ControlFoley, released by Xiaomi's large‑model team, is an open‑source framework that lets creators generate video‑aligned sound effects while explicitly controlling content, style, and timing through text prompts, video dubbing, or reference audio, achieving SOTA performance on multiple benchmarks.
This article reviews the DigMA model, which uses a diffusion‑guided meta‑agent to generate high‑fidelity, controllable order‑flow data for financial markets, details its problem formulation, architecture, training on Chinese stock datasets, extensive experiments—including reinforcement‑learning‑based high‑frequency trading evaluation—and demonstrates its superior accuracy and ultra‑low latency generation.
DynamicFace introduces a diffusion‑based framework that explicitly decouples identity, pose, expression, illumination and background using composable 3D facial priors, achieving superior identity preservation, motion consistency and visual fidelity in both image and video face‑swapping tasks.
DynamicFace introduces a controllable face‑swapping framework that leverages composable 3D facial priors, dual‑stream identity injection, and a FusionTVO module to achieve superior image and video quality, identity preservation, and temporal consistency, outperforming existing state‑of‑the‑art methods on benchmark datasets.
Researchers introduce CineMaster, a SIGGRAPH‑2025 paper presenting a 3D‑aware, controllable text‑to‑video generation framework that lets users define target objects and camera motions via an interactive workflow, enabling cinematic video creation with high‑quality, user‑directed results.
This article analyzes how large‑model AIGC reshapes the production, evaluation, and deployment of advertising creatives on Xiaohongshu, detailing the business motivations, technical pipeline, controllable generation, reward‑model filtering, and experimental results that balance commercial efficiency with community tone.
The 360 AI Research Institute introduces HiCo, a hierarchical controllable diffusion model that enables fine‑grained layout control across up to eight image regions, integrates seamlessly with existing Stable Diffusion ecosystems, and demonstrates superior performance on the GRIT‑VAL benchmark for layout‑aware image synthesis.
