✨MemFly: On-the-Fly Memory Optimization via Information Bottleneck
📝 Summary:
MemFly addresses the challenge of long-term memory in language models by using information bottleneck principles to create an adaptive memory structure with hybrid retrieval mechanisms for improved ta...
🔹 Publication Date: Published on Feb 8
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.07885
• PDF: https://arxiv.org/pdf/2602.07885
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
📝 Summary:
MemFly addresses the challenge of long-term memory in language models by using information bottleneck principles to create an adaptive memory structure with hybrid retrieval mechanisms for improved ta...
🔹 Publication Date: Published on Feb 8
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.07885
• PDF: https://arxiv.org/pdf/2602.07885
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
✨Moonshine: Speech Recognition for Live Transcription and Voice Commands
📝 Summary:
Moonshine is an efficient transformer-based speech recognition model employing Rotary Position Embedding. It reduces compute requirements by 5x compared to Whisper Tiny.en for live transcription without sacrificing accuracy, ideal for real-time use.
🔹 Publication Date: Published on Oct 21, 2024
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2410.15608
• PDF: https://arxiv.org/pdf/2410.15608
• Github: https://github.com/usefulsensors/moonshine
🔹 Models citing this paper:
• https://huggingface.co/UsefulSensors/moonshine
• https://huggingface.co/UsefulSensors/moonshine-base
• https://huggingface.co/UsefulSensors/moonshine-tiny
✨ Spaces citing this paper:
• https://huggingface.co/spaces/microsoft/paza-bench
• https://huggingface.co/spaces/8bitkick/reachy_mini_reactions
• https://huggingface.co/spaces/fastrtc/moonshine-live
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
📝 Summary:
Moonshine is an efficient transformer-based speech recognition model employing Rotary Position Embedding. It reduces compute requirements by 5x compared to Whisper Tiny.en for live transcription without sacrificing accuracy, ideal for real-time use.
🔹 Publication Date: Published on Oct 21, 2024
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2410.15608
• PDF: https://arxiv.org/pdf/2410.15608
• Github: https://github.com/usefulsensors/moonshine
🔹 Models citing this paper:
• https://huggingface.co/UsefulSensors/moonshine
• https://huggingface.co/UsefulSensors/moonshine-base
• https://huggingface.co/UsefulSensors/moonshine-tiny
✨ Spaces citing this paper:
• https://huggingface.co/spaces/microsoft/paza-bench
• https://huggingface.co/spaces/8bitkick/reachy_mini_reactions
• https://huggingface.co/spaces/fastrtc/moonshine-live
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
arXiv.org
Moonshine: Speech Recognition for Live Transcription and Voice Commands
This paper introduces Moonshine, a family of speech recognition models optimized for live transcription and voice command processing. Moonshine is based on an encoder-decoder transformer...
✨Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices
📝 Summary:
Flavors of Moonshine are tiny monolingual ASR models for underrepresented languages. They outperform larger multilingual models by using balanced data, achieving 48% lower error rates. This enables accurate on-device speech recognition.
🔹 Publication Date: Published on Sep 2, 2025
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.02523
• PDF: https://arxiv.org/pdf/2509.02523
• Github: https://github.com/moonshine-ai/moonshine
🔹 Models citing this paper:
• https://huggingface.co/UsefulSensors/moonshine-tiny-ja
• https://huggingface.co/UsefulSensors/moonshine-tiny-ar
• https://huggingface.co/UsefulSensors/moonshine-tiny-zh
✨ Spaces citing this paper:
• https://huggingface.co/spaces/wmoto-ai/moonshine-tiny-ja-demo
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#ASR #EdgeAI #LowResourceLanguages #MachineLearning #TinyML
📝 Summary:
Flavors of Moonshine are tiny monolingual ASR models for underrepresented languages. They outperform larger multilingual models by using balanced data, achieving 48% lower error rates. This enables accurate on-device speech recognition.
🔹 Publication Date: Published on Sep 2, 2025
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.02523
• PDF: https://arxiv.org/pdf/2509.02523
• Github: https://github.com/moonshine-ai/moonshine
🔹 Models citing this paper:
• https://huggingface.co/UsefulSensors/moonshine-tiny-ja
• https://huggingface.co/UsefulSensors/moonshine-tiny-ar
• https://huggingface.co/UsefulSensors/moonshine-tiny-zh
✨ Spaces citing this paper:
• https://huggingface.co/spaces/wmoto-ai/moonshine-tiny-ja-demo
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#ASR #EdgeAI #LowResourceLanguages #MachineLearning #TinyML
✨Kronos: A Foundation Model for the Language of Financial Markets
📝 Summary:
Kronos is a novel foundation model for financial K-line data, employing a specialized tokenizer and autoregressive pre-training on a massive dataset. It significantly outperforms existing models in forecasting, volatility prediction, and generating synthetic financial data.
