update two recent preprint

README.md

@@ -77,6 +77,8 @@ List format follows:
 3. **ICML (UCLA)** / [Latent Diffusion Energy-Based Model for Interpretable Text Modeling](https://arxiv.org/pdf/2206.05895.pdf) / **G2T**,  use diffusion process on latent space with prior sampling with EBM, variational bayes for latent posterior approximation. Similar paradigm of [S-VAE](https://arxiv.org/pdf/1406.5298.pdf) to deal with labels in semi-supervision. / [Code](https://github.com/yuPeiyu98/LDEBM)
 4. **KBS (Tsinghua)** / [PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generation](https://www.sciencedirect.com/science/article/pii/S0950705122008942) / **G2T**, invent *Broadcasting Net* to repeatly add control signals into latent space to create a concentrate and manipulable latent space in VAE. Experimenced on both RNN and BART VAE models. / [Code](https://github.com/ImKeTT/pcae)
 5. **Arxiv (CUHK)** / [Composable Text Controls in Latent Space with ODEs](https://arxiv.org/abs/2208.00638) / **G2T**, employs diffusion process in the latent space based on adaptive GPT-2 VAE (similar to [AdaVAE](https://arxiv.org/abs/2205.05862)), the diffusion process transfer latent distribution from Gaussian to controlled one. Few parameters and data are used for training. / [Code](https://github.com/guangyliu/LatentOps)
+6. **Arxiv (Cornell)** / [Latent Diffusion for Language Generation](https://arxiv.org/pdf/2212.09462.pdf) / **G2T**,  use class-conditional diffusion process on the continuous space between encoder and decoder of a pre-trained encoder-decoder LM (e.g., BART) . / [Code](https://github.com/justinlovelace/latent-diffusion-for-language)
+7. **Arxiv (UBC)** / [DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation](https://arxiv.org/pdf/2212.08724.pdf) / **G2T**, a duel VAE model with generative and classification components trained jointly, augment the controllable generation ability by producing pseudo data labels and pseudo textual instances / Nan
 
 ### 2021