26.05.14 목
[명세진]
- (Capstone Design) 거시경제 컨텍스트 통합 Macro-Aware FT-Transformer(MA-FT) 제안: 부동산, 기업재무 규모별 예측 성능 비교
[김진용]
- (Capstone Design) ResNet-18 기반 Dataset Complexity와 Pruning Sensitivity 상관관계 분석
[박초원]
- (Capstone Design) 홈캠 멀티모달 기반 아동학대 의심상황 감지 파이프라인 (Pose 이벤트 + LLM 평가)
[임민수]
- (Paper Review) Image Super-Resolution Using Deep Convolutional Networks: SRCNN 논문리뷰
[홍화수]
- (Paper Review) An Image is Worth 16x16 Words: ViT(Vision Transformer) 논문리뷰
[서준일]
- (Progress and Plan) RAG 동향 조사 (Graph, Multimodal, Agentic RAG) 및 연구 방향 탐색
[Luciano]
- (Research Progress) VACaps: Text-based Image Retrieval용 대규모 Image-Caption Dataset 구축
[최규문]
- (Paper Review) Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision: ALIGN 논문리뷰
[손원빈]
- (Paper Review) LLaGA: Large Language and Graph Assistant 논문리뷰
[한승용]
- (Paper Review) VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning 논문리뷰