'LLMs/Diffusion' 카테고리의 글 목록

Research Proposal

보호글 2026. 5. 9. 18:51

보호되어 있는 글입니다.

[CDPG] Controlling Conditional Language Models

LLMs/Diffusion 2026. 5. 9. 15:37

역시 읽은지 오래 되어서, 다시 읽음. (ICML 2022)(To be continued...) DPG 먼저 하고, 그리고 나서 CDPG 로...

[KL-Adaptive DPG w/ baseline] RL and DM for Fine-tuning LMs

LLMs/Diffusion 2026. 5. 9. 15:29

역시 읽은지 꽤 오래 되어서, 다시 읽음.(NeurIPS 2022)

[KL-Adaptive DPG] Distributional Approach to Controlled Text Generation

LLMs/Diffusion 2026. 5. 9. 15:20

읽은지 꽤 오래되어서, 다시 읽었다. (ICLR 2021)

[D-CFG] Simple Guidance Mechanism for Discrete Diffusion Models

LLMs/Diffusion 2026. 5. 8. 18:14

(ICLR 2025)https://github.com/kuleshov-group/discrete-diffusion-guidance GitHub - kuleshov-group/discrete-diffusion-guidance: Simple Guidance Mechanisms for Discrete Diffusion ModelsSimple Guidance Mechanisms for Discrete Diffusion Models - kuleshov-group/discrete-diffusion-guidancegithub.com

[d1] Scaling Reasoning in dLLMs via RL

LLMs/Diffusion 2026. 5. 7. 18:31

https://dllm-reasoning.github.io/ d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement LearningTable below shows the detailed performance comparison across different benchmarks and generation sequence lengths. d1-LLaDA consistently outperforms all other models, with diffu-GRPO showing better performance than SFT alone. Table: Model performance on GSdllm-reasoning.github.io(..

[LLaDA] Large Language Diffusion Models

LLMs/Diffusion 2026. 5. 7. 13:57

(NeurIPS 2025)https://ml-gsai.github.io/LLaDA-demo/ LLaDA - Large Language Diffusion ModelsLLaDA is a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance.ml-gsai.github.io

ABOUT ME

밤에 쓰는 편지 밤에 쓰는 편지

티스토리툴바