Robuta

Oct 22, 2024 - Adapter-based Parameter-Efficient Training for V&L tasks - *[CVPR 2022](https://cvpr2022.thecvf.com)*

Dopple.ai is the premier AI platform bringing fictional worlds to life. Engage in meaningful conversations with iconic characters, seek guidance from virtual...

Sep 29, 2025 - a unified framework that bridges multimodal LLMs and diffusion models with patch-level CLIP latents

Jaemin Cho Academic website.

Sep 16, 2025 - a framework that automatically constructs and leverages skill-aware CoT supervisions for domain-adaptive video reasoning

Aug 6, 2024 - Using LLM (GPT-4) to generate a 'diagram plan' for fine-grained layouts (object/text labels/arrows, etc.) and render in either raster images (via diffusion)...

Kisah perjuangan hidup seorang namja bernama Jaemin. Semenjak umur 10 tahun ia sudah di benci oleh keluarganya. Bahkan menginjak usia remaja ia sudah sering...

Feb 11, 2025 - Vision-and-Language modeling without text, by using a transformer which takes only raw visual and audio inputs - *[NeurIPS 2022](https://nips.cc/) (Oral)*

Feb 5, 2024 - Hot Jaemin solo sex scene - boy wanna suck / 재민 엔시티

May 12, 2024 - Text-to-Image Generation via predicting vector-quantized image patches with multimodal LMs - *[EMNLP 2020](https://2020.emnlp.org/)*

May 12, 2024 - Propose a hierarchical VAE model and utterance drop regularization to mitigate posterior collapse problem - *[NAACL 2018](http://naacl.org/naacl-hlt-2018/)*...

Aug 6, 2024 - EnvGen is a novel framework that uses LLMs to adaptively create training environments to help smaller embodied RL agents learn useful skills that they are weak...

Aug 6, 2024 - Using LLM (GPT-4) to generate a 'video plan' for consistent multi-scene video generation - *[COLM 2024](https://colmweb.org/)*

Sep 2, 2023 - Video-based grounding can improve diverse NLU tasks - *[NeurIPS 2021](https://nips.cc/Conferences/2021)*