🔹 Publication Date: Published on Aug 2, 2025
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.02739
• PDF: https://arxiv.org/pdf/2508.02739
• Github: https://github.com/shiyu-coder/Kronos
🔹 Models citing this paper:
• https://huggingface.co/NeoQuasar/Kronos-base
• https://huggingface.co/NeoQuasar/Kronos-Tokenizer-base
• https://huggingface.co/NeoQuasar/Kronos-mini
✨ Spaces citing this paper:
• https://huggingface.co/spaces/xianqiu/qlang
• https://huggingface.co/spaces/ByronWang2005/Kronos-CS2-Skins-Forecast-Demo
• https://huggingface.co/spaces/superyan/kronos-jp
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#FinancialAI #FoundationModels #DeepLearning #QuantitativeFinance #MarketPrediction
📝 Summary:
Kronos is a novel foundation model for financial K-line data, employing a specialized tokenizer and autoregressive pre-training on a massive dataset. It significantly outperforms existing models in forecasting, volatility prediction, and generating synthetic financial data.
🔹 Publication Date: Published on Aug 2, 2025
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.02739
• PDF: https://arxiv.org/pdf/2508.02739
• Github: https://github.com/shiyu-coder/Kronos
🔹 Models citing this paper:
• https://huggingface.co/NeoQuasar/Kronos-base
• https://huggingface.co/NeoQuasar/Kronos-Tokenizer-base
• https://huggingface.co/NeoQuasar/Kronos-mini
✨ Spaces citing this paper:
• https://huggingface.co/spaces/xianqiu/qlang
• https://huggingface.co/spaces/ByronWang2005/Kronos-CS2-Skins-Forecast-Demo
• https://huggingface.co/spaces/superyan/kronos-jp
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#FinancialAI #FoundationModels #DeepLearning #QuantitativeFinance #MarketPrediction
arXiv.org
Kronos: A Foundation Model for the Language of Financial Markets
The success of large-scale pre-training paradigm, exemplified by Large Language Models (LLMs), has inspired the development of Time Series Foundation Models (TSFMs). However, their application to...
❤1
🚀 Master Data Science & Programming!
Unlock your potential with this curated list of Telegram channels. Whether you need books, datasets, interview prep, or project ideas, we have the perfect resource for you. Join the community today!
🔰 Machine Learning with Python
Learn Machine Learning with hands-on Python tutorials, real-world code examples, and clear explanations for researchers and developers.
https://t.iss.one/CodeProgrammer
🔖 Machine Learning
Machine learning insights, practical tutorials, and clear explanations for beginners and aspiring data scientists. Follow the channel for models, algorithms, coding guides, and real-world ML applications.
https://t.iss.one/DataScienceM
🧠 Code With Python
This channel delivers clear, practical content for developers, covering Python, Django, Data Structures, Algorithms, and DSA – perfect for learning, coding, and mastering key programming skills.
https://t.iss.one/DataScience4
🎯 PyData Careers | Quiz
Python Data Science jobs, interview tips, and career insights for aspiring professionals.
https://t.iss.one/DataScienceQ
💾 Kaggle Data Hub
Your go-to hub for Kaggle datasets – explore, analyze, and leverage data for Machine Learning and Data Science projects.
https://t.iss.one/datasets1
🧑🎓 Udemy Coupons | Courses
The first channel in Telegram that offers free Udemy coupons
https://t.iss.one/DataScienceC
😀 ML Research Hub
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.
https://t.iss.one/DataScienceT
💬 Data Science Chat
An active community group for discussing data challenges and networking with peers.
https://t.iss.one/DataScience9
🐍 Python Arab| بايثون عربي
The largest Arabic-speaking group for Python developers to share knowledge and help.
https://t.iss.one/PythonArab
🖊 Data Science Jupyter Notebooks
Explore the world of Data Science through Jupyter Notebooks—insights, tutorials, and tools to boost your data journey. Code, analyze, and visualize smarter with every post.
