Kai Liu

Affiliations:
  • Tencent Hunyuan3D, Tencent AIPD


According to our database1, Kai Liu authored at least 15 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Reinforcement Learning on Pre-Training Data.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning.
CoRR, November, 2025

HunyuanOCR Technical Report.
CoRR, November, 2025

SpecExit: Accelerating Large Reasoning Model via Speculative Exit.
CoRR, September, 2025

Tequila: Trapping-free Ternary Quantization for Large Language Models.
CoRR, September, 2025

Reinforcement Learning on Pre-Training Data.
CoRR, September, 2025

HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels.
CoRR, July, 2025

Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material.
CoRR, June, 2025

Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation.
CoRR, January, 2025

PEARL: Parallel Speculative Decoding with Adaptive Draft Length.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Parallel Speculative Decoding with Adaptive Draft Length.
CoRR, 2024

Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding.
CoRR, 2024

2023
E-Sparse: Boosting the Large Language Model Inference through Entropy-based N: M Sparsity.
CoRR, 2023

EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

2022
MKQ-BERT: Quantized BERT with 4-bits Weights and Activations.
CoRR, 2022


  Loading...