly, leading developers to default to large models and overspend inference budgets. Model routing can mitigate this, but existing routers are designed for chat completion rather than tool use. We present Switchcraft, the first (to the best of our knowledge) model router optimized for agentic tool calling. Switchcraft operates inline, selecting the lowest-cost model subject to correctness. We construct an evaluation framework on five function-calling benchmarks and train a DistilBERT-based classifier, deployed under a latency budget. Switchcraft achieves 82.9% accuracy -- matching or exceeding the best individual model -- while reducing inference cost by 84%, saving over $3,600 per million queries. We find that larger models do not consistently outperform smaller ones on tool-use tasks, and that nominally cheaper models can incur higher total cost due to token-intensive reasoning. Our work enables cost-aware agentic AI deployment without sacrificing correctness.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Two-dimensional diffusiophoretic colloidal banding: Optimizing the spatial and temporal design of solute sinks and sources

In this work, we numerically investigate the impact of two-dimensional solute gradients on the distribution of colloidal particles, i.e., colloidal banding, induced via diffusiophoresis. The solute gradients are generated by spatially arranged sources and sinks that emit/absorb a time-dependent solute flux. First we study a dipole system, i.e., one source and one sink, and discover that interdipole diffusion and flux decay timescales dictate colloidal banding. At timescales shorter than the interdipole diffusion timescale, we observe a rapid enhancement in particle enrichment around the source due to repulsion from the sink. However, at timescales longer than the interdipole diffusion timescale, the source and sink screen each other, leading to a slower enhancement. If the solute flux decays at the timescale of interdipole diffusion, an optimal separation distance is obtained such that particle enrichment is maximized. We find that the partition coefficient between solute inside the source and the bulk strongly impacts the optimal separation distance. Surprisingly, the diffusivity ratio between solute in the source and bulk has a much weaker impact on the optimal dipole separation distance. We also examine an octupole configuration, i.e., four sinks and four sources, arranged in a circle, and demonstrate that the geometric arrangement that maximizes enrichment depends on the radius of the circle. If the radius of the circle is small, it is preferred to have sources and sinks arranged in an alternating fashion. However, if the radius of the circle is large, a consecutive arrangement of sources and sinks is optimal. Our numerical framework introduces a novel method for spatially and temporally designing the banded structure of colloidal particles in two dimensions using diffusiophoresis and opens up new avenues in a field that has primarily focused on one-dimensional solute gradients.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Impact of Asymmetries in Valences and Diffusivities on the Transport of a Binary Electrolyte in a Charged Cylindrical Pore

Ion transport in porous media is present in a wealth of technologies, e.g., energy storage devices such as batteries and supercapacitors, and environmental technologies such as electrochemical carbon capture and capacitive deionization. Recent studies on flat-plate electrodes have demonstrated that asymmetries in ion properties, such as valences and diffusivities, lead to intriguing and counter-intuitive physical phenomena. Yet, the consequences of such asymmetries to ion transport have seldom been explored in porous geometries. To bridge this knowledge gap, we conduct a perturbation expansion of the Poisson-Nernst-Planck equations in a cylindrical pore in the limit of small potentials for a binary electrolyte with arbitrary valences and diffusivities. We obtain good agreement between the perturbation analysis and direct numerical simulations. Our analysis reveals that the charge and the salt transport are coupled with each other. Further, the coupling between the charge and salt transport processes is enhanced with an increase in valence and diffusivity asymmetries of ions. We observe that the mismatch of the ionic diffusivities induces a non-trivial salt dynamics, producing either transient depletion or enhancement of salt in the pore. In the regime of high static diffusion layer conductance, we obtain an analytical solution to our perturbation model. The solution elucidates how electrolyte asymmetry induces two charging timescales that are set by the relative pore size. In the overlapping-double-layer regime, these timescales reduce to the diffusion times of each ion such that the transport of the two ions appears to be decoupled. Overall, our work underscores that the asymmetry in cation and anion diffusivities fundamentally alters the behavior of ionic transport inside a charged cylindrical pore and opens up new avenues of research on electrolyte transport in porous materials.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Ion Transport in an Electrochemical Cell: A Theoretical Framework to Couple Dynamics of Double Layers and Redox Reactions for Multicomponent Electrolyte Solutions

