Hongyi Wang
26 papers · 2018–2026 · 10 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 ↓+11 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (51) π Conference Polyglot Β· Gold π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Grand Slam
π
Triple Crown
π
Keyword Champion
π§
Keyword Pioneer
π₯
Mega-Team Β· Legion
π
Renaissance Researcher
(9)
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(136)
Venues
Top co-authors
Research topics
Machine Learning
(20)
Artificial Intelligence
(15)
Deep Learning
(15)
Application Areas
(13)
Optimization & Theory Β· Machine Learning
(11)
Core AI
(8)
Learning Paradigms Β· Artificial Intelligence
(8)
Optimization & Theory Β· Deep Learning
(7)
Architectures
(6)
Learning Types
(4)
Computer Vision
(3)
Learning Paradigms Β· Machine Learning
(3)
Models
(3)
Computer Science
(2)
Mathematics & Optimization
(2)
Keywords
federated learning
(6)
distributed training
(6)
model compression
(4)
large language model
(4)
vision-language model
(3)
model parallelism
(2)
byzantine resilience
(2)
communication efficiency
(2)
gradient aggregation
(2)
neural network optimization
(2)
byzantine fault tolerance
(2)
variational inference
(1)
stochastic gradient descent
(1)
transfer learning
(1)
neural network training
(1)
adversarial robustness
(1)
lottery ticket hypothesis
(1)
vision transformer
(1)
attention mechanism
(1)
adversarial learning
(1)
Papers
Taming the Phantom: Token-Asymmetric Filtering for Hallucination Mitigation in Large Vision-Language Models
AAAI 2026
AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving
EMNLP 2025
Dissecting and Streamlining the Interactive Loop of Mobile Cloud Gaming
NSDI 2025
M2OST: Many-to-one Regression for Predicting Spatial Transcriptomics from Digital Pathology Images
AAAI 2025
Region-aware Anchoring Mechanism for Efficient Referring Visual Grounding
ICCV 2025
Token Level Routing Inference System for Edge Devices
ACL 2025
Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild
NeurIPS 2024
FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations
NeurIPS 2024
Fusing Models with Complementary Expertise
ICLR 2024
Maestro: Uncovering Low-Rank Structures via Trainable Decomposition
ICML 2024
Position: TrustLLM: Trustworthiness in Large Language Models
ICML 2024
RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs
NAACL 2024
SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning
NeurIPS 2024
Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach
ICLR 2023
FedNAR: Federated Optimization with Normalized Annealing Regularization
NeurIPS 2023
MPCFORMER: FAST, PERFORMANT AND PRIVATE TRANSFORMER INFERENCE WITH MPC
ICLR 2023
SLViT: Scale-Wise Language-Guided Vision Transformer for Referring Image Segmentation
IJCAI 2023
AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness
NeurIPS 2022
Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation
EMNLP 2022
Rare Gems: Finding Lottery Tickets at Initialization
NeurIPS 2022
Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
NeurIPS 2020
Federated Learning with Matched Averaging
ICLR 2020
DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation
NeurIPS 2019
ATOMO: Communication-efficient Learning via Atomic Sparsification
NeurIPS 2018
DRACO: Byzantine-resilient Distributed Training via Redundant Gradients
ICML 2018
The Effect of Network Width on the Performance of Large-batch Training
NeurIPS 2018