18 papers
Do Vision Models Truly Forget? New Findings from Representation-Level Certification of Visual Unlearning in Vertical Federated Learning
Zhenyu Yu, Yangchen Zeng, Chunlei Meng +2
Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics. We challenge thes…
Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies
Ayushman Sarkar, Zhenyu Yu, Mohd Yamani Idna Idris
Visual reasoning matters for many computer vision tasks that go beyond surface-level object detection and classification. Despite progress in relational, symbolic, temporal, causal…
TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation
Yangchen Zeng, Hao Peng, Rongfeng Guo +3
We introduce TriAlignGR, a unified multitask-multimodal framework for generative recommendation that establishes two-stage multimodal semantic propagation: (i) encoding visual sema…
Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection
Yangchen Zeng, Zhenyu Yu, Dongming Jiang +5
Transformer-based detectors have advanced small-object detection, but they often remain inefficient and vulnerable to background-induced query noise, which motivates deep decoders…
ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation
Zhenyu Yu, Chunlei Meng, Yangchen Zeng +2
Next point-of-interest (POI) recommendation requires modeling user mobility as a spatiotemporal sequence, where different behavioral factors may evolve at different temporal and sp…
CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation
Zhenyu Yu, Chunlei Meng, Yangchen Zeng +2
Next Point-of-Interest (POI) recommendation plays a crucial role in location-based services by predicting users' future mobility patterns. Existing methods typically compute a sing…