15 citations · 19 across the 13 of their papers we have counts for
18 papers
From Spectral Saliency to Finite Deletion: Evaluating Selective Language Model Edits
Ibne Farabi Shihab, Joyanta Jyoti Mondal
Deleting singular components offers a precise way to remove a capability from a language model, yet the first-order spectral saliency used to rank components predicts only a local…
When Can Prefixes Compile LoRA? Exact Resource-Capped Tests for Frozen Attention
Joyanta Jyoti Mondal, Ibne Farabi Shihab
Can a fixed continuous prefix replace a given low-rank adapter while the attention head stays frozen? In this research, we show that the answer depends on the adapter's target thro…
Certification Frontiers for Gaussian LoRA: Independent Priors, Posterior Risk, and Prediction-Preserving Balancing
Joyanta Jyoti Mondal, Ibne Farabi Shihab
Post-hoc Bayesian fine-tuning places Gaussians around trained low-rank adapters, yet a calibrated posterior does not by itself yield a useful generalization certificate. Such a pos…
Before Answering: Evidence Sufficiency under Size-Matched Memory Construction
Joyanta Jyoti Mondal, Md. Shifatul Ahsan Apurba, Mridul Banik +2
Agents that answer questions from compressed or retrieved memory must recognize when the evidence a query needs is no longer in memory. Benchmarks for this task usually create insu…
When Can Old Evaluations Certify a New Model? Label-Efficient Release Decisions under Evaluator Drift
Joyanta Jyoti Mondal, Mridul Banik, Md. Shifatul Ahsan Apurba +1
Releasing a model update requires certifying that its current-population risk stays below a threshold. Trusted labels are expensive, while a cheap evaluator, such as an LLM judge,…
FlowNeg: GFlowNet-Guided Diverse Hard Negative Sampling for Knowledge Graph Embedding
Ibne Farabi Shihab, Naoshin Anzum Hridi, Joyanta Jyoti Mondal
Negative sampling determines whether a knowledge graph embedding (KGE) model learns from informative counterexamples or wastes updates on implausible corruptions. Uniform negatives…
Sub-Quadratic Bisimulation Metrics via Approximate Nearest Neighbors: Coverage-Augmented Guarantees and Computable Two-Sided Certificates
Ibne Farabi Shihab, Joyanta Jyoti Mondal
Bisimulation metrics quantify behavioral similarity in Markov decision processes, but their Wasserstein fixed-point operator updates every state pair and incurs quadratic pairwise…
Discrepancy-Rounded Fair Bandits with Static and Time-Varying Exposure Floors
Ibne Farabi Shihab, Joyanta Jyoti Mondal, Anuj Sharma
Minimum-exposure constraints arise in recommendation, content curation, and regulated allocation when each provider, arm, or group must receive guaranteed exposure inside a period…
Graph Dimensionality Reduction for Contextual Bandits: Structure-Specific Regret Bounds under Approximate Smoothness and Noisy Eigenspaces
Joyanta Jyoti Mondal, Ibne Farabi Shihab, Anuj Sharma
Contextual bandits with graph-structured arms arise in recommendation, citation retrieval, and social advertising, where arms connected on a graph tend to share reward signal. Stan…
Multilevel Determinants of Overweight and Obesity Among U.S. Children Aged 10-17: Comparative Evaluation of Statistical and Machine Learning Approaches Using the 2021 National Survey of Children's Health
Joyanta Jyoti Mondal
Background: Childhood and adolescent overweight and obesity remain major public health concerns in the United States and are shaped by behavioral, household, and community factors.…
TWIG: Two-Step Image Generation using Segmentation Masks in Diffusion Models
Mazharul Islam Rakib, Showrin Rahman, Joyanta Jyoti Mondal +4
In today's age of social media and marketing, copyright issues can be a major roadblock to the free sharing of images. Generative AI models have made it possible to create high-qua…
E2CB2former: Effecitve and Explainable Transformer for CB2 Receptor Ligand Activity Prediction
Jiacheng Xie, Yingrui Ji, Linghuan Zeng +5
Accurate prediction of CB2 receptor ligand activity is pivotal for advancing drug discovery targeting this receptor, which is implicated in inflammation, pain management, and neuro…
Aerial Flood Scene Classification Using Fine-Tuned Attention-based Architecture for Flood-Prone Countries in South Asia
Ibne Hassan, Aman Mujahid, Abdullah Al Hasib +4
Countries in South Asia experience many catastrophic flooding events regularly. Through image classification, it is possible to expedite search and rescue initiatives by classifyin…
Med-IC: Fusing a Single Layer Involution with Convolutions for Enhanced Medical Image Classification and Segmentation
Md. Farhadul Islam, Sarah Zabeen, Meem Arafat Manab +7
The majority of medical images, especially those that resemble cells, have similar characteristics. These images, which occur in a variety of shapes, often show abnormalities in th…
Involution Fused ConvNet for Classifying Eye-Tracking Patterns of Children with Autism Spectrum Disorder
Md. Farhadul Islam, Meem Arafat Manab, Joyanta Jyoti Mondal +5
Autism Spectrum Disorder (ASD) is a complicated neurological condition which is challenging to diagnose. Numerous studies demonstrate that children diagnosed with autism struggle w…
Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm
S. M. Fazle Rabby Labib, Joyanta Jyoti Mondal, Meem Arafat Manab +2
The susceptibility of deep neural networks (DNNs) to adversarial attacks undermines their reliability across numerous applications, underscoring the necessity for an in-depth explo…
Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network
Joyanta Jyoti Mondal, Md. Farhadul Islam, Raima Islam +5
The prevalence and mobility of smartphones make these a widely used tool for environmental health research. However, their potential for determining aggregated air quality index (A…
Sherlock in OSS: A Novel Approach of Content-Based Searching in Object Storage System
Jannatun Noor, Rizwanul Haque Ratul, Mir Rownak Ali Uday +3
Object Storage Systems (OSS) inside a cloud promise scalability, durability, availability, and concurrency. However, open-source OSS does not have a specific approach to letting us…