117 citations · 121 across the 28 of their papers we have counts for
30 papers
STRAND: Benchmarking and Improving Object-Centric Spatio-Temporal Monitoring in Video Large Language Models
Thong Nguyen, Tri Cao, Khoi Le +4
While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We argue this stems from a failure i…
MatReplace: A Reference-Free, Conditioning-Aligned Benchmark for Material Replacement in Interior Scenes
Mingzhe Du, Thong Thanh Nguyen, Nguyen Tran Cong Duy +2
Material replacement is a common interior-design operation: changing the material of a selected surface while preserving its geometry, surroundings, and illumination. Despite its c…
DynaPix: Can Vision-Language Models Identify the Exact Future?
Thong Nguyen, Vinh-Hien Do, Quynh Vo +2
Acting in a physical scene requires knowing its real later state, not a plausible one. Current evaluations often accept words or a realistic-looking image, so the predicted state i…
Predict, Then Retrieve: Cross-Instance Future-State Retrieval from Video Prefixes
Quynh Vo, Thong Nguyen, Vinh-Hien Do +2
We introduce Predictive State Retrieval (PSR), a task in which a model observes a short video prefix and a temporal question about an object's future state, then retrieves instance…
When Depth Is Better Told Than Shown: Depth-Ordinal Prompting for Vision-Language Spatial Reasoning
Quynh Vo, Phuc Dao, Cong-Duy Nguyen +1
Vision-language models (VLMs) are expected to reason about physical space -- which object is closer, what lies behind what, and how objects are arranged in 3D -- yet they still str…
TIGER: Text-Conditioned Visual Gated Routing with Acceptance Alignment for Multimodal Speculative Decoding
Quynh Vo, Cong-Duy Nguyen, Ponhvoan Srey +2
Speculative decoding accelerates autoregressive generation by letting a lightweight drafter propose multiple tokens that are verified by a larger target model. Although effective f…
WINDQuant: Weight-Informed Neural Decision-Making for Global Mixed-Precision LLM Quantization
Phong Nam Huu Nguyen, Khoi M. Le, Cong-Duy T Nguyen +3
Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in the ultra-low-bit regime rem…
When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
Khoi Le, Tri Cao, Phong Nguyen +5
Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train-test distributions. Therefore,…
Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency
Thong Nguyen, Khoi M. Le, Cong-Duy Nguyen +3
Recent advancements in image animation have utilized diffusion models to breathe life into static images. However, existing controllable frameworks typically rely on Lagrangian mot…
Video Understanding: Through A Temporal Lens
Thong Thanh Nguyen
This thesis explores the central question of how to leverage temporal relations among video elements to advance video understanding. Addressing the limitations of existing methods,…
More Bias, Less Bias: BiasPrompting for Enhanced Multiple-Choice Question Answering
Duc Anh Vu, Thong Nguyen, Cong-Duy Nguyen +2
With the advancement of large language models (LLMs), their performance on multiple-choice question (MCQ) tasks has improved significantly. However, existing approaches face key li…
Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video Understanding
Thong Nguyen, Zhiyuan Hu, Xu Lin +3
Recent years have witnessed outstanding advances of large vision-language models (LVLMs). In order to tackle video understanding, most of them depend upon their implicit temporal u…
TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems
Khang H. N. Vo, Duc P. T. Nguyen, Thong Nguyen +1
This paper focuses on multimodal alignment within the realm of Artificial Intelligence, particularly in text and image modalities. The semantic gap between the textual and visual m…
CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base
Cong-Duy Nguyen, Xiaobao Wu, Duc Anh Vu +3
Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, but they remain susceptible to hallucination, particularly object hallucination…
Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation
Cong-Duy Nguyen, Xiaobao Wu, Thong Nguyen +5
Previous research on multimodal entity linking (MEL) has primarily employed contrastive learning as the primary objective. However, using the rest of the batch as negative samples…
Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation
Thong Thanh Nguyen, Xiaobao Wu, Yi Bin +3
To equip artificial intelligence with a comprehensive understanding towards a temporal world, video and 4D panoptic scene graph generation abstracts visual data into nodes to repre…
Multi-Scale Contrastive Learning for Video Temporal Grounding
Thong Thanh Nguyen, Yi Bin, Xiaobao Wu +4
Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding. To encode video moment…
MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning
Thong Nguyen, Yi Bin, Xiaobao Wu +6
Data quality stands at the forefront of deciding the effectiveness of video-language representation learning. However, video-text pairs in previous data typically do not align perf…
Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives
Thong Nguyen, Yi Bin, Junbin Xiao +6
Humans use multiple senses to comprehend the environment. Vision and language are two of the most vital senses since they allow us to easily communicate our thoughts and perceive t…
Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
Xiaobao Wu, Xinshuai Dong, Liangming Pan +2
Dynamic topic models track the evolution of topics in sequential documents, which have derived various applications like trend analysis and opinion mining. However, existing models…
Encoding and Controlling Global Semantics for Long-form Video Question Answering
Thong Thanh Nguyen, Zhiyuan Hu, Xiaobao Wu +3
Seeking answers effectively for long videos is essential to build video question answering (videoQA) systems. Previous methods adaptively select frames and regions from long videos…
FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model
Xiaobao Wu, Thong Nguyen, Delvin Ce Zhang +2
Topic models have been evolving rapidly over the years, from conventional to recent neural models. However, existing topic models generally struggle with either effectiveness, effi…
KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive Learning
Cong-Duy Nguyen, Thong Nguyen, Xiaobao Wu +1
Previous work on multimodal sentence embedding has proposed multimodal contrastive learning and achieved promising results. However, by taking the rest of the batch as negative sam…
Topic Modeling as Multi-Objective Contrastive Optimization
Thong Nguyen, Xiaobao Wu, Xinshuai Dong +3
Recent representation learning approaches enhance neural topic models by optimizing the weighted linear combination of the evidence lower bound (ELBO) of the log-likelihood and the…