8 citations · 8 across the 19 of their papers we have counts for
19 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…
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 +3
Next Point-of-Interest (POI) recommendation ranks a user's likely next location based on check-in history. Most recent rankers compress the trajectory into a single user vector and…
DeepInterestGR: Mining Deep Multi-Interest Using Multi-Modal LLMs for Generative Recommendation
Yangchen Zeng, Guangyuan Dong, Zhenyu Yu +4
We introduce DeepInterestGR, a novel framework that integrates deep interest mining into the generative recommendation pipeline. This addresses the "Shallow Interest" problem: exis…
DeCorStory: Gram-Schmidt Prompt Embedding Decorrelation for Consistent Storytelling
Ayushman Sarkar, Zhenyu Yu, Mohd Yamani Idna Idris
Maintaining visual and semantic consistency across frames is a key challenge in text-to-image storytelling. Existing training-free methods, such as One-Prompt-One-Story, concatenat…
StoryState: Agent-Based State Control for Consistent and Editable Storybooks
Ayushman Sarkar, Zhenyu Yu, Wei Tang +3
Large multimodal models have enabled one-click storybook generation, where users provide a short description and receive a multi-page illustrated story. However, the underlying sto…
ReDiStory: Region-Disentangled Diffusion for Consistent Visual Story Generation
Ayushman Sarkar, Zhenyu Yu, Chu Chen +3
Generating coherent visual stories requires maintaining subject identity across multiple images while preserving frame-specific semantics. Recent training-free methods concatenate…
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…
From Physics to Foundation Models: A Review of AI-Driven Quantitative Remote Sensing Inversion
Zhenyu Yu, Mohd Yamani Idna Idris, Hua Wang +3
Quantitative remote sensing inversion aims to estimate continuous surface variables-such as biomass, vegetation indices, and evapotranspiration-from satellite observations, support…
A Layered Self-Supervised Knowledge Distillation Framework for Efficient Multimodal Learning on the Edge
Tarique Dahri, Zulfiqar Ali Memon, Zhenyu Yu +6
We introduce Layered Self-Supervised Knowledge Distillation (LSSKD) framework for training compact deep learning models. Unlike traditional methods that rely on pre-trained teacher…
SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discovery
Zhenyu Yu, Mohd. Yamani Idna Idris, Pei Wang +3
We propose SatelliteFormula, a novel symbolic regression framework that derives physically interpretable expressions directly from multi-spectral remote sensing imagery. Unlike tra…
DC4CR: When Cloud Removal Meets Diffusion Control in Remote Sensing
Zhenyu Yu, Mohd Yamani Idna Idris, Pei Wang
Cloud occlusion significantly hinders remote sensing applications by obstructing surface information and complicating analysis. To address this, we propose DC4CR (Diffusion Control…
SatelliteCalculator: A Multi-Task Vision Foundation Model for Quantitative Remote Sensing Inversion
Zhenyu Yu, Mohd. Yamani Idna Idris, Pei Wang
Quantitative remote sensing inversion plays a critical role in environmental monitoring, enabling the estimation of key ecological variables such as vegetation indices, canopy stru…
A Diffusion-Based Framework for Terrain-Aware Remote Sensing Image Reconstruction
Zhenyu Yu, Mohd Yamani Inda Idris, Pei Wang
Remote sensing imagery is essential for environmental monitoring, agricultural management, and disaster response. However, data loss due to cloud cover, sensor failures, or incompl…
Rainy: Unlocking Satellite Calibration for Deep Learning in Precipitation
Zhenyu Yu, Hanqing Chen, Mohd Yamani Idna Idris +1
Precipitation plays a critical role in the Earth's hydrological cycle, directly affecting ecosystems, agriculture, and water resource management. Accurate precipitation estimation…
DanceText: A Training-Free Layered Framework for Controllable Multilingual Text Transformation in Images
Zhenyu Yu, Mohd Yamani Idna Idris, Hua Wang +6
We present DanceText, a training-free framework for multilingual text editing in images, designed to support complex geometric transformations and achieve seamless foreground-backg…
ForgetMe: Evaluating Selective Forgetting in Generative Models
Zhenyu Yu, Mohd Yamani Inda Idris, Pei Wang
The widespread adoption of diffusion models in image generation has increased the demand for privacy-compliant unlearning. However, due to the high-dimensional nature and complex f…