8 citations · 13 across the 9 of their papers we have counts for
10 papers
Measuring the Reasoning-Action Coupling in Driving Vision-Language-Action Models through Counterfactuals
Gabriel Manalu, Saad Wazir, Thao Do +4
Driving vision-language-action (VLA) models bring an appealing form of explainability to a safety-critical domain, since a system that can state the reasons for its maneuvers offer…
FIBER: A Differentially Private Optimizer with Filter-Aware Innovation Bias Correction
Duc Dm, Thao Do, Minh Son Hoang +3
Differentially private (DP) training protects individual examples by adding noise to gradients, but the injected noise interacts nontrivially with adaptive optimizers. Recent DP me…
SAT: Selective Aggregation Transformer for Image Super-Resolution
Dinh Phu Tran, Thao Do, Saad Wazir +3
Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attenti…
EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question Answering
Thao Do, Dinh Phu Tran, An Vo +2
Efficient context compression is critical for retrieval-augmented question answering in resource-constrained settings, where long retrieved contexts increase latency, memory use, a…
Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering
Dinh Phu Tran, Jihoon Jeong, Saad Wazir +4
We present a formal problem formulation for \textit{Reliable} Audio-Visual Question Answering (-AVQA), where we prefer abstention over answering incorrectly. While rec…
VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization
Son Nguyen, Giang Nguyen, Hung Dao +2
Key Information Extraction (KIE) underpins the understanding of visual documents (e.g., receipts and contracts) by extracting precise semantic content and accurately capturing spat…
Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition
Thao Do, Dinh Phu Tran, An Vo +1
Extracting fine-grained OCR text from aged documents in diacritic languages remains challenging due to unexpected artifacts, time-induced degradation, and lack of datasets. While s…
QuickBrowser: A Unified Model to Detect and Read Simple Object in Real-time
Thao Do, Daeyoung Kim
There are many real-life use cases such as barcode scanning or billboard reading where people need to detect objects and read the object contents. Commonly existing methods are fir…
Smart Inference for Multidigit Convolutional Neural Network based Barcode Decoding
Thao Do, Yalew Tolcha, Tae Joon Jun +1
Barcodes are ubiquitous and have been used in most of critical daily activities for decades. However, most of traditional decoders require well-founded barcode under a relatively s…
Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization
Giang Nguyen, Shuan Chen, Thao Do +3
Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human l…