Transformers 2: Self-adaptive LLMs

Paper: https://arxiv.org/pdf/2501.06252v2.pdf

Code:
https://github.com/SakanaAI/self-adaptive-llms
https://github.com/codelion/adaptive-classifier

Datasets: GSM8K - HumanEval - MATH
MBPP - TextVQA - OK-VQA - ARC (AI2 Reasoning Challenge)

https://news.1rj.ru/str/DataScienceT ❤️

Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Diffusion Transformer Networks

paper: https://arxiv.org/pdf/2412.00733v3.pdf

Code: https://github.com/fudan-generative-vision/hallo3

https://news.1rj.ru/str/DataScienceT 😮

Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback

Paper: https://arxiv.org/pdf/2412.15838v2.pdf

Code: https://github.com/pku-alignment/align-anything

Dataset: LLaVA-Bench

https://news.1rj.ru/str/DataScienceT 😱

Search-o1: Agentic Search-Enhanced Large Reasoning Models

Large reasoning models (LRMs) like OpenAI-o1 have demonstrated impressive long stepwise reasoning capabilities through large-scale reinforcement learning. However, their extended reasoning processes often suffer from knowledge insufficiency, leading to frequent uncertainties and potential errors. To address this limitation, we introduce \textbf{Search-o1}, a framework that enhances LRMs with an agentic retrieval-augmented generation (RAG) mechanism and a Reason-in-Documents module for refining retrieved documents. Search-o1 integrates an agentic search workflow into the reasoning process, enabling dynamic retrieval of external knowledge when LRMs encounter uncertain knowledge points. Additionally, due to the verbose nature of retrieved documents, we design a separate Reason-in-Documents module to deeply analyze the retrieved information before injecting it into the reasoning chain, minimizing noise and preserving coherent reasoning flow. Extensive experiments on complex reasoning tasks in science, mathematics, and coding, as well as six open-domain QA benchmarks, demonstrate the strong performance of Search-o1. This approach enhances the trustworthiness and applicability of LRMs in complex reasoning tasks, paving the way for more reliable and versatile intelligent systems.

paper: https://arxiv.org/pdf/2501.05366v1.pdf

Code: https://github.com/sunnynexus/search-o1

Datasets: Natural Questions - TriviaQA - MATH - HotpotQA - GPQA - Bamboogle

#Search_o1 #LargeReasoningModels #AgenticRAG #ReasonInDocuments #DynamicKnowledgeRetrieval #ComplexReasoning #ScienceMathCoding #OpenDomainQA #TrustworthyAI #IntelligentSystems #python

https://news.1rj.ru/str/DataScienceT 😱

Click-Calib: A Robust Extrinsic Calibration Method for Surround-View Systems

Surround-View System (SVS) is an essential component in Advanced Driver Assistance System (ADAS) and requires precise calibrations. However, conventional offline extrinsic calibration methods are cumbersome and time-consuming as they rely heavily on physical patterns. Additionally, these methods primarily focus on short-range areas surrounding the vehicle, resulting in lower calibration quality in more distant zones. To address these limitations, we propose Click-Calib, a pattern-free approach for offline SVS extrinsic calibration. Without requiring any special setup, the user only needs to click a few keypoints on the ground in natural scenes. Unlike other offline calibration approaches, Click-Calib optimizes camera poses over a wide range by minimizing reprojection distance errors of keypoints, thereby achieving accurate calibrations at both short and long distances. Furthermore, Click-Calib supports both single-frame and multiple-frame modes, with the latter offering even better results. Evaluations on our in-house dataset and the public WoodScape dataset demonstrate its superior accuracy and robustness compared to baseline methods.

Paper: https://arxiv.org/pdf/2501.01557v2.pdf

Code: https://github.com/lwangvaleo/click_calib

Dataset: WoodScape

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI

https://news.1rj.ru/str/DataScienceT 👩‍💻

Machine learning and deep learning
✅@Machine_learn

Large language Model Git

🔺https://news.1rj.ru/str/deep_learning_proj

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

Paper: https://arxiv.org/pdf/2501.12948v1.pdf

Codes:
https://github.com/zhaoolee/garss
https://github.com/deepseek-ai/deepseek-r1

Datasets: MMLU - IFEval - GPQA - MMLU-Pro

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI

https://news.1rj.ru/str/DataScienceT ❤️

DeepSeek-V3 Technical Report

We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models. Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hours for its full training. In addition, its training process is remarkably stable. Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks. The model checkpoints are available at https://github.com/deepseek-ai/DeepSeek-V3.

Paper: https://arxiv.org/pdf/2412.19437v1.pdf

Code: https://github.com/deepseek-ai/deepseek-v3

Datasets: MMLU - GSM8K

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek

https://news.1rj.ru/str/DataScienceT 😱

ChatGPT Cheat Sheet for Business - DataCamp

Unlock the full potential of AI with our comprehensive ChatGPT Cheat Sheet for Business! Tailored specifically for professionals and entrepreneurs, this guide offers actionable insights on leveraging ChatGPT to streamline workflows, enhance customer interactions, and drive business growth. Whether you're a marketing specialist, project manager, or CEO, this cheat sheet is your go-to resource for mastering conversational AI.

From crafting compelling content to automating routine tasks, learn how to harness the power of ChatGPT in real-world business scenarios. With clear examples and step-by-step instructions, you’ll be able to integrate ChatGPT seamlessly into your operations, improving efficiency and innovation.

Don’t miss out on staying ahead of the competition by embracing the future of AI-driven solutions!

#ChatGPT #AIforBusiness #DataCamp #CheatSheet #ConversationalAI #BusinessGrowth #Automation #CustomerEngagement #ContentCreation #EfficiencyBoost #Innovation #FutureOfWork #TechTrends #AIInnovation #DigitalTransformation #BusinessSuccess

https://news.1rj.ru/str/CodeProgrammer ⭐️

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

We present JanusFlow, a powerful framework that unifies image understanding and generation in a single model. JanusFlow introduces a minimalist architecture that integrates autoregressive language models with rectified flow, a state-of-the-art method in generative modeling. Our key finding demonstrates that rectified flow can be straightforwardly trained within the large language model framework, eliminating the need for complex architectural modifications. To further improve the performance of our unified model, we adopt two key strategies: (i) decoupling the understanding and generation encoders, and (ii) aligning their representations during unified training. Extensive experiments show that JanusFlow achieves comparable or superior performance to specialized models in their respective domains, while significantly outperforming existing unified approaches across standard benchmarks. This work represents a step toward more efficient and versatile vision-language models.

Paper: https://arxiv.org/pdf/2411.07975v1.pdf

Code: https://github.com/deepseek-ai/janus

Datasets: GQA MMBench MM-Vet SEED-Bench

https://news.1rj.ru/str/DataScienceT 💚

🐫Tülu 3 (what a name) 405B - ​​another release!

An open source model (and no, it's not a Chinese model) that outperforms the DeepSeek-V3! on multiple benchmarks

Scalable to 405B - ​​with performance on par with GPT-4o and outperforming previous models in the same class.

▪ Blog: https://allenai.org/blog/tulu-3-405B
▪You can test it here: https://playground.allenai.org/?model=tulu3-405b
▪ Technical report: https://allenai.org/blog/tulu-3-technical
▪ Hugging Face : https://huggingface.co/collections/allenai/tulu-3-models-673b8e0dc3512e30e7dc54f5

#llm #ml #ai #opensource

https://news.1rj.ru/str/DataScienceT ❤️