셀프 로드 자전거 정비 가이드 작성일 2025-07-06 | In 자전거정비 , 일상 , with gpt , Reading time 6 안녕하세요! 오랜만에 일상글을 작성해보네요 오늘은 출퇴근 및 라이딩에 사용하고 있는 제 자전거(첼로 스칼라티 D7)를 집에서 셀프 정비하기 위한 가이드를 만들었는데 공유해봅니다. Read more »
Janus-Pro: UnifiedMultimodalUnderstanding and Generation with Data and Model Scaling 작성일 2025-07-06 | In paper-review , with-gpt , Janus , DeepSeek , Reading time 32 논문 링크 Read more »
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 작성일 2025-07-06 | In paper-review , with-gpt , DeepSeek , Reading time 32 논문 링크 Read more »
DeepSeek-V3 Technical Report 작성일 2025-07-05 | In paper-review , with-gpt , Reading time 37 논문 링크 Read more »
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding 작성일 2025-07-05 | In paper-review , with-gpt , Reading time 31 논문 링크 Read more »
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation 작성일 2025-07-02 | In paper-review , with-gpt , Reading time 27 논문 링크 Read more »
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation 작성일 2025-07-02 | In paper-review , with-gpt , Reading time 31 논문 링크 Read more »
Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts 작성일 2025-07-01 | In paper-review , with-gpt , Reading time 29 논문 링크 Read more »
Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning 작성일 2025-07-01 | In paper-review , with-gpt , Reading time 32 논문 링크 Read more »
DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search 작성일 2025-07-01 | In paper-review , with-gpt , Reading time 32 논문 링크 Read more »