Kai Yu

9

Papers

199

Total Citations

Papers (9)

SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

NeurIPS 2025arXiv

Reducing Tool Hallucination via Reliability Alignment

Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism

Bitrate-Controlled Diffusion for Disentangling Motion and Content in Video

Evolving Subnetwork Training for Large Language Models

VQTalker: Towards Multilingual Talking Avatars Through Facial Motion Tokenization

UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding

DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion Priors