✨IterResearch: Rethinking Long-Horizon Agents via Markovian State Reconstruction
📝 Summary:
IterResearch improves long-horizon reasoning by reformulating it as a Markov Decision Process with strategic workspace reconstruction. This novel paradigm overcomes context suffocation, achieving substantial performance gains and unprecedented interaction scaling, and also serves as an effective ...
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07327
• PDF: https://arxiv.org/pdf/2511.07327
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#ReinforcementLearning #AI #MachineLearning #AIagents #MDP
📝 Summary:
IterResearch improves long-horizon reasoning by reformulating it as a Markov Decision Process with strategic workspace reconstruction. This novel paradigm overcomes context suffocation, achieving substantial performance gains and unprecedented interaction scaling, and also serves as an effective ...
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07327
• PDF: https://arxiv.org/pdf/2511.07327
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#ReinforcementLearning #AI #MachineLearning #AIagents #MDP
✨MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
📝 Summary:
MVU-Eval is a new comprehensive benchmark for evaluating Multi-Video Understanding in Multimodal Large Language Models. It addresses a critical gap in existing single-video benchmarks and reveals significant performance limitations in current MLLMs for multi-video scenarios.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07250
• PDF: https://arxiv.org/pdf/2511.07250
• Project Page: https://huggingface.co/datasets/MVU-Eval-Team/MVU-Eval-Data
• Github: https://github.com/NJU-LINK/MVU-Eval
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MLLMs #VideoUnderstanding #AI #Benchmarking #ComputerVision
📝 Summary:
MVU-Eval is a new comprehensive benchmark for evaluating Multi-Video Understanding in Multimodal Large Language Models. It addresses a critical gap in existing single-video benchmarks and reveals significant performance limitations in current MLLMs for multi-video scenarios.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07250
• PDF: https://arxiv.org/pdf/2511.07250
• Project Page: https://huggingface.co/datasets/MVU-Eval-Team/MVU-Eval-Data
• Github: https://github.com/NJU-LINK/MVU-Eval
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MLLMs #VideoUnderstanding #AI #Benchmarking #ComputerVision
✨The Station: An Open-World Environment for AI-Driven Discovery
📝 Summary:
The Station is an open-world multi-agent AI environment enabling autonomous scientific discovery. Agents engage in full scientific journeys, achieving state-of-the-art results across diverse benchmarks. This new paradigm fosters emergent behaviors and novel method development, moving beyond rigid...
🔹 Publication Date: Published on Nov 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06309
• PDF: https://arxiv.org/pdf/2511.06309
• Github: https://github.com/dualverse-ai/station
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#AI #MultiAgentSystems #ScientificDiscovery #OpenWorldAI #AutonomousAI
📝 Summary:
The Station is an open-world multi-agent AI environment enabling autonomous scientific discovery. Agents engage in full scientific journeys, achieving state-of-the-art results across diverse benchmarks. This new paradigm fosters emergent behaviors and novel method development, moving beyond rigid...
🔹 Publication Date: Published on Nov 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06309
• PDF: https://arxiv.org/pdf/2511.06309
• Github: https://github.com/dualverse-ai/station
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#AI #MultiAgentSystems #ScientificDiscovery #OpenWorldAI #AutonomousAI
❤1
This media is not supported in your browser
VIEW IN TELEGRAM
✨Robot Learning from a Physical World Model
📝 Summary:
PhysWorld enables robots to learn accurate manipulation from AI-generated videos by integrating video generation with physical world modeling. This approach grounds visual guidance into physically executable actions, eliminating the need for real robot data.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07416
• PDF: https://arxiv.org/pdf/2511.07416
• Project Page: https://pointscoder.github.io/PhysWorld_Web/
• Github: https://github.com/PointsCoder/OpenReal2Sim
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#RobotLearning #Robotics #AI #PhysicalModeling #MachineLearning
📝 Summary:
PhysWorld enables robots to learn accurate manipulation from AI-generated videos by integrating video generation with physical world modeling. This approach grounds visual guidance into physically executable actions, eliminating the need for real robot data.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07416
• PDF: https://arxiv.org/pdf/2511.07416
• Project Page: https://pointscoder.github.io/PhysWorld_Web/
• Github: https://github.com/PointsCoder/OpenReal2Sim
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#RobotLearning #Robotics #AI #PhysicalModeling #MachineLearning
✨DigiData: Training and Evaluating General-Purpose Mobile Control Agents
📝 Summary:
DigiData provides a diverse, high-quality dataset for training mobile control agents with complex goals from app feature exploration. DigiData-Bench offers dynamic AI-powered evaluation protocols, improving agent assessment beyond common metrics.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07413
• PDF: https://arxiv.org/pdf/2511.07413
• Github: https://facebookresearch.github.io/DigiData
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MobileAgents #ArtificialIntelligence #MachineLearning #Datasets #AgentTraining
📝 Summary:
DigiData provides a diverse, high-quality dataset for training mobile control agents with complex goals from app feature exploration. DigiData-Bench offers dynamic AI-powered evaluation protocols, improving agent assessment beyond common metrics.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07413
• PDF: https://arxiv.org/pdf/2511.07413
• Github: https://facebookresearch.github.io/DigiData
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MobileAgents #ArtificialIntelligence #MachineLearning #Datasets #AgentTraining
❤1
✨SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?
