Vikas Singh
YOU?
Author Swipe
View article: CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding
CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding Open
Post-training quantization is an effective method for reducing the serving cost of large language models, where the standard approach is to use a round-to-nearest quantization level scheme. However, this often introduces large errors due t…
View article: Familial Woolly Hair
Familial Woolly Hair Open
A 10-year-old Indian female presented with persistently short, sparse scalp hair since birth, with no subsequent growth. Clinical examination revealed tightly coiled, light-colored, and diffusely thinned scalp hair, along with partial loss…
View article: PTHP-22. Does the Extent of Resection matter In Medulloblastomas? In an era of Molecular Subgrouping: A single-center Indian study
PTHP-22. Does the Extent of Resection matter In Medulloblastomas? In an era of Molecular Subgrouping: A single-center Indian study Open
Molecular subgrouping (MS) has stratified outcomes in medulloblastoma, while the extent of resection (EOR) remains the standard of care. When gross total resection (GTR) is not possible due to the tumor’s invasive nature or risk of neurolo…
View article: SURG-59. Peri-operative Outcomes Following Primary Surgery For Medulloblastomas And Association With Molecular Subgroups
SURG-59. Peri-operative Outcomes Following Primary Surgery For Medulloblastomas And Association With Molecular Subgroups Open
Medulloblastomas are most common pediatric malignant brain tumor. Molecular classification has identified 4 main subgroups (WNT, SHH, group 3 and group4) which have distinct demographic and clinical outcomes. The also have different develo…
View article: Antenatal Diagnosis of Cranio-thoraco-omphalopagus in Ultrasound: A Case Report
Antenatal Diagnosis of Cranio-thoraco-omphalopagus in Ultrasound: A Case Report Open
View article: Outcomes of Infants and Young Children With <scp>CNS</scp> Embryonal Tumors Using Pre‐Irradiation Chemotherapy: A Decade Long Experience
Outcomes of Infants and Young Children With <span>CNS</span> Embryonal Tumors Using Pre‐Irradiation Chemotherapy: A Decade Long Experience Open
Background Management of infants and young children with embryonal tumors of the central nervous system remains a challenge. We report the outcomes in these children with the strategy of surgery, pre‐irradiation chemotherapy, and delayed r…
View article: ALA Fluorescence-Guided Resection of High-Grade Glioma: Dye Can See, What Eye Cannot See!
ALA Fluorescence-Guided Resection of High-Grade Glioma: Dye Can See, What Eye Cannot See! Open
View article: Brainshift correction using navigated intraoperative ultrasound informs intraoperative decision-making during glioma surgery
Brainshift correction using navigated intraoperative ultrasound informs intraoperative decision-making during glioma surgery Open
View article: Hotel Booking Cancellation Prediction Using Applied Bayesian Models
Hotel Booking Cancellation Prediction Using Applied Bayesian Models Open
This study applies Bayesian models to predict hotel booking cancellations, a key challenge affecting resource allocation, revenue, and customer satisfaction in the hospitality industry. Using a Kaggle dataset with 36,285 observations and 1…
View article: Skin as a Reflection of Gut Health: An Overview of Dermatological Manifestations in Primary Neoplastic and Autoimmune Gastrointestinal Disorders
Skin as a Reflection of Gut Health: An Overview of Dermatological Manifestations in Primary Neoplastic and Autoimmune Gastrointestinal Disorders Open
Gastrointestinal (GI) diseases can present with several extraintestinal manifestations, and cutaneous signs and symptoms are most frequent. Although conventionally GI and skin are considered two entirely separate organ systems, they are cl…
View article: THE CHALLENGES AND IMPACT OF THE FINANCIAL SYSTEM ON ECONOMIC GROWTH IN THE CONTEXT OF THE INDIAN ECONOMY
THE CHALLENGES AND IMPACT OF THE FINANCIAL SYSTEM ON ECONOMIC GROWTH IN THE CONTEXT OF THE INDIAN ECONOMY Open
This paper examines the intricate relationship between the financial system and economic growth in India, focusing on the challenges and potential impact of the financial sector on sustainable development. As one of the world’s fastest-gro…
View article: Variational Sampling of Temporal Trajectories
Variational Sampling of Temporal Trajectories Open
A deterministic temporal process can be determined by its trajectory, an element in the product space of (a) initial condition $z_0 \in \mathcal{Z}$ and (b) transition function $f: (\mathcal{Z}, \mathcal{T}) \to \mathcal{Z}$ often influenc…
View article: LookupFFN: Making Transformers Compute-lite for CPU inference
LookupFFN: Making Transformers Compute-lite for CPU inference Open
While GPU clusters are the de facto choice for training large deep neural network (DNN) models today, several reasons including ease of workflow, security and cost have led to efforts investigating whether CPUs may be viable for inference …
View article: Pooling Image Datasets With Multiple Covariate Shift and Imbalance
Pooling Image Datasets With Multiple Covariate Shift and Imbalance Open
Small sample sizes are common in many disciplines, which necessitates pooling roughly similar datasets across multiple institutions to study weak but relevant associations between images and disease outcomes. Such data often manifest shift…
View article: Relationship of APOE genotypes and level of cognitive reserve to cognitive trajectories among cognitively normal individuals
