ORCA: Hunting Compositional Failures in Text-to-Image Diffusion paper

Compositional failures in text-to-image diffusion come from misaligned information, not missing information. One auxiliary loss aligns the diffusion latent with a low-rank visual target, steered by the T5 minus CLIP residual.

TDGNet: Hallucination Detection in Diffusion Language Models via Temporal Dynamic Graphs paper

Hallucination in diffusion language models is visible in the denoising trajectory before it reaches the output. TDGNet reads that trajectory as a temporal dynamic graph.

3D-Guided Scalable Flow Matching for Generating Volumetric Tissue Spatial Transcriptomics from Serial Histology paper

HoloTea imputes spot-level gene expression from H&E while looking at the neighbouring sections: morphologically matching spots on adjacent slides are retrieved and fused through a lightweight ControlNet, so the conditioning follows anatomical continuity rather than treating each slice as an island.

An application guide, from two years of getting it wrong

Everything I learned applying for a master's and then a PhD from Iran: papers, GPA, emails, statements, funding, and the part nobody writes down, which is what it does to you.

VAGUE-Gate: A Plug-and-Play Local-Privacy Shield for Retrieval-Augmented Generation paper

A client-side epsilon-local differential privacy gate that rewrites retrieved context before it reaches the model, preserving end-to-end guarantees under post-processing across 32 pipeline variants.

Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models paper

IllusionBench hides letters, faces and animals inside ordinary scenes. Human annotators read the shapes almost perfectly; leading vision-language models do not.