Skip to content

Mar 14, 2025

Presentation Slide

Research Works

Article 1

Title: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Presenter: CHEN Yi

Presentation Date: March 14, 2025 (Friday)

Research Areas: Multimodal Foundation Model, Embodied AI

DOI: https://doi.org/10.48550/arXiv.2501.12948

Article 2

Title: DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Presenter: CHEN Yi

Presentation Date: March 14, 2025 (Friday)

Research Areas: Multimodal Foundation Model, Embodied AI

DOI: https://doi.org/10.48550/arXiv.2501.12948

Article 3

Title: s1: Simple test-time scaling

Presenter: CHEN Yi

Presentation Date: March 14, 2025 (Friday)

Research Areas: Multimodal Foundation Model, Embodied AI

DOI: https://doi.org/10.48550/arXiv.2501.12948

Article 4

Title: Demystifying Long Chain-of-Thought Reasoning in LLMs

Presenter: CHEN Yi

Presentation Date: March 14, 2025 (Friday)

Research Areas: Multimodal Foundation Model, Embodied AI

DOI: https://doi.org/10.48550/arXiv.2501.12948

Article 5

Title: LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

Presenter: CHEN Yi

Presentation Date: March 14, 2025 (Friday)

Research Areas: Multimodal Foundation Model, Embodied AI

DOI: https://doi.org/10.48550/arXiv.2501.12948

Article 6

Title: Visual-RFT: Visual Reinforcement Fine-Tuning

Presenter: CHEN Yi

Presentation Date: March 14, 2025 (Friday)

Research Areas: Multimodal Foundation Model, Embodied AI

DOI: https://doi.org/10.48550/arXiv.2501.12948

Photo Album