Telegram

DeepSeek

p

近期文章

DeepThink Goes WILD: How DeepSeek R1 Is Revolutionizing Code, Reasoning, and AI-Driven Tech Workflows
Whether you’re a solo builder, a startup founder, or a seasoned engineer—DeepThink is the wild new edge in your stack.
ic_writer ds66
ic_date 2024-07-20
Explainable Sentiment Analysis with DeepSeek‑R1: Performance, Efficiency, and Few‑Shot Learning
This study demonstrates that DeepSeek‑R1 offers a compelling package for sentiment analysis
ic_writer ds66
ic_date 2024-07-17
1. How Effective Is Constitutional AI in Small LLMs? A Study on DeepSeek‑R1 and Its Peers ⚖️
Both works underscore the versatility of DeepSeek‑R1's reasoning chains: in safety-alignment and factual grounding contexts,
ic_writer ds66
ic_date 2024-07-17
How Effective Is Constitutional AI in Small LLMs? A Study on DeepSeek‑R1 and Its Peers
Constitutional AI remains a promising alignment method in small LLMs—but its success hinges on architecture and inherent reasoning quality.
ic_writer ds66
ic_date 2024-07-15
Medical Reasoning in LLMs: An In-Depth Analysis of DeepSeek R1
DeepSeek‑R1 demonstrates foundational medical reasoning capacity through structured CoT outputs, achieving high diagnostic accuracy (93%) and alignment with expert reasoning patterns.
ic_writer ds66
ic_date 2024-07-15
DeepSeek-R1 Thoughtology: Let's think About LLM Reasoning
DeepSeek‑R1 Thoughtology: Let’s about LLM Reasoning
ic_writer ds66
ic_date 2024-07-15
🧠 DeepSeek‑R1 vs. o3‑mini: Evaluating Machine Translation and Summarization with Reasoning LLMs
By releasing their code and evaluation pipelines, the authors pave the way for deeper, community-led exploration of reasoning’s role in NLG evaluation.
ic_writer ds66
ic_date 2024-07-15
RealSafe‑R1: Enhancing Safety in Reasoning Models Without Sacrificing Capabilities
RealSafe‑R1 demonstrates a pragmatic and open-source approach to strengthening safety in reasoning LLMs. By fine-tuning on safety-aware reasoning outputs,
ic_writer ds66
ic_date 2024-07-15
A Method for Building a Medical Vertical LLM Based on DeepSeek‑R1
This three-pronged architecture expertly balances specialization and efficiency. Through LoRA-based knowledge distillation,
ic_writer ds66
ic_date 2024-07-14
100 Days After DeepSeek‑R1: Surveying Replication Studies & Future Paths for Reasoning Language Models
If you'd like visual pipeline diagrams, code examples from HuggingFace, or a comparison of RL algorithms (PPO vs. GRPO), I’d be happy to provide them!
ic_writer ds66
ic_date 2024-07-14
“R1dacted”: Investigating Local Censorship in DeepSeek's R1 Language Model
DeepSeek‑R1’s local censorship is a landmark case in AI governance. It sheds light on how state-aligned
ic_writer ds66
ic_date 2024-07-14
Deepsite v2: The Future of AI-Powered Website Building
It’s not just about building websites. It’s about amplifying your ideas and making the web accessible to everyone—with nothing more than a prompt.
ic_writer ds66
ic_date 2024-07-14