Electrochemical devices often consist of multicomponent electrolyte solutions. Two processes influence the overall dynamics of these devices: the formation of electrical double layers and chemical conversion due to redox reactions. However, due to the presence of multiple length and time scales, it is challenging to simulate both processes directly from the Poisson-Nernst-Planck equations. Therefore, common modeling approaches ignore one of the processes, assume the two are independent, or extrapolate the results from reaction-free systems. To overcome these limitations, we formulate and derive an asymptotic model by solving the Poisson-Nernst-Planck equations for an arbitrary number of ions in the thin-double-layer limit. Our analysis reveals that there are two distinct timescales in the system: double-layer charging and bulk diffusion. Our model displays excellent quantitative agreement with direct numerical simulations. Further, our approach is computationally efficient and numerically stable, even for large potentials. We investigate the dynamics of charging for a binary electrolyte and three-ion system, and find that redox reactions impact the double-layer charging process at short times whereas they modify the double-layer capacitance at long times. Overall, the proposed theoretical framework advances our ability to simulate electrochemical devices that contain multiple ions and widens opportunities for future research in the field.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

TruthBot: An Automated Conversational Tool for Intent Learning, Curated Information Presenting, and Fake News Alerting

We present TruthBot, an all-in-one multilingual conversational chatbot designed for seeking truth (trustworthy and verified information) on specific topics. It helps users to obtain information specific to certain topics, fact-check information, and get recent news. The chatbot learns the intent of a query by training a deep neural network from the data of the previous intents and responds appropriately when it classifies the intent in one of the classes above. Each class is implemented as a separate module that uses either its own curated knowledge-base or searches the web to obtain the correct information. The topic of the chatbot is currently set to COVID-19. However, the bot can be easily customized to any topic-specific responses. Our experimental results show that each module performs significantly better than its closest competitor, which is verified both quantitatively and through several user-based surveys in multiple languages. TruthBot has been deployed in June 2020 and is currently running.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Counterfactual Estimation and Optimization of Click Metrics for Search Engines

Optimizing an interactive system against a predefined online metric is particularly challenging, when the metric is computed from user feedback such as clicks and payments. The key challenge is the counterfactual nature: in the case of Web search, any change to a component of the search engine may result in a different search result page for the same query, but we normally cannot infer reliably from search log how users would react to the new result page. Consequently, it appears impossible to accurately estimate online metrics that depend on user feedback, unless the new engine is run to serve users and compared with a baseline in an A/B test. This approach, while valid and successful, is unfortunately expensive and time-consuming. In this paper, we propose to address this problem using causal inference techniques, under the contextual-bandit framework. This approach effectively allows one to run (potentially infinitely) many A/B tests offline from search log, making it possible to estimate and optimize online metrics quickly and inexpensively. Focusing on an important component in a commercial search engine, we show how these ideas can be instantiated and applied, and obtain very promising results that suggest the wide applicability of these techniques.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Hiding Sound in Image by K-LSB Mutation

In this paper a novel approach to hide sound files in a digital image is proposed and implemented such that it becomes difficult to conclude about the existence of the hidden data inside the image. In this approach, we utilize the rightmost k-LSB of pixels in an image to embed MP3 sound bits into a pixel. The pixels are so chosen that the distortion in image would be minimized due to embedding. This requires comparing all the possible permutations of pixel values, which may would lead to exponential time computation. To speed up this, Cuckoo Search (CS) could be used to find the most optimal solution. The advantage of using proposed CS is that it is easy to implement and is very effective at converging in relatively less iterations/generations.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Automated Switching System for Skin Pixel Segmentation in Varied Lighting

In Computer Vision, colour-based spatial techniquesoften assume a static skin colour model. However, skin colour perceived by a camera can change when lighting changes. In common real environment multiple light sources impinge on the skin. Moreover, detection techniques may vary when the image under study is taken under different lighting condition than the one that was earlier under consideration. Therefore, for robust skin pixel detection, a dynamic skin colour model that can cope with the changes must be employed. This paper shows that skin pixel detection in a digital colour image can be significantly improved by employing automated colour space switching methods. In the root of the switching technique which is employed in this study, lies the statistical mean of value of the skin pixels in the image which in turn has been derived from the Value, measures as a third component of the HSV. The study is based on experimentations on a set of images where capture time conditions varying from highly illuminated to almost dark.

0 citations0 reviewsNo code linkedOpen access