9 papers
GEOSTEER: Geodesic Optimization for Activation Steering in Large Language Models
Xuan Cuong Ngo, Hao Vo, Ngan Le
Activation steering provides a lightweight way to control large language models (LLMs) by modifying their hidden activations at inference time. Among these approaches, norm-preserv…
TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation
Duc Nguyen, Sieu Tran, Hao Vo +6
Unsupervised video object-centric learning aims to decompose dynamic scenes into temporally persistent entity representations. Existing recurrent video slot-attention methods propa…
MVDGC: Joint 3D and 2D Multi-view Pedestrian Detection via Dual Geometric Constraints
Thinh Phan, Hao Vo, Khoa Vo +3
The core challenge in multi-view pedestrian detection (MVPD) lies in effective aggregation of visual features from different viewpoints for robust occlusion reasoning. Recent appro…
OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs
Hao Vo, Phu Loc Nguyen, Khoa Vo +7
Multimodal Large Language Models (MLLMs) have achieved remarkable performance on 2D visual tasks, yet enhancing their spatial intelligence for real-world applications such as Auton…
DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
Hao Vo, Khoa Vo, Phu Loc Nguyen +10
Spatiotemporal intelligence in autonomous driving (AD) requires an agent to integrate multi-view observations into a coherent scene representation, maintain object continuity acros…
ARGUSTRACK: A Multi-View Annotation System for Multi-Object Tracking
Hao Vo, Duc Nguyen, Ngan Le
Multi-Camera Multi-Target (MCMT) tracking has emerged as a critical capability for applications ranging from autonomous driving to animal behavior monitoring. While recent advances…
Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning
Sieu Tran, Duc Nguyen, Hao Vo +2
Unsupervised video object-centric learning aims to decompose dynamic scenes into persistent, object-level representations without supervision. However, existing slot-based methods…
SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection
Hao Vo, Khoa Vo, Thinh Phan +5
Camera-only 3D object detection has emerged as a cost-effective and scalable alternative to LiDAR for autonomous driving, yet existing methods primarily prioritize overall performa…
AgentSGEN: Multi-Agent LLM in the Loop for Semantic Collaboration and GENeration of Synthetic Data
Vu Dinh Xuan, Hao Vo, David Murphy +1
The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical an…