Chen Jin

Researcher@Astrazeneca·英国·OpenReview

研究方向

diffusion model · vision-language model · hallucination · foundation model · deep learning · segmentation · histology image · attentation · stochastic modelling · image reconstruction

6.5

Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

ICLR 2026Withdrawn

5.0

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

ICLR 2026Withdrawn

通讯

3.3

合作者 (20)

Philip Alexander Teare

Chen Jin

Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

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

Protein generation with embedding learning for motif diversification

Diffusion Instruction Tuning

Balancing Act: Diversity and Consistency in Large Language Model Ensembles

Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?

DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations

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