MLAI_KAIST

KAIST Machine Learning and Artificial Intelligence Group

[MLAI_KAIST @MLAI_KAIST]

LS-Merge: Merging Language Models in Latent Space (https://t.co/zdHuOtPwlf)

[MLAI_KAIST @MLAI_KAIST]

We have 5 papers accepted to ICLR2026!

https://t.co/725IjMQFsW

[MLAI_KAIST @MLAI_KAIST]

Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows (https://t.co/34eKBZXzsn)

Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs (https://t.co/EawjZcKLei)

[Dongki Kim @DongkiKim95]

🚀Excited to share that our Mol-LLaMA is accepted at #NeurIPS2025!!

📄Paper: https://t.co/R49oLR4g9d
🖥️Project Page: https://t.co/wFuIEwQUo2

See you in San Diego!

[Heejun Lee @ainl0310]

🤗Our paper, "Delta Attention," has been accepted to NIPS 2025. The delta correction is beneficial for anyone interested in improving the accuracy of sparse attention. Wonderful work, @TheOneJeffrey

[Minki Kang @mkkang_1133]

Our Agent Distillation paper is accepted at #NeurIPS2025 Spotlight! 🚀

Turn your small LM into a strong agent 💪
Code: https://t.co/ost8pKZRwo

[Jina Kim @jk020218]

✨Excited to share our new work "Robust Molecular Property Prediction via Densifying Scarce Labeled Data", accepted by GenBio ICML Workshop 2025!

arxiv : https://t.co/YM1d9n0TBu

Special thanks to all the collaborators @TheOneJeffrey @andreisbru and our advisor, @SungJuHwang1

[Minki Kang @mkkang_1133]

🚨 New preprint!
Can small language models (sLMs) solve complex problems like LLMs?
We show how to go beyond cloning reasoning—to distill tool-using agent behavior into sLMs as tiny as 0.5B.

Meet Agent Distillation:
📄 https://t.co/whBmSl96Em

Here's the details 🧵👇:

[Jinheon Baek @jinheonbaek]

So excited to share that five papers have been accepted to #ACL2025 🎉

Huge thanks to all my amazing collaborators. I am especially grateful that all the internship projects (which I have worked on during my PhD journey) have all found their way to publication. Its rewarding. 😊

[Kangsan Kim @kangsan_kim_]

Introducing 🌌UniversalRAG — a novel RAG framework that adaptively retrieves from multimodal corpora (📕text, 🖼image, 🎥video) at the right level of granularity, from short snippets to long content.

Huge thanks to @omarsar0 for sharing our work!

Paper: https://t.co/x2YgCXZuY4

[Jeff Willette @TheOneJeffrey]

There is a HUGE problem with sparse attention! We found it causes a misalignment of queries and keys, so even if you add a dense decode/generation phase, the sparsely encoded context can be forgotten. But wait... We can fix it with a simple correction! https://t.co/T7KjLd0lDb

[Sangwon Jang @jangsangwon7]

🤔Can you really trust what your AI creates? Meet Silent Branding Attack—a sneaky, no-trigger-needed method to secretly poison text-to-image models!

👀 Test yourself: Can you spot which images below have been silently branded?

[Simon Aytes @s_aytes]

📣 Excited to introduce Sketch-of-Thought (SoT)

We've drawn inspiration from human cognition to make #LLM reasoning more efficient, reducing token usage by an avg. of 75% while having comparable accuracy to traditional CoT approaches.

🔗Paper: https://t.co/miWx9ar49k

[MLAI_KAIST @MLAI_KAIST]

Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models

Sangwon Jang, June Suk Choi, Jaehyeong Jo, Kimin Lee, Sung Ju Hwang, CVPR 2025

[MLAI_KAIST @MLAI_KAIST]

We have 2 papers accepted to CVPR 2025. Our students are on a roll for 2025!

[MLAI_KAIST @MLAI_KAIST]

VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding

Kangsan Kim, Geon Park, Youngwan Lee, Woongyeong Yeo, Sung Ju Hwang, CVPR 2025
https://t.co/MJWaFB4OEn

[Dongki Kim @DongkiKim95]

🚨Excited to introduce Mol-LLaMA, a large molecular language model that grasps the general knowledge centered on molecules, positioning it as a general-purpose assistant for molecular analysis.

Paper: https://t.co/R49oLR3IjF
Project Page: https://t.co/wFuIEwQmyu

🧵below

[MLAI_KAIST @MLAI_KAIST]

Diffusion-based Neural Network Weights Generation
(Bedionita Soro, Bruno_Andreis, Hayeon Lee, Wonyong Jeong, Song Chong, Frank Hutter, Sung Ju Hwang), ICLR 2025 (7/7)

[MLAI_KAIST @MLAI_KAIST]

Wow! we have 5 papers accepted to ICLR 2025 and one accepted to NAACL 2025. We look forward to seeing you at the conferences (1/7)

[MLAI_KAIST @MLAI_KAIST]

Training Free Exponential Context Extension via Cascading KV Cache
(Jeffrey Willette, Heejun Lee, Youngwan Lee, Myeongjae Jeon, Sung Ju Hwang), ICLR 2025 (6/7)