✨WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance

📝 Summary:
WebCoach introduces a self-evolving framework for web agents with persistent cross-session memory. It uses a WebCondenser, External Memory Store, and a Coach to learn from past experiences without retraining. This significantly improves task success and enables smaller models to match larger LLM ...

🔹 Publication Date: Published on Nov 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12997
• PDF: https://arxiv.org/pdf/2511.12997

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#WebAgents #AI #MachineLearning #LLM #MemoryAI

✨MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

📝 Summary:
MiroThinker v1.0 is an open-source research agent introducing 'interactive scaling.' It trains models with reinforcement learning for deeper agent-environment interactions, performing up to 600 tool calls per task. This achieves state-of-the-art performance and establishes interaction depth as a ...

🔹 Publication Date: Published on Nov 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.11793
• PDF: https://arxiv.org/pdf/2511.11793
• Project Page: https://dr.miromind.ai/
• Github: https://github.com/MiroMindAI/MiroThinker

🔹 Models citing this paper:
• https://huggingface.co/miromind-ai/MiroThinker-v1.0-72B
• https://huggingface.co/miromind-ai/MiroThinker-v1.0-8B
• https://huggingface.co/miromind-ai/MiroThinker-v1.0-30B

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#MiroThinker #ResearchAgents #ReinforcementLearning #OpenSourceAI #LLM

✨P1: Mastering Physics Olympiads with Reinforcement Learning

📝 Summary:
P1 is a family of open-source physics reasoning models trained via reinforcement learning. P1-235B-A22B achieved Gold-medal performance at IPhO 2025 and won 12 other competitions. These models also show strong generalizability on other reasoning tasks.

🔹 Publication Date: Published on Nov 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.13612
• PDF: https://arxiv.org/pdf/2511.13612
• Project Page: https://prime-rl.github.io/P1/
• Github: https://github.com/PRIME-RL/P1

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#ReinforcementLearning #Physics #AI #MachineLearning #OpenSource

✨MicroVQA++: High-Quality Microscopy Reasoning Dataset with Weakly Supervised Graphs for Multimodal Large Language Model

📝 Summary:
MicroVQA plus plus is a new high-quality microscopy VQA dataset built via a three-stage process. This includes HiCQA-Graph, a novel filtering method using NLI, CLIP, and MLLM signals. The dataset enables strong microscopy reasoning performance for MLLMs.

🔹 Publication Date: Published on Nov 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.11407
• PDF: https://arxiv.org/pdf/2511.11407
• Github: https://github.com/ieellee/MicroVQA-PlusPlus

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#MLLM #Microscopy #VQA #AIResearch #Dataset

✨Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance

📝 Summary:
SoCE is a novel model souping technique that boosts LLM performance. It uses non-uniform weighted averaging of expert models identified for specific benchmark categories, unlike uniform methods. This leads to state-of-the-art results and improved robustness.

🔹 Publication Date: Published on Nov 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.13254
• PDF: https://arxiv.org/pdf/2511.13254

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#LLMs #ModelSouping #MachineLearning #AI #StateOfTheArt

✨Instella: Fully Open Language Models with Stellar Performance

📝 Summary:
Instella is a family of fully open language models trained on open data. It achieves state-of-the-art among fully open models and competes with leading open-weight LLMs. Specialized variants for long context and math reasoning are also offered.

🔹 Publication Date: Published on Nov 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.10628
• PDF: https://arxiv.org/pdf/2511.10628
• Github: https://github.com/AMD-AGI/Instella

🔹 Models citing this paper:
• https://huggingface.co/amd/AMD-OLMo
• https://huggingface.co/amd/Instella-3B-Instruct
• https://huggingface.co/amd/Instella-3B

✨ Datasets citing this paper:
• https://huggingface.co/datasets/amd/Instella-Long
• https://huggingface.co/datasets/amd/Instella-GSM8K-synthetic

✨ Spaces citing this paper:
• https://huggingface.co/spaces/DexterSptizu/AMD-OLMo-1B
• https://huggingface.co/spaces/universeofml/DeepFocusTrain

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#LLMs #OpenSource #AI #MachineLearning #NLP

✨Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs

📝 Summary:
EvoSynth is a new framework that autonomously engineers and evolves novel, code-based jailbreak methods for LLMs, moving beyond prompt refinement. It uses self-correction to create diverse and highly successful attacks, achieving 85.5% ASR against robust models.

🔹 Publication Date: Published on Nov 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12710
• PDF: https://arxiv.org/pdf/2511.12710

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#LLMs #JailbreakAttacks #AISecurity #EvolutionaryAlgorithms #AIResearch

✨Dynamic Reflections: Probing Video Representations with Text Alignment

📝 Summary:
This work presents the first comprehensive study on video-text representation alignment. It reveals alignment depends on data richness and correlates with downstream task performance, suggesting its value for general video understanding. This introduces video-text alignment as a zero-shot method ...

🔹 Publication Date: Published on Nov 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02767
• PDF: https://arxiv.org/pdf/2511.02767
• Github: https://video-prh.github.io/

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#VideoUnderstanding #TextAlignment #VideoTextAI #ZeroShotLearning #RepresentationLearning

✨Back to Basics: Let Denoising Generative Models Denoise

📝 Summary:
Denoising diffusion models should predict clean images directly, not noise, leveraging the data manifold assumption. The paper introduces JiT, a model using simple, large-patch Transformers that achieves competitive generative results on ImageNet.

