@MLAI_KAIST

KAIST Machine Learning and Artificial Intelligence Group

 Daejeon, South Korea
mlai-kaist.com/
Joined June 2020
  • Tweets139
  • Following19
  • Followers458
28Media
We have 5 papers accepted to ICLR2026! mlai-kaist.com/publication

PUBLICATION | mlai

mlai-kaist.com
1
8
521
more replies
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)

Multi-View Encoders for Performance Prediction in LLM-Based...

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, but optimizing LLM-based agentic systems remains challenging due to the vast search space of agent...

arxiv.org
1
140
LS-Merge: Merging Language Models in Latent Space (openreview.net/forum?id=VSDV…)
110
🚀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!

Mol-LLaMA: Towards General Understanding of Molecules in Large...

Understanding molecules is key to understanding organisms and driving advances in drug discovery, requiring interdisciplinary knowledge across chemistry and biology. Although large molecular...

arxiv.org
Dongki Kim
@DongkiKim9524 Feb 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
8
23
2,496
MLAI_KAIST retweeted
Heejun Lee@ainl031019 Sep 2025
🤗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
Jeff Willette@TheOneJeffrey19 Sep 2025
Noice! Our paper "Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction" has been accepted to NeurIPS 2025! See you in San Diego (See part 2 of post for breakdown of our work) arxiv.org/pdf/2505.11254
1
1
5
256
Our Agent Distillation paper is accepted at #NeurIPS2025 Spotlight! 🚀 Turn your small LM into a strong agent 💪 Code: github.com/Nardien/agent-dis…

GitHub - Nardien/agent-distillation: Official Code Repository for the paper "Distilling LLM Agent...

Official Code Repository for the paper "Distilling LLM Agent into Small Models with Retrieval and Code Tools" - Nardien/agent-distillation

github.com
Minki Kang@mkkang_113326 May 2025
🚨 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/2505.1… Here's the details 🧵👇:

Paper page - Distilling LLM Agent into Small Models with Retrieval and Code Tools

Join the discussion on this paper page

huggingface.co
3
11
89
8,304
MLAI_KAIST retweeted
Jina Kim@JinaK_021818 Jun 2025
✨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
14
72
7,444
🚨 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/2505.1… Here's the details 🧵👇:

Paper page - Distilling LLM Agent into Small Models with Retrieval and Code Tools

Join the discussion on this paper page

huggingface.co
2
27
1
129
18,004
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. 😊
1
5
70
3,001
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

UniversalRAG: Retrieval-Augmented Generation over Corpora of...

Retrieval-Augmented Generation (RAG) has shown substantial promise in improving factual accuracy by grounding model responses with external knowledge relevant to queries. However, most existing...

arxiv.org
elvis
@omarsar030 Apr 2025
Universal RAG RAG is dead, they said. Then you see papers like this and it gives you a better understanding of the opportunities and challenges ahead. Lots of great ideas in this paper. I've summarized a few below:
1
13
17
2,205
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/2505.1…

Paper page - Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction

Join the discussion on this paper page

huggingface.co
3
1
11
661
🤔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?
1
9
1
15
2,420
MLAI_KAIST retweeted
Simon Aytes@s_aytes11 Mar 2025
📣 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

Sketch-of-Thought: Efficient LLM Reasoning with Adaptive...

Recent advances in large language models (LLMs) have enabled strong reasoning capabilities through Chain-of-Thought (CoT) prompting, which elicits step-by-step problem solving, but often at the...

arxiv.org
9
30
2,245
We have 2 papers accepted to CVPR 2025. Our students are on a roll for 2025!
1
1
3
382
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

VideoICL: Confidence-based Iterative In-context Learning for...

Recent advancements in video large multimodal models (LMMs) have significantly improved their video understanding and reasoning capabilities. However, their performance drops on...

arxiv.org
1
1
2
243
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
232
🚨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
1
12
1
26
5,227
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)
1
1
4
361
more replies
Training Free Exponential Context Extension via Cascading KV Cache (Jeffrey Willette, Heejun Lee, Youngwan Lee, Myeongjae Jeon, Sung Ju Hwang), ICLR 2025 (6/7)
1
2
134
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)
2
149
Load more