1 citations · 3 across the 45 of their papers we have counts for
18 papers · 1 filter
LLM-Guided Probabilistic Fusion for Label-Efficient Document Layout Analysis
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Document layout understanding remains data-intensive despite advances in semi-supervised learning. We present a framework that enhances semi-supervised detection by fusing visual p…
Temporal Zoom Networks: Distance Regression and Continuous Depth for Efficient Action Localization
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Temporal action localization requires both precise boundary detection and computational efficiency. Current methods apply uniform computation across all temporal positions, wasting…
Anytime-Valid Answer Sufficiency Certificates for LLM Generation via Sequential Information Lift
Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma
We introduce Sequential-EDFL (Empirical Dynamic Formal Lift), which applies anytime-valid sequential testing to language model generation stopping. Our approach tracks information…
Calibrated and Resource-Aware Super-Resolution for Reliable Driver Behavior Analysis
Ibne Farabi Shihab, Weiheng Chai, Jiyang Wang +3
Driver monitoring systems require not just high accuracy but reliable, well-calibrated confidence scores for safety-critical deployment. While direct low-resolution training yields…
What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Sparse-reward reinforcement learning (RL) remains fundamentally hard: without structure, any agent needs samples to recover rewards. We introduce…
Selective Risk Certification for LLM Outputs via Information-Lift Statistics: PAC-Bayes, Robustness, and Skeleton Design
Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma
Large language models often produce confident but incorrect outputs, creating a critical need for reliable uncertainty quantification with formal abstention guarantees. We introduc…
Differentiable Entropy Regularization: A Complexity-Aware Approach for Neural Optimization
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
We introduce the first differentiable approximation of range-partition entropy, a complexity measure from computational geometry that directly bounds algorithmic runtime. Unlike ar…
Causal Consistency Regularization: Training Verifiably Sensitive Reasoning in Large Language Models
Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma
Large language models can produce correct answers while relying on flawed reasoning traces, partly because common training objectives reward final-answer correctness rather than fa…
The 9th AI City Challenge
Zheng Tang, Shuo Wang, David C. Anastasiu +25
The ninth AI City Challenge continues to advance real-world applications of computer vision and AI in transportation, industrial automation, and public safety. The 2025 edition fea…
Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Proxy optimization, where AI systems exploit evaluator weaknesses rather than improve intended objectives, threatens both reinforcement learning (reward hacking) and LLM alignment…
Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges
Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma
Crash detection from video feeds is a critical problem in intelligent transportation systems. Recent developments in large language models (LLMs) and vision-language models (VLMs)…
Image Segmentation with Large Language Models: A Survey with Perspectives for Intelligent Transportation Systems
Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma
The integration of Large Language Models (LLMs) with computer vision is profoundly transforming perception tasks like image segmentation. For intelligent transportation systems (IT…
Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Integrating large language models (LLMs) as priors in reinforcement learning (RL) offers significant advantages but comes with substantial computational costs. We present a princip…
Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
State-space models (SSMs), particularly the Mamba architecture, have emerged as powerful alternatives to Transformers for sequence modeling, offering linear-time complexity and com…
HMAE: Self-Supervised Few-Shot Learning for Quantum Spin Systems
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Quantum machine learning for spin and molecular systems faces critical challenges of scarce labeled data and computationally expensive simulations. To address these limitations, we…
ClearVision: Leveraging CycleGAN and SigLIP-2 for Robust All-Weather Classification in Traffic Camera Imagery
Anush Lakshman Sivaraman, Kojo Adu-Gyamfi, Ibne Farabi Shihab +1
Adverse weather conditions challenge safe transportation, necessitating robust real-time weather detection from traffic camera imagery. We propose a novel framework combining Cycle…
Accuracy is Not Agreement: Expert-Aligned Evaluation of Crash Narrative Classification Models
Sudesh Ramesh Bhagat, Ibne Farabi Shihab, Anuj Sharma
This study investigates the relationship between deep learning (DL) model accuracy and expert agreement in classifying crash narratives. We evaluate five DL models -- including BER…
Enhancing Traffic Incident Response through Sub-Second Temporal Localization with HybridMamba
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Traffic crash detection in long-form surveillance videos is essential for improving emergency response and infrastructure planning, yet remains difficult due to the brief and infre…