Kaiwen Zheng (@zkwthu) 's Twitter Profile
Kaiwen Zheng

@zkwthu

Ph.D. student at Tsinghua University

ID: 1525686195614646273

linkhttps://zhengkw18.github.io/ calendar_today15-05-2022 03:55:22

21 Tweet

58 Followers

14 Following

AK (@_akhaliq) 's Twitter Profile Photo

DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics paper page: huggingface.co/papers/2310.13… Diffusion probabilistic models (DPMs) have exhibited excellent performance for high-fidelity image generation while suffering from inefficient sampling. Recent works

DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics

paper page: huggingface.co/papers/2310.13…

Diffusion probabilistic models (DPMs) have exhibited excellent performance for high-fidelity image generation while suffering from inefficient sampling. Recent works
AK (@_akhaliq) 's Twitter Profile Photo

Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis paper page: huggingface.co/papers/2312.03… In text-to-speech (TTS) synthesis, diffusion models have achieved promising generation quality. However, because of the pre-defined data-to-noise diffusion process, their

Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis

paper page: huggingface.co/papers/2312.03…

In text-to-speech (TTS) synthesis, diffusion models have achieved promising generation quality. However, because of the pre-defined data-to-noise diffusion process, their
Vidu AI (@viduai_official) 's Twitter Profile Photo

Multimodal AI With New Emergence! We're thrilled to launch Vidu-1.5 next week, the world’s first multimodal model to support Multi-Entity Consistency! Vidu-1.5 can seamlessly integrate people, objects, and environments to generate stunning videos, overturning traditional

Yin Cui (@yincuicv) 's Twitter Profile Photo

Is self-improvement exclusive to RL? Can we use supervised learning to match LLMs trained with SOTA RL algorithms? In Negative-aware Fine-Tuning (NFT), we introduce a purely supervised learning method to enhance LLMs' math reasoning with no external teachers. NFT matches or

Is self-improvement exclusive to RL?

Can we use supervised learning to match LLMs trained with SOTA RL algorithms?

In Negative-aware Fine-Tuning (NFT), we introduce a purely supervised learning method to enhance LLMs' math reasoning with no external teachers. NFT matches or