Taihang Hu

6 papers · 2024–2025 · 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 (16)

Venues

NeurIPS (3) ICCV (2) ICLR (1)

Top co-authors

Jian Yang (4) yaxing wang (4) Joost van de Weijer (3) Ming-Ming Cheng (3) Hongcheng Gao (3) Linxuan Li (3) Senmao Li (2) Fahad Shahbaz Khan (2) Kai Wang (2) Jiadong Pan (1)

Research topics

Machine Learning (6) Deep Learning (5) Models (5) Computer Vision (3) Generation (3) Learning Types (3) Artificial Intelligence (2) Core AI (2) Application Areas (1) Core Methods (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1) Processing (1)

Keywords

diffusion model (4) image generation (2) contrastive learning (1) catastrophic forgetting (1) model unlearning (1) image synthesis (1) image editing (1) text-to-image generation (1) machine unlearning (1) generative model (1) autoregressive model (1) latent space (1) text embedding (1) text-to-image diffusion (1) inference acceleration (1) concept erasure (1) encoder feature (1) token merging (1) parallel decoding (1) malicious fine-tuning (1)

Papers

Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing ICCV 2025 Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts ICCV 2025 Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference NeurIPS 2024 Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models ICLR 2024 Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning NeurIPS 2024 Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis NeurIPS 2024