Browsing: Hugging Face
The Disentangled Geometry-editable and Appearance-preserving Diffusion (DGAD) model effectively integrates target objects into background scenes by using semantic embeddings for…
Autoregressive (AR) image generation models have gained increasing attention for their breakthroughs in synthesis quality, highlighting the need for robust…
OminiAbnorm-CT, a model for automated interpretation of CT images, outperforms existing methods in localizing and describing abnormalities across different body…
The framework $\Psi$-Sampler uses SMC with pCNL for efficient posterior sampling and reward alignment in score-based generative models, enhancing performance…
SuperWriter-Agent enhances long-form text generation by integrating structured planning and refinement, achieving top performance with a 7B model and hierarchical…
Direct Preference Optimization (DPO) has recently been applied as a post-training technique for text-to-video diffusion models. To obtain training data,…
RefEdit, an instruction-based editing model trained on synthetic data, outperforms baselines in complex scene editing and referring expression tasks. Despite…
FlowPathAgent, a neurosymbolic agent, enhances the reliability of LLM predictions for flowchart interpretation by tracing specific components and generating accurate…
Critique-GRPO, an RL framework combining numerical and natural language feedback, enhances LLM reasoning across tasks and outperforms existing methods. Recent…
A dynamic layerwise pruning method adaptively determines layer importance by combining model weights and activation information to maintain performance in…