152 citations · 306 across the 37 of their papers we have counts for
38 papers
When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
Jiaming Cheng, Subhransu Das, Rajiv Ramnath
Multi-agent LLM systems relay key-value caches instead of text and credit their gains to exchanged "latent thoughts". That credit is a claim about which example's cache is relayed,…
Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deployment
Subhransu Das, Jiaming Cheng, Arnav Kumar +6
Running large AI models on resource-constrained edge devices requires model compression to reduce model size and computation. What compresses well, however, need not deploy well. W…
ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization
Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha +1
Document Visual Question Answering (VQA) requires models to not only extract accurate textual answers but also precisely localize them within document images, a capability critical…
Exploiting the Experts: Unauthorized Compression in MoE-LLMs
Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Dheeraj Kulshrestha +1
Mixture-of-Experts (MoE) architectures are increasingly adopted in large language models (LLMs) for their scalability and efficiency. However, their modular structure introduces a…
MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use
Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha +1
Document Visual Question Answering (DocVQA) requires models to jointly understand textual semantics, spatial layout, and visual features. Current methods struggle with explicit spa…
DocVAL: Validated Chain-of-Thought Distillation for Grounded Document VQA
Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Ser-Nam Lim +1
Document visual question answering requires models not only to answer questions correctly, but also to precisely localize answers within complex document layouts. While large visio…
InsightBuild: LLM-Powered Causal Reasoning in Smart Building Systems
Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Rajiv Ramnath
Smart buildings generate vast streams of sensor and control data, but facility managers often lack clear explanations for anomalous energy usage. We propose InsightBuild, a two-sta…
ALCo-FM: Adaptive Long-Context Foundation Model for Accident Prediction
Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Rajiv Ramnath
Traffic accidents are rare, yet high-impact events that require long-context multimodal reasoning for accurate risk forecasting. In this paper, we introduce ALCo-FM, a unified adap…
TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation
Amin Karimi Monsefi, Mridul Khurana, Rajiv Ramnath +3
We propose TaxaDiffusion, a taxonomy-informed training framework for diffusion models to generate fine-grained animal images with high morphological and identity accuracy. Unlike s…
PIAD-SRNN: Physics-Informed Adaptive Decomposition in State-Space RNN
Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Rajiv Ramnath
Time series forecasting often demands a trade-off between accuracy and efficiency. While recent Transformer models have improved forecasting capabilities, they come with high compu…
DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness
Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Ser-Nam Lim +1
Document Visual Question Answering (VQA) demands robust integration of text detection, recognition, and spatial reasoning to interpret complex document layouts. In this work, we in…
Scalable Deep Metric Learning on Attributed Graphs
Xiang Li, Gagan Agrawal, Ruoming Jin +1
We consider the problem of constructing embeddings of large attributed graphs and supporting multiple downstream learning tasks. We develop a graph embedding method, which is based…
Federated Contrastive Learning of Graph-Level Representations
Xiang Li, Gagan Agrawal, Rajiv Ramnath +1
Graph-level representations (and clustering/classification based on these representations) are required in a variety of applications. Examples include identifying malicious network…
KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion Models
Pouyan Navard, Amin Karimi Monsefi, Mengxi Zhou +3
Recent advances in diffusion models have significantly improved text-to-image (T2I) generation, but they often struggle to balance fine-grained precision with high-level control. M…
Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning
Amin Karimi Monsefi, Mengxi Zhou, Nastaran Karimi Monsefi +3
We present a novel frequency-based Self-Supervised Learning (SSL) approach that significantly enhances its efficacy for pre-training. Prior work in this direction masks out pre-def…
DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks
Amin Karimi Monsefi, Kishore Prakash Sailaja, Ali Alilooee +2
In this paper, we introduce DetailCLIP: A Detail-Oriented CLIP to address the limitations of contrastive learning-based vision-language models, particularly CLIP, in handling detai…
DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document Annotation
Ahmad Mohammadshirazi, Ali Nosrati Firoozsalari, Mengxi Zhou +2
Automating the annotation of scanned documents is challenging, requiring a balance between computational efficiency and accuracy. DocParseNet addresses this by combining deep learn…
Recent Advances in Traffic Accident Analysis and Prediction: A Comprehensive Review of Machine Learning Techniques
Noushin Behboudi, Sobhan Moosavi, Rajiv Ramnath
Traffic accidents pose a severe global public health issue, leading to 1.19 million fatalities annually, with the greatest impact on individuals aged 5 to 29 years old. This paper…
Efficient and Interpretable Information Retrieval for Product Question Answering with Heterogeneous Data
Biplob Biswas, Rajiv Ramnath
Expansion-enhanced sparse lexical representation improves information retrieval (IR) by minimizing vocabulary mismatch problems during lexical matching. In this paper, we explore t…
CrashFormer: A Multimodal Architecture to Predict the Risk of Crash
Amin Karimi Monsefi, Pouya Shiri, Ahmad Mohammadshirazi +4
Reducing traffic accidents is a crucial global public safety concern. Accident prediction is key to improving traffic safety, enabling proactive measures to be taken before a crash…
Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain
Amin Karimi Monsefi, Payam Karisani, Mengxi Zhou +5
Standard modern machine-learning-based imaging methods have faced challenges in medical applications due to the high cost of dataset construction and, thereby, the limited labeled…
Novel Physics-Based Machine-Learning Models for Indoor Air Quality Approximations
Ahmad Mohammadshirazi, Aida Nadafian, Amin Karimi Monsefi +2
Cost-effective sensors are capable of real-time capturing a variety of air quality-related modalities from different pollutant concentrations to indoor/outdoor humidity and tempera…
Judge Me in Context: A Telematics-Based Driving Risk Prediction Framework in Presence of Weak Risk Labels
Sobhan Moosavi, Rajiv Ramnath
Driving risk prediction has been a topic of much research over the past few decades to minimize driving risk and increase safety. The use of demographic information in risk predict…
Will there be a construction? Predicting road constructions based on heterogeneous spatiotemporal data
Amin Karimi Monsefi, Sobhan Moosavi, Rajiv Ramnath
Road construction projects maintain transportation infrastructures. These projects range from the short-term (e.g., resurfacing or fixing potholes) to the long-term (e.g., adding a…