https://t.iss.one/DataScienceN
📺 Free Online Courses | Videos
Free online courses covering data science, machine learning, analytics, programming, and essential skills for learners.
https://t.iss.one/DataScienceV
📈 Data Analytics
Dive into the world of Data Analytics – uncover insights, explore trends, and master data-driven decision making.
https://t.iss.one/DataAnalyticsX
🎧 Learn Python Hub
Master Python with step-by-step courses – from basics to advanced projects and practical applications.
https://t.iss.one/Python53
⭐️ Research Papers
Professional Academic Writing & Simulation Services
https://t.iss.one/DataScienceY
━━━━━━━━━━━━━━━━━━
Admin: @HusseinSheikho
Unlock your potential with this curated list of Telegram channels. Whether you need books, datasets, interview prep, or project ideas, we have the perfect resource for you. Join the community today!
Learn Machine Learning with hands-on Python tutorials, real-world code examples, and clear explanations for researchers and developers.
https://t.iss.one/CodeProgrammer
Machine learning insights, practical tutorials, and clear explanations for beginners and aspiring data scientists. Follow the channel for models, algorithms, coding guides, and real-world ML applications.
https://t.iss.one/DataScienceM
This channel delivers clear, practical content for developers, covering Python, Django, Data Structures, Algorithms, and DSA – perfect for learning, coding, and mastering key programming skills.
https://t.iss.one/DataScience4
Python Data Science jobs, interview tips, and career insights for aspiring professionals.
https://t.iss.one/DataScienceQ
Your go-to hub for Kaggle datasets – explore, analyze, and leverage data for Machine Learning and Data Science projects.
https://t.iss.one/datasets1
The first channel in Telegram that offers free Udemy coupons
https://t.iss.one/DataScienceC
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.
https://t.iss.one/DataScienceT
An active community group for discussing data challenges and networking with peers.
https://t.iss.one/DataScience9
The largest Arabic-speaking group for Python developers to share knowledge and help.
https://t.iss.one/PythonArab
Explore the world of Data Science through Jupyter Notebooks—insights, tutorials, and tools to boost your data journey. Code, analyze, and visualize smarter with every post.
https://t.iss.one/DataScienceN
Free online courses covering data science, machine learning, analytics, programming, and essential skills for learners.
https://t.iss.one/DataScienceV
Dive into the world of Data Analytics – uncover insights, explore trends, and master data-driven decision making.
https://t.iss.one/DataAnalyticsX
Master Python with step-by-step courses – from basics to advanced projects and practical applications.
https://t.iss.one/Python53
Professional Academic Writing & Simulation Services
https://t.iss.one/DataScienceY
━━━━━━━━━━━━━━━━━━
Admin: @HusseinSheikho
Please open Telegram to view this post
VIEW IN TELEGRAM
❤1
✨MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
📝 Summary:
MedXIAOHE is a medical vision-language foundation model achieving state-of-the-art performance. It uses entity-aware pretraining, reinforcement learning, and tool-augmented training for reliable, expert-level diagnostic reasoning with low hallucination.
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12705
• PDF: https://arxiv.org/pdf/2602.12705
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MedicalAI #MLLMs #VisionLanguage #DiagnosticAI #FoundationModels
📝 Summary:
MedXIAOHE is a medical vision-language foundation model achieving state-of-the-art performance. It uses entity-aware pretraining, reinforcement learning, and tool-augmented training for reliable, expert-level diagnostic reasoning with low hallucination.
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12705
• PDF: https://arxiv.org/pdf/2602.12705
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MedicalAI #MLLMs #VisionLanguage #DiagnosticAI #FoundationModels
✨GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics
📝 Summary:
GeoAgent improves geolocation reasoning by using GeoSeek, a new expert-annotated dataset, and novel geo-similarity and consistency rewards. This ensures geographic accuracy and reasoning consistency. It outperforms existing methods and generates human-aligned conclusions.
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12617
• PDF: https://arxiv.org/pdf/2602.12617
• Project Page: https://ghost233lism.github.io/GeoAgent-page/
• Github: https://github.com/HVision-NKU/GeoAgent
🔹 Models citing this paper:
• https://huggingface.co/ghost233lism/GeoAgent
✨ Datasets citing this paper:
• https://huggingface.co/datasets/ghost233lism/GeoSeek
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#Geolocation #AI #ReinforcementLearning #GeospatialAI #DataScience
📝 Summary:
GeoAgent improves geolocation reasoning by using GeoSeek, a new expert-annotated dataset, and novel geo-similarity and consistency rewards. This ensures geographic accuracy and reasoning consistency. It outperforms existing methods and generates human-aligned conclusions.
