Lei Tong — accepted AI-conference papers

2026

Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation

Lei Tong, Zhihua Liu, Chaochao Lu, Dino Oglic, Tom Diethe, Philip Teare +2

ICML 2026poster

We present Causal-Adapter, a modular framework that adapts frozen text-to-image diffusion backbones for counterfactual image generation. Our method enables causal interventions on target attributes while preserving all other aspects of the image, including the core identity. In contrast to prior app…

Cited by 0 Source ↗Scholar ↗

2025

Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation

Zhihua Liu, Amrutha Saseendran, Lei Tong, Xilin He, Fariba Yousefi, Nikolay Burlutskiy +5

ICML 2025poster

Open-set image segmentation poses a significant challenge because existing methods often demand extensive training or fine-tuning and generally struggle to segment unified objects consistently across diverse text reference expressions. Motivated by this, we propose Segment Anyword, a novel training-…

Cited by 0 Source ↗PDF ↗Scholar ↗