MLAI_KAIST

LS-Merge: Merging Language Models in Latent Space (openreview.net/forum?id=VSDV0…)

Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows (arxiv.org/abs/2505.19764) Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs (arxiv.org/abs/2510.09201)

We have 5 papers accepted to ICLR2026! mlai-kaist.com/publication

🚀Excited to share that our Mol-LLaMA is accepted at #NeurIPS2025!! 📄Paper: arxiv.org/abs/2502.13449 🖥️Project Page: mol-llama.github.io See you in San Diego!

🤗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

Our Agent Distillation paper is accepted at #NeurIPS2025 Spotlight! 🚀 Turn your small LM into a strong agent 💪 Code: github.com/Nardien/agent-…

✨Excited to share our new work "Robust Molecular Property Prediction via Densifying Scarce Labeled Data", accepted by GenBio ICML Workshop 2025! arxiv : arxiv.org/abs/2506.11877 Special thanks to all the collaborators @TheOneJeffrey @andreisbru and our advisor, @SungJuHwang1

🚨 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: 📄 huggingface.co/papers/2505.17… Here's the details 🧵👇:

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. 😊

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: arxiv.org/abs/2504.20734

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! huggingface.co/papers/2505.11…

🤔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?

📣 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: arxiv.org/abs/2503.05179

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

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 arxiv.org/abs/2412.02186

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

🚨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: arxiv.org/abs/2502.13449 Project Page: mol-llama.github.io 🧵below

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)

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

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)