activity
20242026
collaborators

13 papers

cs.LG2026

When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learning

Thinh T. H. Nguyen, Khoa D. Doan, Binh T. Nguyen +2

Federated class-incremental learning (FCIL) becomes substantially harder when clients observe different label subsets, progress through tasks at different stages, and provide uneve…

cs.CV2026

Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization

Khiem Le, Long Ho, Cuong Do +2

Domain shift is a formidable issue in Machine Learning that causes a model to suffer from performance degradation when tested on unseen domains. Federated Domain Generalization (Fe…

cs.CV2026

ReasonVQA: A Multi-hop Reasoning Benchmark with Structural Knowledge for Visual Question Answering

Duong T. Tran, Trung-Kien Tran, Manfred Hauswirth +1

In this paper, we propose a new dataset, ReasonVQA, for the Visual Question Answering (VQA) task. Our dataset is automatically integrated with structured encyclopedic knowledge and…

cs.LG2025

Edge-Based Predictive Data Reduction for Smart Agriculture: A Lightweight Approach to Efficient IoT Communication

Dora Krekovic, Mario Kusek, Ivana Podnar Zarko +1

The rapid growth of IoT devices has led to an enormous amount of sensor data that requires transmission to cloud servers for processing, resulting in excessive network congestion,…

cs.CL2025

SLM-Bench: A Comprehensive Benchmark of Small Language Models on Environmental Impacts--Extended Version

Nghiem Thanh Pham, Tung Kieu, Duc-Manh Nguyen +3

Small Language Models (SLMs) offer computational efficiency and accessibility, yet a systematic evaluation of their performance and environmental impact remains lacking. We introdu…

cs.CV2025

Collaborative Perceiver: Elevating Vision-based 3D Object Detection via Local Density-Aware Spatial Occupancy

Jicheng Yuan, Manh Nguyen Duc, Qian Liu +2

Vision-based bird's-eye-view (BEV) 3D object detection has advanced significantly in autonomous driving by offering cost-effectiveness and rich contextual information. However, exi…