Skip to content
conftrace_

Didi Zhu

10 papers · 2023–2025 · 3 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 ↓
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15) 💎 Century Club · Bronze ⚡ Prolific Year · Productive

Venues

ICML (5) ICLR (3) ICCV (2)

Top co-authors

Kun Kuang (4) Zexi Li (3) Chao Wu (3) Tao Shen (3) Fei Wu (3) Bo Du (2) Dacheng Tao (2) Ziyu Zhao (2) Jinluan Yang (2) Min Zhang (2)

Research topics

Machine Learning (8) Artificial Intelligence (7) Core AI (7) Application Areas (5) Deep Learning (3) Optimization & Theory (3) Architectures (2) Learning Types (2) Computer Vision (1) Core Methods (1) Generation (1) Learning Paradigms (1) Models (1)

Keywords

model merging (3) vision-language model (2) fine tuning (2) catastrophic forgetting (2) parameter clustering (1) text-to-image generation (1) attention mechanism (1) neural network optimization (1) multi-task learning (1) sensitivity analysis (1) semantic alignment (1) backdoor attack (1) low-rank adaptation (1) spurious correlation (1) zero-shot generalization (1) vision transformer (1) stable diffusion (1) parameter importance (1) attention map (1) continual learning (1)

Papers

Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning ICML 2025 Decoding Correlation-Induced Misalignment in the Stable Diffusion Workflow for Text-to-Image Generation ICCV 2025 ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models ICML 2025 Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning ICML 2025 Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering ICLR 2025 Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace ICLR 2025 REMEDY: Recipe Merging Dynamics in Large Vision-Language Models ICLR 2025 ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think ICML 2025 Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models ICML 2024 Universal Domain Adaptation via Compressive Attention Matching ICCV 2023