24 citations · 66 across the 26 of their papers we have counts for
30 papers
How Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning Benchmark
Bach Nguyen, Zhaonan Li, Mau Son Nguyen +5
Real-world reasoning rarely reduces to static question answering: agents must actively gather information from tools and sensors that are often noisy and unreliable. Yet most exist…
Gripper-aware Vision Language Action Models
Hanyi Zhang, Zihong Luo, Tianyu Li +16
Vision language action models (VLAs) have advanced general purpose robotic grasping and manipulation by enabling robots to interpret visual observations and natural language instru…
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…
Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think
Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha +18
Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose pro…
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…
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…
CodeGraphVLP: Code-as-Planner Meets Semantic-Graph State for Non-Markovian Vision-Language-Action Models
Khoa Vo, Sieu Tran, Taisei Hanyu +8
Vision-Language-Action (VLA) models promise generalist robot manipulation, but are typically trained and deployed as short-horizon policies that assume the latest observation is su…
Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning
Chi-Yao Huang, Khoa Vo, Aayush Atul Verma +2
Training a single network with multiple objectives often leads to conflicting gradients that degrade shared representations, forcing them into a compromised state that is suboptima…
Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Grounding
Khoa Vo, Taisei Hanyu, Yuki Ikebe +8
Recent Vision-Language-Action (VLA) models have made impressive progress toward general-purpose robotic manipulation by post-training large Vision-Language Models (VLMs) for action…
Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective
Nhat Chung, Taisei Hanyu, Toan Nguyen +9
As embodied agents operate in increasingly complex environments, the ability to perceive, track, and reason about individual object instances over time becomes essential, especiall…
SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation
Taisei Hanyu, Nhat Chung, Huy Le +10
Inspired by how humans reason over discrete objects and their relationships, we explore whether compact object-centric and object-relation representations can form a foundation for…
Joint-Local Grounded Action Transformation for Sim-to-Real Transfer in Multi-Agent Traffic Control
Justin Turnau, Longchao Da, Khoa Vo +4
Traffic Signal Control (TSC) is essential for managing urban traffic flow and reducing congestion. Reinforcement Learning (RL) offers an adaptive method for TSC by responding to dy…
Amodal Instance Segmentation with Diffusion Shape Prior Estimation
Minh Tran, Khoa Vo, Tri Nguyen +1
Amodal Instance Segmentation (AIS) presents an intriguing challenge, including the segmentation prediction of both visible and occluded parts of objects within images. Previous met…
Error Detection and Constraint Recovery in Hierarchical Multi-Label Classification without Prior Knowledge
Joshua Shay Kricheli, Khoa Vo, Aniruddha Datta +2
Recent advances in Hierarchical Multi-label Classification (HMC), particularly neurosymbolic-based approaches, have demonstrated improved consistency and accuracy by enforcing cons…
HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model
Khoa Vo, Thinh Phan, Kashu Yamazaki +2
Current video-language models (VLMs) rely extensively on instance-level alignment between video and language modalities, which presents two major limitations: (1) visual reasoning…
ShapeFormer: Shape Prior Visible-to-Amodal Transformer-based Amodal Instance Segmentation
Minh Tran, Winston Bounsavy, Khoa Vo +3
Amodal Instance Segmentation (AIS) presents a challenging task as it involves predicting both visible and occluded parts of objects within images. Existing AIS methods rely on a bi…
ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection
Thinh Phan, Khoa Vo, Duy Le +3
Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with…
Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
Kashu Yamazaki, Taisei Hanyu, Khoa Vo +5
Precise 3D environmental mapping is pivotal in robotics. Existing methods often rely on predefined concepts during training or are time-intensive when generating semantic maps. Thi…
Contextual Explainable Video Representation: Human Perception-based Understanding
Khoa Vo, Kashu Yamazaki, Phong X. Nguyen +3
Video understanding is a growing field and a subject of intense research, which includes many interesting tasks to understanding both spatial and temporal information, e.g., action…
CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection
Hyekang Kevin Joo, Khoa Vo, Kashu Yamazaki +1
Video anomaly detection (VAD) -- commonly formulated as a multiple-instance learning problem in a weakly-supervised manner due to its labor-intensive nature -- is a challenging pro…
VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning
Kashu Yamazaki, Khoa Vo, Sang Truong +2
Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling. Following the human p…