Shangguang Wang
11 papers · 2015–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Academic Marathon Β· Half π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (22) π Conference Polyglot Β· Silver β‘ Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Renaissance Researcher
(6)
Top co-authors
Research topics
Keywords
large language model
(3)
membership inference attack
(3)
black-box attack
(2)
multimodal large language model
(2)
remote sensing
(1)
parameter sharing
(1)
variational inference
(1)
cloud removal
(1)
multimodal learning
(1)
diffusion model
(1)
mixture of expert
(1)
adversarial attack
(1)
temporal dependency
(1)
privacy protection
(1)
hallucination reduction
(1)
retrieval-augmented generation
(1)
inference acceleration
(1)
task interference
(1)
entity relationship
(1)
feature extraction
(1)
Papers
Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models
ACL 2026
Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Models
CVPR 2026
Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation
ACL 2026
Robust Membership Inference for Large Language Models under Adversarial Generative Corruption
ACL 2026
SCo-Cloud: Satellite Constellation Collaboration for Cloud-Aware Onboard-Computed Imaging and Transmission
AAAI 2026
SwiftEP: Accelerating MoE Inference with Buffer Fusion and TMA Offloading
NSDI 2026
Multimodal Knowledge Retrieval-Augmented Iterative Alignment for Satellite Commonsense Conversation
IJCAI 2025
Variational Multi-Modal Hypergraph Attention Network for Multi-Modal Relation Extraction
IJCAI 2025
SILENCE: Protecting privacy in offloaded speech understanding on resource-constrained devices
NeurIPS 2024
Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing With Non-Learnable Primitives
CVPR 2023
Re-Ranking Voting-Based Answers by Discarding User Behavior Biases
IJCAI 2015