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12617
• PDF: https://arxiv.org/pdf/2602.12617
• Project Page: https://ghost233lism.github.io/GeoAgent-page/
• Github: https://github.com/HVision-NKU/GeoAgent
🔹 Models citing this paper:
• https://huggingface.co/ghost233lism/GeoAgent
✨ Datasets citing this paper:
• https://huggingface.co/datasets/ghost233lism/GeoSeek
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#Geolocation #AI #ReinforcementLearning #GeospatialAI #DataScience
✨Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions
📝 Summary:
Researchers created ASID-1M, a dataset of structured, quality-verified audiovisual instructions, and ASID-Captioner, a model trained on it. This improves fine-grained caption quality, reduces hallucinations, and achieves SOTA results.
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.13013
• PDF: https://arxiv.org/pdf/2602.13013
• Github: https://github.com/ASID-Caption/ASID-Caption
🔹 Models citing this paper:
• https://huggingface.co/AudioVisual-Caption/ASID-Captioner-3B
• https://huggingface.co/AudioVisual-Caption/ASID-Captioner-7B
✨ Datasets citing this paper:
• https://huggingface.co/datasets/AudioVisual-Caption/ASID-1M
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MLLM #VideoAI #DeepLearning #ComputerVision #NLP
📝 Summary:
Researchers created ASID-1M, a dataset of structured, quality-verified audiovisual instructions, and ASID-Captioner, a model trained on it. This improves fine-grained caption quality, reduces hallucinations, and achieves SOTA results.
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.13013
• PDF: https://arxiv.org/pdf/2602.13013
• Github: https://github.com/ASID-Caption/ASID-Caption
🔹 Models citing this paper:
• https://huggingface.co/AudioVisual-Caption/ASID-Captioner-3B
• https://huggingface.co/AudioVisual-Caption/ASID-Captioner-7B
✨ Datasets citing this paper:
• https://huggingface.co/datasets/AudioVisual-Caption/ASID-1M
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MLLM #VideoAI #DeepLearning #ComputerVision #NLP
✨Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
📝 Summary:
MLLMs struggle with fine-grained perception due to latency from iterative zooming. Region-to-Image Distillation internalizes zooming into a single forward pass by training a model on region-grounded data. This significantly improves fine-grained perception without tool calls, achieving leading pe...
🔹 Publication Date: Published on Feb 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11858
• PDF: https://arxiv.org/pdf/2602.11858
• Github: https://github.com/inclusionAI/Zooming-without-Zooming
🔹 Models citing this paper:
• https://huggingface.co/inclusionAI/ZwZ-8B
• https://huggingface.co/inclusionAI/ZwZ-4B
• https://huggingface.co/inclusionAI/ZwZ-7B
✨ Datasets citing this paper:
• https://huggingface.co/datasets/inclusionAI/ZwZ-RL-VQA
• https://huggingface.co/datasets/inclusionAI/ZoomBench
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MultimodalAI #ComputerVision #FineGrainedPerception #DeepLearning #ModelDistillation
📝 Summary:
MLLMs struggle with fine-grained perception due to latency from iterative zooming. Region-to-Image Distillation internalizes zooming into a single forward pass by training a model on region-grounded data. This significantly improves fine-grained perception without tool calls, achieving leading pe...
🔹 Publication Date: Published on Feb 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11858
• PDF: https://arxiv.org/pdf/2602.11858
• Github: https://github.com/inclusionAI/Zooming-without-Zooming
🔹 Models citing this paper:
• https://huggingface.co/inclusionAI/ZwZ-8B
• https://huggingface.co/inclusionAI/ZwZ-4B
• https://huggingface.co/inclusionAI/ZwZ-7B
✨ Datasets citing this paper:
• https://huggingface.co/datasets/inclusionAI/ZwZ-RL-VQA
• https://huggingface.co/datasets/inclusionAI/ZoomBench
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MultimodalAI #ComputerVision #FineGrainedPerception #DeepLearning #ModelDistillation
arXiv.org
Zooming without Zooming: Region-to-Image Distillation for...
Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelmed by global...
This media is not supported in your browser
VIEW IN TELEGRAM
✨OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
📝 Summary:
OneVision-Encoder improves visual understanding by aligning architectures with video compression principles. It uses codec-aligned sparsity to focus on high-entropy regions, significantly boosting efficiency and accuracy. This method outperforms strong vision backbones across various benchmarks, ...
