2025-11-10 [AAAI 2026] Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale Verifier (by Hyeongseop Rha) is accepted to AAAI 2026.
2025-09-24 [2026 봄학기 연구실 학생 모집] 전기및전자공학부 - 국비 석사 2명, KAIST 장학생 (석사, 박사), KAIST 프로그램(KEPSI, EPSS, LGenius, EPSD) & 김재철 AI 대학원 - KAIST 장학생 (석사) 모집합니다.
2025-09-24 [NVIDIA Academic Grant] Professor Yong Man Ro's project, Inclusive Multimodal LLM for Vocal and Non-Vocal Human Communication, has been selected for the NVIDIA Academic Grant Program.
2025-09-24 [NeurIPS 2025] Unified Reinforcement and Imitation Learning for Vision-Language Models (by Byung-Kwan Lee) is accepted in NeurIPS 2025.
2025-09-04 [Pattern Recognition] Adaptive Integration of Textual Context and Visual Embeddings for Underrepresented Vision Classification (by Seongyeop Kim) is accepted to Pattern Recognition.
2025-07-22 [Pattern Recognition] Causal Unsupervised Semantic Segmentation (by Junho Kim, Byung-Kwan Lee) is accepted to Pattern Recognition.
2025-07-11 [ICIP 2025] Closing the Modality Gap: Integrating LLMs with LiDAR for 3D Object Detection and Object-level Understanding (by Youngchae Chee) is accepted to ICIP 2025.
2025-07-07 [ACM MM 2025] Focus Where It Matters: LLM-Guided Regional Identification for Instruction-based Image Editing (by Minho Park) is accepted to ACM MM 2025.
2025-06-26 [ICCV 2025] Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations (by Jeong Hun Yeo) is accepted to ICCV 2025.
2025-06-23 [Recent Ph.D. Graduate: Postdoc] Junho Kim Joins a postdoc in AI research at UIUC
2025-06-22 [Meta Internship] [Meta Internship] Se Jin Park will join Meta for a research scientist intern.
2025-06-03 [IEEE TMM] TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages (by Minsu Kim) is accepted to IEEE Transactions on Multimedia.
2025-05-28 [ACL 2025] MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens (by Jeong Hun Yeo, Hyeongseop Rha) is accepted to the Findings of ACL 2025.
2025-05-14 [ICML 2025] Long-Form Speech Generation with Spoken Language Models (by Se Jin Park) is accepted as Oral (~1%) in ICML 2025.
2025-04-18 [2025 가을학기 연구실 학생 모집] MLLM (Multimodal large language model)+ (Vision, Audio, Language) 분야를 연구할 인재를 초청합니다.
2025-03-12 [Recruited by Deepmind] Dr. Minsu Kim and Dr. Joanna Hong, have been recruited by DeepMind.
2025-02-27 [CVPR 2025] SALOVA: Segment-Augmented Long Video Assistance for Targeted Retrieval and Routing in Long-Form Video Analysis (by Junho Kim, Hyunjun Kim) is accepted in CVPR 2025.
2025-02-27 [CVPR 2025] VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models (by Byung-Kwan Lee) is accepted in CVPR 2025.
IVYLAB & IVLLAB