arXiv subjects

Uzair Ahmed

Publications and source records attributed to Uzair Ahmed.

7 recordsLinked to original sources

arXiv2026

Can LLMs Reliably Self-Report Adversarial Prefills, and How?

Prior work shows that large language models (LLMs) exhibit varying degrees of introspective capability on benign tasks. We extend the question to safety contexts and examine how reliably a model can recognize that its own prior response was elicited by an adversarial prefill attack. Across ten open-weight instruction-tuned LLMs from 3B to 70B parameters and four safety benchmarks, no model reliably recognizes its own compromised outputs, with models claiming intent on prefilled responses at an average rate of 25.3%. Introspective signal stems primarily from reasoning about safety and refusal. Orthogonalizing models' weights against the refusal direction collapses the gap between claim rates on prefilled and natural outputs to near zero, though the direction is not its unique mediator. Framing the question as internal intention versus external tampering elicits qualitatively different responses on the same models. Training models to mimic correct introspective answers or optimize an introspective objective can improve the accuracy of introspection, but such training does not transfer to the tampering probe and counterintuitively raises attack success rate under adversarial prefill on most models, amounting to a partial mitigation. These findings outline mechanisms underpinning the observed introspective signals in safety contexts and highlight risks in the reliability of LLM self-reports.

cs.CL↗

arXiv2025

SOLAR: Scalable Optimization of Large-scale Architecture for Reasoning

Large Language Models excel in reasoning yet often rely on Chain-of-Thought prompts, limiting performance on tasks demanding more nuanced topological structures. We present SOLAR (Scalable Optimization of Large-scale Architecture for Reasoning), a framework that dynamically optimizes Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thought (GoT) topologies to boost accuracy and efficiency. Our Topological-Annotation-Generation (TAG) system automates dataset creation, annotation, and difficulty segmentation, leading to stronger post training and test-time performance. We also propose Topological-Scaling, a curriculum-learning-based approach that adaptively combines post training and inference scaling to each task. On MATH and GSM8K, SOLAR delivers notable gains: +5% accuracy with Topological Tuning, +9% with Topological Rewarding, and +10.02% with Hybrid Scaling, while reducing response length by over 5%, lowering inference latency. To further enhance efficiency, we introduce a multi-task Topological Reward Model (M-TRM) that selects both the optimal reasoning topology and final answer in a single pass, eliminating multiple single-task TRMs. Remarkably, M-TRM also surpasses all single-task TRMs, improving accuracy by +10% and rank correlation by +9%. Overall, SOLAR establishes a new benchmark for scalable, high-precision LLM reasoning and introduces a fully automated, dynamic topology competition mechanism.

cs.AI↗

arXiv2024

Towards Greener Nights: Exploring AI-Driven Solutions for Light Pollution Management

This research endeavors to address the pervasive issue of light pollution through an interdisciplinary approach, leveraging data science and machine learning techniques. By analyzing extensive datasets and research findings, we aim to develop predictive models capable of estimating the degree of sky glow observed in various locations and times. Our research seeks to inform evidence-based interventions and promote responsible outdoor lighting practices to mitigate the adverse impacts of light pollution on ecosystems, energy consumption, and human well-being.

cs.LG↗

arXiv2022

Unitail: Detecting, Reading, and Matching in Retail Scene

To make full use of computer vision technology in stores, it is required to consider the actual needs that fit the characteristics of the retail scene. Pursuing this goal, we introduce the United Retail Datasets (Unitail), a large-scale benchmark of basic visual tasks on products that challenges algorithms for detecting, reading, and matching. With 1.8M quadrilateral-shaped instances annotated, the Unitail offers a detection dataset to align product appearance better. Furthermore, it provides a gallery-style OCR dataset containing 1454 product categories, 30k text regions, and 21k transcriptions to enable robust reading on products and motivate enhanced product matching. Besides benchmarking the datasets using various state-of-the-arts, we customize a new detector for product detection and provide a simple OCR-based matching solution that verifies its effectiveness.

cs.CV↗

arXiv2021

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Few-shot object detection is an imperative and long-lasting problem due to the inherent long-tail distribution of real-world data. Its performance is largely affected by the data scarcity of novel classes. But the semantic relation between the novel classes and the base classes is constant regardless of the data availability. In this work, we investigate utilizing this semantic relation together with the visual information and introduce explicit relation reasoning into the learning of novel object detection. Specifically, we represent each class concept by a semantic embedding learned from a large corpus of text. The detector is trained to project the image representations of objects into this embedding space. We also identify the problems of trivially using the raw embeddings with a heuristic knowledge graph and propose to augment the embeddings with a dynamic relation graph. As a result, our few-shot detector, termed SRR-FSD, is robust and stable to the variation of shots of novel objects. Experiments show that SRR-FSD can achieve competitive results at higher shots, and more importantly, a significantly better performance given both lower explicit and implicit shots. The benchmark protocol with implicit shots removed from the pretrained classification dataset can serve as a more realistic setting for future research.

cs.CV↗

arXiv2019

Transfer Learning and Meta Classification Based Deep Churn Prediction System for Telecom Industry

A churn prediction system guides telecom service providers to reduce revenue loss. However, the development of a churn prediction system for a telecom industry is a challenging task, mainly due to the large size of the data, high dimensional features, and imbalanced distribution of the data. In this paper, we present a solution to the inherent problems of churn prediction, using the concept of Transfer Learning (TL) and Ensemble-based Meta-Classification. The proposed method TL-DeepE is applied in two stages. The first stage employs TL by fine-tuning multiple pre-trained Deep Convolution Neural Networks (CNNs). Telecom datasets are normally in vector form, which is converted into 2D images because Deep CNNs have high learning capacity on images. In the second stage, predictions from these Deep CNNs are appended to the original feature vector and thus are used to build a final feature vector for the high-level Genetic Programming (GP) and AdaBoost based ensemble classifier. Thus, the experiments are conducted using various CNNs as base classifiers and the GP-AdaBoost as a meta-classifier. By using 10-fold cross-validation, the performance of the proposed TL-DeepE system is compared with existing techniques, for two standard telecommunication datasets; Orange and Cell2cell. Performing experiments on Orange and Cell2cell datasets, the prediction accuracy obtained was 75.4% and 68.2%, while the area under the curve was 0.83 and 0.74, respectively.

cs.LG↗

arXiv2016

Formation and transformation of low density, onion-like carbon cages

A novel growth technique for low density, non-icosahedral carbon onion-like structures on Cu surface is described. The technique differs with the formation of carbon onions inside the C1+ implanted metal surfaces at high temperatures with densities ~ 2 g cm-3 in the form of multishelled icosahedral fullerenes wrapped around C60. We report spheroidal cage formation of shell with variable shell thickness, radii and curvature on C1+-irradiated Cu surfaces by the accumulating C atoms which emerge out of the edges of the implanted sheets and grids. Atom-by-atom C accreting structures grow along the edges, corners and crevices. These, in turn, form the open and closed multiple-shelled cages. Variable curvature is the most common feature of the growing structures. The growth at room temperature does not ensure sphericity of the cages due to the absence of high temperature annealing. These cages have very low density, hollow interiors and often exhibit the conspicuous cage-inside-cage structures. Another feature of the as-grown, non-spherical onions is the existence of spherical protrusions with different local radii within the same cage. Formation of cages with sizes ~ few nanometer to hundreds of nanometer depends upon the irradiation rate of C1+. In situ formation and transformations of the cages observed under 120 keV electron beam irradiation is described by using a nanoelastic model.

cond-mat.mes-hall↗