🔹 Publication Date: Published on Nov 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.13720
• PDF: https://arxiv.org/pdf/2511.13720
• Github: https://github.com/LTH14/JiT

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#DiffusionModels #GenerativeAI #DeepLearning #ComputerVision #AIResearch

✨Genomic Next-Token Predictors are In-Context Learners

📝 Summary:
In-context learning ICL emerges organically in genomic sequences through large-scale predictive training, mirroring its behavior in language models. This first evidence suggests ICL is a general phenomenon of large-scale modeling, not exclusive to human language.

🔹 Publication Date: Published on Nov 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12797
• PDF: https://arxiv.org/pdf/2511.12797

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#Genomics #InContextLearning #AI #MachineLearning #LLMs

✨A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain

📝 Summary:
This paper proposes a decentralized RAG system using a blockchain-based mechanism to score data source reliability. It dynamically evaluates sources, boosting performance by 10.7% compared to centralized systems and achieving 56% cost savings in unreliable environments.

🔹 Publication Date: Published on Nov 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07577
• PDF: https://arxiv.org/pdf/2511.07577
• Github: https://github.com/yining610/Reliable-dRAG

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#RAG #Blockchain #DecentralizedAI #GenerativeAI #AIResearch

✨UFO^3: Weaving the Digital Agent Galaxy

📝 Summary:
UFO^3 unifies diverse digital devices into a single orchestration fabric, enabling AI agents to collaborate seamlessly across platforms. It models tasks dynamically for asynchronous execution, achieving efficient, resilient, and accurate cross-device task orchestration with improved parallelism a...

🔹 Publication Date: Published on Nov 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.11332
• PDF: https://arxiv.org/pdf/2511.11332
• Project Page: https://microsoft.github.io/UFO/
• Github: https://github.com/microsoft/UFO/

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AIAgents #TaskOrchestration #DistributedSystems #EdgeAI #MultiAgentSystems

✨UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity

📝 Summary:
UnSAMv2 enables continuous segmentation granularity control for the SAM model without human annotations. It uses self-supervised learning on unlabeled data to discover mask-granularity pairs and a novel control embedding. UnSAMv2 significantly enhances SAM-2s performance across various segmentati...

🔹 Publication Date: Published on Nov 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.13714
• PDF: https://arxiv.org/pdf/2511.13714
• Project Page: https://yujunwei04.github.io/UnSAMv2-Project-Page/
• Github: https://github.com/yujunwei04/UnSAMv2

✨ Spaces citing this paper:
• https://huggingface.co/spaces/yujunwei04/UnSAMv2

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #ComputerVision #SelfSupervisedLearning #ImageSegmentation #DeepLearning

✨OpenUS: A Fully Open-Source Foundation Model for Ultrasound Image Analysis via Self-Adaptive Masked Contrastive Learning

📝 Summary:
OpenUS is an open-source ultrasound foundation model built on a large public dataset. It uses a vision Mamba backbone and a novel self-adaptive masking framework to enhance pre-training, enabling label-efficient fine-tuning for various US tasks.

🔹 Publication Date: Published on Nov 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.11510
• PDF: https://arxiv.org/pdf/2511.11510
• Github: https://github.com/XZheng0427/OpenUS

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#OpenSource #FoundationModel #UltrasoundAI #MachineLearning #MedicalImaging

✨Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing

📝 Summary:
SerenQA evaluates LLMs for discovering surprising, valuable serendipitous answers in scientific knowledge graphs, focusing on drug repurposing. It uses a new serendipity metric. Experiments show LLMs struggle with genuine surprising insights.

🔹 Publication Date: Published on Nov 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12472
• PDF: https://arxiv.org/pdf/2511.12472
• Project Page: https://cwru-db-group.github.io/serenQA
• Github: https://github.com/CWRU-DB-Group/DrugKG

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#LLM #KnowledgeGraphs #DrugRepurposing #AI #Serendipity

✨SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization

📝 Summary:
SafeGRPO introduces a self-rewarded, rule-governed framework for multimodal safety alignment in MLLMs. It integrates verifiable reward construction and step-guided safety thinking to improve robustness against compositional risks and enhance reasoning stability.

🔹 Publication Date: Published on Nov 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12982
• PDF: https://arxiv.org/pdf/2511.12982

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#MLLMs #AISafety #MultimodalAI #ReinforcementLearning #AIResearch

✨Error-Driven Scene Editing for 3D Grounding in Large Language Models

📝 Summary:
DEER-3D improves 3D LLM grounding by iteratively editing and retraining models. It diagnoses predicate-level errors, then generates targeted 3D scene edits as counterfactuals to enhance spatial understanding and accuracy.

🔹 Publication Date: Published on Nov 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.14086
• PDF: https://arxiv.org/pdf/2511.14086
• Github: https://github.com/zhangyuejoslin/Deer-3D

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#LLMs #3DGrounding #ComputerVision #DeepLearning #AIResearch

✨ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning

📝 Summary:
ATLAS is a new, high-difficulty, multidisciplinary benchmark for LLMs, featuring 800 original problems across seven scientific fields. It addresses current benchmark limitations with complex, open-ended answers and aims to differentiate advanced scientific reasoning, serving as a ruler for AGI pr...

🔹 Publication Date: Published on Nov 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.14366
• PDF: https://arxiv.org/pdf/2511.14366

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#LLM #AGI #AIResearch #ScientificReasoning #Benchmark

✨Orion: A Unified Visual Agent for Multimodal Perception, Advanced Visual Reasoning and Execution

📝 Summary:
Orion is a visual agent framework that orchestrates specialized computer vision tools to execute complex visual workflows. It achieves competitive performance on benchmarks and enables autonomous, tool-driven visual reasoning.

🔹 Publication Date: Published on Nov 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.14210
• PDF: https://arxiv.org/pdf/2511.14210

==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#ComputerVision #AIagents #VisualReasoning #MultimodalAI #DeepLearning