42 citations · 95 across the 22 of their papers we have counts for
12 papers · 1 filter
ClaimScope: Label-Blind Witness Verification for Mathematical Claim Auditing
Mushir Akhtar
Mathematical agents are commonly evaluated by answer accuracy or proof acceptance. We introduce ClaimScope, a 72-task benchmark for auditing proposed claims through a verdict, scop…
When Does Muon Actually Win? A Paired Data-, Time-, and Tuning-Budget Benchmark
Mushir Akhtar, Hazem N. Nounou, Majdi Mansouri +1
Muon's gains in data efficiency motivate evaluating its performance under explicit data, time, and tuning budgets. On a single A100 GPU, we compare a reference single-device Muon i…
SAGE-CP: When Marginal Coverage Hides Route-Conditional Failures in Adaptive VLM Ensembles
Mushir Akhtar, M. Tanveer
Adaptive VLM ensembles save computation by stopping early on easy images and escalating harder ones. Although a single conformal threshold can make the final predictor marginally v…
Beyond Benchmark Scores: Auditing Medical Vision-Language Models for Chest X-Ray Tuberculosis Screening
Mushir Akhtar, M. Tanveer, Mohd. Arshad
A medical model's benchmark score does not establish that the same conclusion holds under a different evaluation. This study tests whether claims about model ranking, score reliabi…
Bounded Adjustment with Reliability-Guided Embedding for Imbalanced Learning with Noisy Labels
Mushir Akhtar, Akarsh J., M. Tanveer +1
Class-balanced learning and label noise create a coupled failure mode: frequency correction prevents majority classes from dominating the decision rule, but can amplify incorrectly…
IFW-BLS: Dual-Robust Broad Learning System with Intuitionistic Fuzzy Wave Loss
Mushir Akhtar, M. Tanveer
Broad Learning System is an efficient randomized learning model that expands network width through feature and enhancement nodes and estimates the output weights without deep backp…
Robust Broad Learning System with Wave Loss for Classification under Data Uncertainty
Mushir Akhtar, A. Varshney, A. Quadir +3
Broad Learning System (BLS) offers an efficient alternative to deep architectures by enabling fast learning through randomized feature mapping and closed-form solutions. However, i…
ECA-BLS: An Efficient Complex-Augmented Broad Learning System
A. Rahaman, A. Quadir, M. Sajid +2
Broad Learning System (BLS) is an efficient alternative to deep architectures due to its fast training, analytical learning, and strong generalization under limited data. However,…
Residual-Guided Randomized Neural Networks
Mushir Akhtar, M. Tanveer, Mohd. Arshad
Randomized neural networks enable fast and analytically tractable training by fixing the input to hidden layer parameters at random and learning the output weights in closed form;…
Robust Dual-Model Collaborative Random Vector Functional Link Network
A. Quadir, A. Rahaman, Mushir Akhtar +1
Random vector functional link (RVFL) networks are lightweight and fast neural models that offer efficient training and strong generalization through randomized hidden-layer weights…
Mitigating Class-Tail Undercoverage in Medical Vision-Language Models under Clinical Shift
Mushir Akhtar, M. Tanveer
Medical vision-language models (VLMs) can retain high observed marginal coverage after clinical shift while substantially under-covering an individual disease class. The affected c…
CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks
Mushir Akhtar, M. Tanveer, Mohd. Arshad
Randomized neural networks (RdNNs) enable efficient, backpropagation-free training by freezing randomly initialized input-to-hidden weights, which permits a closed-form solution fo…