collaborators

11 papers

cs.CV2026

Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning

Md Tanvirul Alam

Reinforcement learning with verifiable rewards (RLVR) has substantially improved language-model reasoning, yet its extension to vision-language models remains constrained by the la…

cs.LG2026

Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs

Md Tanvirul Alam, Aritran Piplai, Ionut Cardei +2

Cyber threat intelligence (CTI) analysts routinely convert noisy, unstructured security artifacts into standardized, automation-ready representations. Although large language model…

cs.CV2026

Beyond Perception Errors: Semantic Fixation in Large Vision-Language Models

Md Tanvirul Alam

Large vision-language models (VLMs) often rely on familiar semantic priors, but existing evaluations do not cleanly separate perception failures from rule-mapping failures. We stud…

cs.CV2026

SPHINX: A Synthetic Environment for Visual Perception and Reasoning

Md Tanvirul Alam, Saksham Aggarwal, Justin Yang Chae +1

We present Sphinx, a synthetic environment for visual perception and reasoning that targets core cognitive primitives. Sphinx procedurally generates puzzles using motifs, tiles, ch…

cs.CV2026

Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing

Dipkamal Bhusal, Md Tanvirul Alam, Nidhi Rastogi

Gradient-based saliency methods such as Vanilla Gradient (VG) and Integrated Gradients (IG) are widely used to explain image classifiers, yet the resulting maps are often noisy and…

cs.CR2026

AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence

Md Tanvirul Alam, Dipkamal Bhusal, Salman Ahmad +2

Large Language Models (LLMs) have demonstrated strong capabilities in natural language reasoning, yet their application to Cyber Threat Intelligence (CTI) remains limited. CTI anal…