🔹 Publication Date: Published on Feb 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.08683
• PDF: https://arxiv.org/pdf/2602.08683
• Project Page: https://www.lmms-lab.com/onevision-encoder/index.html
• Github: https://github.com/EvolvingLMMs-Lab/OneVision-Encoder/blob/main/docs/data_card.md
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MultimodalAI #ComputerVision #DeepLearning #Sparsity #AIResearch
📝 Summary:
OneVision-Encoder improves visual understanding by aligning architectures with video compression principles. It uses codec-aligned sparsity to focus on high-entropy regions, significantly boosting efficiency and accuracy. This method outperforms strong vision backbones across various benchmarks, ...
🔹 Publication Date: Published on Feb 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.08683
• PDF: https://arxiv.org/pdf/2602.08683
• Project Page: https://www.lmms-lab.com/onevision-encoder/index.html
• Github: https://github.com/EvolvingLMMs-Lab/OneVision-Encoder/blob/main/docs/data_card.md
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MultimodalAI #ComputerVision #DeepLearning #Sparsity #AIResearch
✨Intelligent AI Delegation
📝 Summary:
AI agents require better task decomposition and robust delegation. This paper proposes an adaptive framework for intelligent AI delegation, incorporating authority transfer, responsibility, and trust to handle dynamic environments and failures in complex AI and human networks.
🔹 Publication Date: Published on Feb 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11865
• PDF: https://arxiv.org/pdf/2602.11865
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AIDelegation #AIagents #TaskDecomposition #HumanAICollaboration #MultiAgentSystems
📝 Summary:
AI agents require better task decomposition and robust delegation. This paper proposes an adaptive framework for intelligent AI delegation, incorporating authority transfer, responsibility, and trust to handle dynamic environments and failures in complex AI and human networks.
🔹 Publication Date: Published on Feb 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11865
• PDF: https://arxiv.org/pdf/2602.11865
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AIDelegation #AIagents #TaskDecomposition #HumanAICollaboration #MultiAgentSystems
✨ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
📝 Summary:
ABot-M0 presents a unified framework for embodied agent development that standardizes diverse robotic data and employs action manifold learning to improve prediction efficiency and stability. AI-gener...
🔹 Publication Date: Published on Feb 11
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11236
• PDF: https://arxiv.org/pdf/2602.11236
• Project Page: https://amap-cvlab.github.io/ABot-Manipulation
• Github: https://github.com/amap-cvlab/ABot-Manipulation
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
📝 Summary:
ABot-M0 presents a unified framework for embodied agent development that standardizes diverse robotic data and employs action manifold learning to improve prediction efficiency and stability. AI-gener...
🔹 Publication Date: Published on Feb 11
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11236
• PDF: https://arxiv.org/pdf/2602.11236
• Project Page: https://amap-cvlab.github.io/ABot-Manipulation
• Github: https://github.com/amap-cvlab/ABot-Manipulation
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
✨SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
📝 Summary:
SciAgentGym and SciAgentBench enable evaluation of scientific tool-use capabilities, while SciForge improves agent performance through dependency graph modeling of tool interactions. AI-generated summ...
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12984
• PDF: https://arxiv.org/pdf/2602.12984
• Github: https://github.com/CMarsRover/SciAgentGYM
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
📝 Summary:
SciAgentGym and SciAgentBench enable evaluation of scientific tool-use capabilities, while SciForge improves agent performance through dependency graph modeling of tool interactions. AI-generated summ...
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12984
• PDF: https://arxiv.org/pdf/2602.12984
• Github: https://github.com/CMarsRover/SciAgentGYM
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
✨FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge Matching
📝 Summary:
FLAC enables maximum entropy RL for generative policies by regulating stochasticity via kinetic energy. It formulates policy optimization as a Generalized Schrödinger Bridge, avoiding explicit action density estimation while achieving strong performance.
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12829
• PDF: https://arxiv.org/pdf/2602.12829
• Project Page: https://pinkmoon-io.github.io/flac.github.io/
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#ReinforcementLearning #MachineLearning #GenerativeAI #OptimalTransport #KineticEnergy
📝 Summary:
FLAC enables maximum entropy RL for generative policies by regulating stochasticity via kinetic energy. It formulates policy optimization as a Generalized Schrödinger Bridge, avoiding explicit action density estimation while achieving strong performance.
