Видео

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions Presenter: Dahye Lee Date: Nov. 7th, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts Presenter: Dahye Lee Date: Oct. 24th, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: Compositional Chain-of-Thought Prompting for Large Multimodal Models Presenter: Seongyeop Kim Date: Nov. 5th, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: Make Your LLM Fully Utilize the Context Presenter: Sangyun Chung Date: Oct. 31st, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: Aligning Large Multimodal Models with Factually Augmented RLHF Presenter: Byung-Kwan Lee Date: Oct. 29th, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: RegionGPT: Towards Region Understanding Vision Language Model Presenter: Damin Yeom Date: Oct. 22nd, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title:MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding Presenter: Minho Park Date: Oct. 15th, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: Language Model Beats Diffusion: Tokenizer is Key to Visual Generation Presenter: Byung-Kwan Lee Date: Oct. 10th, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: Analyzing and Mitigating Object Hallucination in Large Vision-Language Models Presenter: Seongyeop Kim Date: Oct. 8th, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text Presenter: Sangyun Chung Date: Oct. 4th, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: GroundingGPT: Language Enhanced Multi-modal Grounding Model Presenter: Minho Park Date: Oct. 2nd, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: Auto-Encoding Morph-Tokens for Multimodal LLM Presenter: Damin Yeom Date: Sep. 26th, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling Presenter: Dahye Lee Date: Sep. 24th, 2024

EE837 Special Topics on Signal Processing: Multimedia Processing and Learning (Fall 2024) Student Presentation Paper title: Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models Presenter: Seongyeop Kim Date: Sep. 19th, 2024

EE837 (Fall 2024): DreamLLM: Synergistic Multimodal Comprehension and Creation

EE837 (Fall 2024): LLM Pruning and Distillation in Practice: The Minitron Approach

EE474 (Spring 2024): AI Chatbot "Warny" for Automotive Dashboard Warning Lights

EE474 (Spring 2024): Generating Moving Emoticons from Webtoon

EE474 (Spring 2024): MUSE: Multimodal Utility for Story Enhancement

EE474 (Spring 2024): ALACen: Automatic Language-level Adjustment for Video Censorship

EE474 (Spring 2024): Adaptation of Music

EE474 (Spring 2024): Beyond the Page: AI-Powered Multimedia Books from Text for Children

EE474 (Spring 2024): REMEDI: REpresenting Me using D-Id studio

Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection

Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection

Mitigating Dataset Bias in Image Captioning through CLIP Confounder free Captioning Network (ICIP23)

DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding (ICCV23)

Watch or Listen: Robust Audio-Visual Speech Recognition (CVPR23)

Lip-to-speech Synthesis in the Wild with Multi-task Learning (ICASSP23)