DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper submitted by #DeepSeek team has generated significant attention in the AI community.
This work addresses the enhancement of reasoning capabilities in Large Language Models (LLMs) through the application of reinforcement learning techniques. The authors introduce a novel framework, DeepSeek-R1, which aims to improve LLM reasoning abilities by incorporating incentives for logical reasoning processes within their training. This integration of reinforcement learning allows LLMs to go beyond basic linguistic processing, developing sophisticated reasoning methods that can boost performance across a wide array of complex applications.
This approach has cause lots of discussions in different communities, but it definitely opens up the whole new direction of development for the research.
Paper: https://arxiv.org/abs/2501.12948
#nn #LLM
@Machine_learn
Paper submitted by #DeepSeek team has generated significant attention in the AI community.
This work addresses the enhancement of reasoning capabilities in Large Language Models (LLMs) through the application of reinforcement learning techniques. The authors introduce a novel framework, DeepSeek-R1, which aims to improve LLM reasoning abilities by incorporating incentives for logical reasoning processes within their training. This integration of reinforcement learning allows LLMs to go beyond basic linguistic processing, developing sophisticated reasoning methods that can boost performance across a wide array of complex applications.
This approach has cause lots of discussions in different communities, but it definitely opens up the whole new direction of development for the research.
Paper: https://arxiv.org/abs/2501.12948
#nn #LLM
@Machine_learn
arXiv.org
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via...
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning...
❤2
@Machine_learn
Please open Telegram to view this post
VIEW IN TELEGRAM
𝗡𝗟𝗣_𝘄𝗶𝘁𝗵_𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀.pdf
8.2 MB
Natural Language Processing with Transformers Building Language Applications
with Hugging Face
#Book
@Machine_learn
with Hugging Face
#Book
@Machine_learn
🔥2👍1
🐋 DeepClaude
▪ Github
▪Docs
@Machine_learn
git clone https://github.com/getasterisk/deepclaude.git
cd deepclaude
▪ Github
▪Docs
@Machine_learn
اخرین زمان برای مشارکت در این پروژه تا اخر شب...!
@Raminmousa
@Raminmousa
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
Paper: https://arxiv.org/pdf/2401.02954v1.pdf
Code: https://github.com/deepseek-ai/deepseek-llm
Dataset: AlignBench
@Machine_learn
Paper: https://arxiv.org/pdf/2401.02954v1.pdf
Code: https://github.com/deepseek-ai/deepseek-llm
Dataset: AlignBench
@Machine_learn
❤2
📃Can social network analysis contribute to supply chain
management? A systematic literature review and
bibliometric analysis
📎 Study paper
@Machine_learn
management? A systematic literature review and
bibliometric analysis
📎 Study paper
@Machine_learn
👍1
WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training
🖥 Github: https://github.com/penfever/wildchat-50m
📕 Paper: https://arxiv.org/abs/2501.18511v1
🧠 Dataset: https://huggingface.co/collections/nyu-dice-lab/wildchat-50m-679a5df2c5967db8ab341ab7
@Machine_learn
@Machine_learn
Please open Telegram to view this post
VIEW IN TELEGRAM
👍1
با عرض سلام در يكي از پروژه هاي طبقه بندي سرطان پوست نياز به مشاركت داريم. جايگاه نفر سوم خالي مي باشد.
🔸 🔻 🔸 🔻 🔸 🔻 🔻
@Raminmousa
@Raminmousa
Please open Telegram to view this post
VIEW IN TELEGRAM
Machine learning books and papers pinned «با عرض سلام در يكي از پروژه هاي طبقه بندي سرطان پوست نياز به مشاركت داريم. جايگاه نفر سوم خالي مي باشد. 🔸 🔻 🔸 🔻 🔸 🔻 🔻 @Raminmousa»
Forwarded from Papers
با عرض سلام نفر ٥ ام از پروژه جديدمون باقي مونده و ٦ جايگاه ديگه پر شدن.
امكان اموزش كامل كار
كدنويسي كار
نحوه جمع اوري داده ها
نگارش مقاله در اين كار وجود داره
Project Title: MedRec: Medical recommender system for image classification without retraining
Github: https://github.com/Ramin1Mousa/MedicalRec
Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence
Impact factor: 20.8
🔺 5- 300$
جهت مشارکت می تونید به ایدی بنده پیام بدین.
@Raminmousa
امكان اموزش كامل كار
كدنويسي كار
نحوه جمع اوري داده ها
نگارش مقاله در اين كار وجود داره
Project Title: MedRec: Medical recommender system for image classification without retraining
Github: https://github.com/Ramin1Mousa/MedicalRec
Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence
Impact factor: 20.8
جهت مشارکت می تونید به ایدی بنده پیام بدین.
@Raminmousa
Please open Telegram to view this post
VIEW IN TELEGRAM
Forwarded from Github LLMs
LLMs can see and hear without any training
30 Jan 2025 · Kumar Ashutosh, Yossi Gandelsman, Xinlei Chen, Ishan Misra, Rohit Girdhar ·
We present MILS: Multimodal Iterative LLM Solver, a surprisingly simple, training-free approach, to imbue multimodal capabilities into your favorite LLM. Leveraging their innate ability to perform multi-step reasoning, MILS prompts the LLM to generate candidate outputs, each of which are scored and fed back iteratively, eventually generating a solution to the task. This enables various applications that typically require training specialized models on task-specific data. In particular, we establish a new state-of-the-art on emergent zero-shot image, video and audio captioning. MILS seamlessly applies to media generation as well, discovering prompt rewrites to improve text-to-image generation, and even edit prompts for style transfer! Finally, being a gradient-free optimization approach, MILS can invert multimodal embeddings into text, enabling applications like cross-modal arithmetic.
Paper: https://arxiv.org/pdf/2501.18096v1.pdf
Code: https://github.com/facebookresearch/mils
✅
https://www.tg-me.com/deep_learning_proj
30 Jan 2025 · Kumar Ashutosh, Yossi Gandelsman, Xinlei Chen, Ishan Misra, Rohit Girdhar ·
We present MILS: Multimodal Iterative LLM Solver, a surprisingly simple, training-free approach, to imbue multimodal capabilities into your favorite LLM. Leveraging their innate ability to perform multi-step reasoning, MILS prompts the LLM to generate candidate outputs, each of which are scored and fed back iteratively, eventually generating a solution to the task. This enables various applications that typically require training specialized models on task-specific data. In particular, we establish a new state-of-the-art on emergent zero-shot image, video and audio captioning. MILS seamlessly applies to media generation as well, discovering prompt rewrites to improve text-to-image generation, and even edit prompts for style transfer! Finally, being a gradient-free optimization approach, MILS can invert multimodal embeddings into text, enabling applications like cross-modal arithmetic.
Paper: https://arxiv.org/pdf/2501.18096v1.pdf
Code: https://github.com/facebookresearch/mils
https://www.tg-me.com/deep_learning_proj
Please open Telegram to view this post
VIEW IN TELEGRAM
❤1👍1🔥1