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12829
• PDF: https://arxiv.org/pdf/2602.12829
• Project Page: https://pinkmoon-io.github.io/flac.github.io/
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#ReinforcementLearning #MachineLearning #GenerativeAI #OptimalTransport #KineticEnergy
✨Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
📝 Summary:
Xiaomi-Robotics-0 is an open-sourced vision-language-action model enabling real-time, high-performance robot manipulation. It leverages large-scale pre-training and specialized methods for fast execution on real robots, achieving SOTA simulation and high real-robot success.
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12684
• PDF: https://arxiv.org/pdf/2602.12684
• Project Page: https://xiaomi-robotics-0.github.io/
• Github: https://github.com/XiaomiRobotics/Xiaomi-Robotics-0
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#Robotics #AI #VisionLanguageModels #OpenSource #RobotManipulation
📝 Summary:
Xiaomi-Robotics-0 is an open-sourced vision-language-action model enabling real-time, high-performance robot manipulation. It leverages large-scale pre-training and specialized methods for fast execution on real robots, achieving SOTA simulation and high real-robot success.
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12684
• PDF: https://arxiv.org/pdf/2602.12684
• Project Page: https://xiaomi-robotics-0.github.io/
• Github: https://github.com/XiaomiRobotics/Xiaomi-Robotics-0
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#Robotics #AI #VisionLanguageModels #OpenSource #RobotManipulation
✨On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs
📝 Summary:
RL-finetuned VLMs are highly vulnerable to misleading text, severely impacting robustness and confidence. RL fine-tuning presents an accuracy-faithfulness trade-off, eroding reasoning reliability despite accuracy gains. This necessitates joint evaluation of correctness, robustness, and reasoning ...
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12506
• PDF: https://arxiv.org/pdf/2602.12506
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#VLM #Robustness #ReinforcementLearning #ChainOfThought #AI
📝 Summary:
RL-finetuned VLMs are highly vulnerable to misleading text, severely impacting robustness and confidence. RL fine-tuning presents an accuracy-faithfulness trade-off, eroding reasoning reliability despite accuracy gains. This necessitates joint evaluation of correctness, robustness, and reasoning ...
🔹 Publication Date: Published on Feb 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.12506
• PDF: https://arxiv.org/pdf/2602.12506
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#VLM #Robustness #ReinforcementLearning #ChainOfThought #AI
✨TADA! Tuning Audio Diffusion Models through Activation Steering
📝 Summary:
Research reveals that specific attention layers in audio diffusion models control distinct musical concepts, enabling precise manipulation of audio features through activation steering. AI-generated s...
🔹 Publication Date: Published on Feb 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11910
• PDF: https://arxiv.org/pdf/2602.11910
• Project Page: https://audio-steering.github.io
• Github: https://github.com/luk-st/steer-audio
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
📝 Summary:
Research reveals that specific attention layers in audio diffusion models control distinct musical concepts, enabling precise manipulation of audio features through activation steering. AI-generated s...
🔹 Publication Date: Published on Feb 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11910
• PDF: https://arxiv.org/pdf/2602.11910
• Project Page: https://audio-steering.github.io
• Github: https://github.com/luk-st/steer-audio
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
✨Light4D: Training-Free Extreme Viewpoint 4D Video Relighting
📝 Summary:
Light4D enables consistent 4D video synthesis under target illumination through disentangled flow guidance and temporal consistent attention mechanisms. AI-generated summary Recent advances in diffusi...
🔹 Publication Date: Published on Feb 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11769
• PDF: https://arxiv.org/pdf/2602.11769
• Project Page: https://aigeeksgroup.github.io/Light4D
• Github: https://aigeeksgroup.github.io/Light4D
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
📝 Summary:
Light4D enables consistent 4D video synthesis under target illumination through disentangled flow guidance and temporal consistent attention mechanisms. AI-generated summary Recent advances in diffusi...
🔹 Publication Date: Published on Feb 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11769
• PDF: https://arxiv.org/pdf/2602.11769
• Project Page: https://aigeeksgroup.github.io/Light4D
• Github: https://aigeeksgroup.github.io/Light4D
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AI #DataScience #MachineLearning #HuggingFace #Research
arXiv.org
Light4D: Training-Free Extreme Viewpoint 4D Video Relighting
Recent advances in diffusion-based generative models have established a new paradigm for image and video relighting. However, extending these capabilities to 4D relighting remains challenging, due...