Relationship of APOE genotypes and level of cognitive reserve to cognitive trajectories among cognitively normal individuals Open
Background Prior findings indicate that both genetic factors and indices of cognitive reserve (CR) influence risk of cognitive decline, with APOE4 genetic status increasing risk, and APOE2 genetic status and higher CR indices decreasing ri…
View article: Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens Open
Transformers are central in modern natural language processing and computer vision applications. Despite recent works devoted to reducing the quadratic cost of such models (as a function of the sequence length), dealing with ultra long seq…
View article: Alzheimer’s disease genetic risk and cognitive reserve in relationship to long-term cognitive trajectories among cognitively normal individuals
Alzheimer’s disease genetic risk and cognitive reserve in relationship to long-term cognitive trajectories among cognitively normal individuals Open
Background Both Alzheimer’s disease (AD) genetic risk factors and indices of cognitive reserve (CR) influence risk of cognitive decline, but it remains unclear whether they interact. This study examined whether a CR index score modifies th…
View article: On the Versatile Uses of Partial Distance Correlation in Deep Learning
On the Versatile Uses of Partial Distance Correlation in Deep Learning Open
Comparing the functional behavior of neural network models, whether it is a single network over time or two (or more networks) during or post-training, is an essential step in understanding what they are learning (and what they are not), a…
View article: Understanding Uncertainty Maps in Vision with Statistical Testing
Understanding Uncertainty Maps in Vision with Statistical Testing Open
Quantitative descriptions of confidence intervals and uncertainties of the predictions of a model are needed in many applications in vision and machine learning. Mechanisms that enable this for deep neural network (DNN) models are slowly b…
View article: Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets
Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets Open
Pooling multiple neuroimaging datasets across institutions often enables improvements in statistical power when evaluating associations (e.g., between risk factors and disease outcomes) that may otherwise be too weak to detect. When there …
View article: Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets
Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets Open
Pooling multiple neuroimaging datasets across institutions often enables improvements in statistical power when evaluating associations (e.g., between risk factors and disease outcomes) that may otherwise be too weak to detect. When there …
View article: Graph Reparameterizations for Enabling 1000+ Monte Carlo Iterations in Bayesian Deep Neural Networks
Graph Reparameterizations for Enabling 1000+ Monte Carlo Iterations in Bayesian Deep Neural Networks Open
Uncertainty estimation in deep models is essential in many real-world applications and has benefited from developments over the last several years. Recent evidence suggests that existing solutions dependent on simple Gaussian formulations …
View article: Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data
Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data Open
Panel data involving longitudinal measurements of the same set of participants taken over multiple time points is common in studies to understand childhood development and disease modeling. Deep hybrid models that marry the predictive powe…
View article: Preoperative neurocognitive dysfunction in and Indian cohort of brain tumor patients and factors associated with domain-specific dysfunction
Preoperative neurocognitive dysfunction in and Indian cohort of brain tumor patients and factors associated with domain-specific dysfunction Open
View article: On the Versatile Uses of Partial Distance Correlation in Deep Learning
On the Versatile Uses of Partial Distance Correlation in Deep Learning Open
View article: Navigated 3D intraoperative ultrasound guidance improves resections in gliomas compared to 2D ultrasound–propensity matched analysis
Navigated 3D intraoperative ultrasound guidance improves resections in gliomas compared to 2D ultrasound–propensity matched analysis Open
View article: Deep Unlearning via Randomized Conditionally Independent Hessians
Deep Unlearning via Randomized Conditionally Independent Hessians Open
No description supplied
View article: Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs
Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs Open
No description supplied
View article: Effect of doses to hippocampal subvolumes on short-term memory function in patients pituitary adenomas treated with conformal radiotherapy: report from a prospective phase II study
Effect of doses to hippocampal subvolumes on short-term memory function in patients pituitary adenomas treated with conformal radiotherapy: report from a prospective phase II study Open
View article: Forward Operator Estimation in Generative Models with Kernel Transfer Operators
Forward Operator Estimation in Generative Models with Kernel Transfer Operators Open
Generative models which use explicit density modeling (e.g., variational autoencoders, flow-based generative models) involve finding a mapping from a known distribution, e.g. Gaussian, to the unknown input distribution. This often requires…