Didi Zhu

Orcid: 0009-0004-6892-5357

According to our database1, Didi Zhu authored at least 37 papers between 2021 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence.
CoRR, May, 2026

Watch Wider and Think Deeper: Collaborative Cross-modal Chain-of-Thought for Complex Visual Reasoning.
CoRR, January, 2026

Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-task Learning.
Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1, 2026

2025
OmniEduBench: A Comprehensive Chinese Benchmark for Evaluating Large Language Models in Education.
CoRR, October, 2025

Noise Projection: Closing the Prompt-Agnostic Gap Behind Text-to-Image Misalignment in Diffusion Models.
CoRR, October, 2025

FedMcon: an adaptive aggregation method for federated learning via meta controller.
Frontiers Inf. Technol. Electron. Eng., August, 2025

FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning.
CoRR, August, 2025

Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices.
CoRR, March, 2025

Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model.
CoRR, March, 2025

Generative Artificial Intelligence in Robotic Manipulation: A Survey.
CoRR, March, 2025

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging.
CoRR, February, 2025

Let Human Sketches Help: Empowering Challenging Image Segmentation Task with Freehand Sketches.
CoRR, January, 2025

Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning.
CoRR, January, 2025

FedGuCci: Making Local Models More Connected in Landscape for Federated Learning.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.2, 2025

ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

REMEDY: Recipe Merging Dynamics in Large Vision-Language Models.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Decoding Correlation-Induced Misalignment in the Stable Diffusion Workflow for Text-to-Image Generation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

2024
Towards Effective Clustered Federated Learning: A Peer-to-Peer Framework With Adaptive Neighbor Matching.
IEEE Trans. Big Data, December, 2024

Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning.
CoRR, 2024

Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering.
CoRR, 2024

Improving Group Connectivity for Generalization of Federated Deep Learning.
CoRR, 2024

RESMatch: Referring Expression Segmentation in a Semi-Supervised Manner.
CoRR, 2024

An Adaptive Aggregation Method for Federated Learning via Meta Controller.
Proceedings of the 6th ACM International Conference on Multimedia in Asia, Workshops, 2024

Neural Collapse Anchored Prompt Tuning for Generalizable Vision-Language Models.
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023
Bridging the Gap: Neural Collapse Inspired Prompt Tuning for Generalization under Class Imbalance.
CoRR, 2023

Universal Domain Adaptation via Compressive Attention Matching.
CoRR, 2023

Generalized Universal Domain Adaptation with Generative Flow Networks.
Proceedings of the 31st ACM International Conference on Multimedia, 2023

Quantitatively Measuring and Contrastively Exploring Heterogeneity for Domain Generalization.
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

Universal Domain Adaptation via Compressive Attention Matching.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022
Mining Latent Relationships among Clients: Peer-to-peer Federated Learning with Adaptive Neighbor Matching.
CoRR, 2022

2021
Ensemble Federated Adversarial Training with Non-IID data.
CoRR, 2021


  Loading...