Peiran Dong

5 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 (11)

Venues

ICLR (2) NeurIPS (2) ICML (1)

Top co-authors

Song Guo (5) Jie Zhang (3) Yue Yu (2) Bingjie WANG (2) Jiewei Zhang (2) Ziming Liu (2) Junxiao Wang (2) Zicong Hong (1) Xueyang Tang (1) Sikai Bai (1)

Research topics

Artificial Intelligence (4) Core AI (4) Deep Learning (3) Models (3) Computer Vision (2) Generation (2) Machine Learning (1) Natural Language Processing (1) Analysis (1) Learning Types (1) Resources & Methods (1)

Keywords

diffusion model (2) large language model (2) test-time adaptation (1) safety alignment (1) model alignment (1) adversarial attack (1) spurious correlation (1) cross-attention map (1) image purification (1) clip guidance (1) concept transfer (1) attention map refinement (1) entity localization (1) concept negation (1) generative refusal (1) causal representation editing (1) safe content generation (1) anchoring (1) concept bleeding (1) object detection network (1)

Papers

Causally Motivated Sycophancy Mitigation for Large Language Models ICLR 2025 Durable Quantization Conditioned Misalignment Attack on Large Language Models ICLR 2025 Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring ICML 2024 Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing NeurIPS 2024 Towards Test-Time Refusals via Concept Negation NeurIPS 2023