8 papers
Evaluating self-supervised echocardiographic representations across downstream extraction strategies for left-ventricular segmentation and ejection fraction estimation
Sylwia Majchrowska, Philip Teare
Self-supervised learning (SSL) is increasingly used in medical imaging to reduce annotation requirements, but representation quality is often judged using a single downstream evalu…
Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding
Yanzheng Xiang, Lan Wei, Yizhen Yao +8
Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelism often harms quality. Revocable decod…
Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation
Lei Tong, Zhihua Liu, Chaochao Lu +5
We present Causal-Adapter, a modular framework that adapts frozen text-to-image diffusion backbones for counterfactual image generation. Our method supports causal interventions on…
CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute
Chen Jin, Ryutaro Tanno, Tom Diethe +1
Large Language Models (LLMs) often rely on test-time scaling via parallel decoding (for example, 512 samples) to boost reasoning accuracy, but this incurs substantial compute. We i…
Protein generation with embedding learning for motif diversification
Kevin Michalewicz, Chen Jin, Philip Alexander Teare +4
A fundamental challenge in protein design is the trade-off between generating structural diversity while preserving motif biological function. Current state-of-the-art methods, suc…
Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States
Qinglin Zhu, Yizhen Yao, Runcong Zhao +7
Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired app…