Peng Zhang
PulseAugur coverage of Peng Zhang — every cluster mentioning Peng Zhang across labs, papers, and developer communities, ranked by signal.
-
Wan-Animate-2 framework enhances character animation with direct video input
Researchers have introduced Wan-Animate-2, a novel framework for character animation that directly processes driving videos using a redesigned Diffusion Transformer. This approach enhances motion generation fidelity and…
-
Wan-Dancer framework generates minute-scale coherent dance videos from music
Researchers have introduced Wan-Dancer, a novel framework capable of generating long-duration, high-quality dance videos from music. This method ensures temporal continuity and global structure by decoupling the process…
-
Apple researchers unveil new method for synchronized text-to-video-audio generation
Researchers have developed a new framework called the Cross-Referential Rewriter (CRR) to improve text-to-sounding-video (T2SV) generation. This dual-agent system addresses challenges in aligning video and audio generat…
-
Notion, Salesforce, Uber scale AI with Anyscale's Ray framework
Anyscale hosted Ray Day Seattle, showcasing how companies like Notion and Salesforce are using the Ray framework to scale AI workloads. Notion significantly reduced embedding costs by 80% and improved query latency by m…