W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges: sparse large-magnitude activation outliers, and strongly timestep-dependent activation distributions across the multi-st... read more
Sampling from learned high-dimensional distributions is a foundational computational problem. We introduce U-turn chains: Markov chains obtained by iterating short forward-backward steps of a diffusion model, in which each step proposes a move that r... read more
The rapid advancement of diffusion-based image generation models has raised serious concerns regarding potential copyright and privacy infringements involving human-created data. Membership inference attacks (MIAs) have emerged as a promising tool fo... read more
Implicit neural representations have emerged as a promising paradigm for video compression, with recent methods achieving competitive performance on natural video. However, screen content video -- common in remote desktop, online education, and cloud... read more
Accurate pancreas segmentation is critical for early cancer diagnosis, where annotation scarcity necessitates Semi-Supervised Learning (SSL). However, due to significant inter-sample morphological variability, existing SSL methods face severe general... read more
We present BhashaSetu, a linguistically enriched English--Marathi parallel dataset addressing persistent data limitations in low-resource neural machine translation (NMT). Marathi, spoken by over 95 million people, remains underrepresented in high-qu... read more
The rich information underlying graphs has inspired further investigation of unsupervised graph representation. Existing studies mainly depend on node features and topological properties within static graphs to create self-supervised signals, neglect... read more
Flow matching with clean-data prediction has shown that regressing the clean point can exploit low-dimensional structure more effectively than predicting an ambient noised quantity. We ask whether this principle remains useful after images are mapped... read more
In greenhouse tomato production, automated harvesting requires accurate detection of ripe tomatoes, ripeness classification, and precise picking-point localization for robotic end-effectors. This paper proposes YOLO26-RipeLoc Lite, a lightweight deep... read more
Multilevel image thresholding is widely used for segmentation in applications ranging from medical imaging to remote sensing. Classical objective functions, such as Otsu's between-class variance and Kapur's entropy, are often optimized using metaheur... read more
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.