📝 Summary:
SWE-fficiency is a new benchmark evaluating how language models optimize real-world software repositories for performance on actual workloads. Agents must identify bottlenecks and generate correct code patches matching expert speedup. Current agents significantly underperform, struggling with loc...
🔹 Publication Date: Published on Nov 8
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06090
• PDF: https://arxiv.org/pdf/2511.06090
• Project Page: https://swefficiency.com/
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #SoftwareOptimization #PerformanceTuning #AIagents #Benchmarking
📝 Summary:
SWE-fficiency is a new benchmark evaluating how language models optimize real-world software repositories for performance on actual workloads. Agents must identify bottlenecks and generate correct code patches matching expert speedup. Current agents significantly underperform, struggling with loc...
🔹 Publication Date: Published on Nov 8
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06090
• PDF: https://arxiv.org/pdf/2511.06090
• Project Page: https://swefficiency.com/
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #SoftwareOptimization #PerformanceTuning #AIagents #Benchmarking
✨LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAs
📝 Summary:
LUT-LLM is an FPGA accelerator for LLM inference that leverages on-chip memory to shift computation from arithmetic to memory-based operations via table lookups. This innovative approach achieves 1.66x lower latency than AMD MI210 and 1.72x higher energy efficiency than NVIDIA A100 for a 1.7B LLM.
🔹 Publication Date: Published on Nov 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06174
• PDF: https://arxiv.org/pdf/2511.06174
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #FPGA #AI #DeepLearning #AIHardware
📝 Summary:
LUT-LLM is an FPGA accelerator for LLM inference that leverages on-chip memory to shift computation from arithmetic to memory-based operations via table lookups. This innovative approach achieves 1.66x lower latency than AMD MI210 and 1.72x higher energy efficiency than NVIDIA A100 for a 1.7B LLM.
🔹 Publication Date: Published on Nov 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06174
• PDF: https://arxiv.org/pdf/2511.06174
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #FPGA #AI #DeepLearning #AIHardware
✨DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation
📝 Summary:
This study develops a two-stage reinforcement learning method for competitive code generation. It uses tailored data curation and a hard-focus curriculum, achieving state-of-the-art performance on competitive programming benchmarks.
🔹 Publication Date: Published on Nov 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06307
• PDF: https://arxiv.org/pdf/2511.06307
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#ReinforcementLearning #CodeGeneration #DataCuration #MachineLearning #AIResearch
📝 Summary:
This study develops a two-stage reinforcement learning method for competitive code generation. It uses tailored data curation and a hard-focus curriculum, achieving state-of-the-art performance on competitive programming benchmarks.
🔹 Publication Date: Published on Nov 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06307
• PDF: https://arxiv.org/pdf/2511.06307
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#ReinforcementLearning #CodeGeneration #DataCuration #MachineLearning #AIResearch
❤1
✨SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization
📝 Summary:
SofT-GRPO is a novel algorithm that enhances soft-thinking in LLMs by integrating Gumbel noise and Gumbel-Softmax. This method successfully reinforces soft-thinking policies, enabling LLMs to outperform discrete-token reinforcement learning approaches, especially on complex tasks.
🔹 Publication Date: Published on Nov 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06411
• PDF: https://arxiv.org/pdf/2511.06411
🔹 Models citing this paper:
• https://huggingface.co/zz1358m/SofT-GRPO-master
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #ReinforcementLearning #AI #MachineLearning #DeepLearning
📝 Summary:
SofT-GRPO is a novel algorithm that enhances soft-thinking in LLMs by integrating Gumbel noise and Gumbel-Softmax. This method successfully reinforces soft-thinking policies, enabling LLMs to outperform discrete-token reinforcement learning approaches, especially on complex tasks.
🔹 Publication Date: Published on Nov 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06411
• PDF: https://arxiv.org/pdf/2511.06411
🔹 Models citing this paper:
• https://huggingface.co/zz1358m/SofT-GRPO-master
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #ReinforcementLearning #AI #MachineLearning #DeepLearning
✨Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models
📝 Summary:
Diffusion-SDPO improves text-to-image quality by fixing a flaw in standard DPO where preferred output error can increase. It uses a safeguarded update to adaptively scale the loser gradient, ensuring the preferred output's error never increases. This leads to consistent quality gains across bench...
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03317
• PDF: https://arxiv.org/pdf/2511.03317
• Github: https://github.com/AIDC-AI/Diffusion-SDPO
🔹 Models citing this paper:
• https://huggingface.co/AIDC-AI/Diffusion-SDPO
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#DiffusionModels #DPO #TextToImage #GenerativeAI #AI
📝 Summary:
Diffusion-SDPO improves text-to-image quality by fixing a flaw in standard DPO where preferred output error can increase. It uses a safeguarded update to adaptively scale the loser gradient, ensuring the preferred output's error never increases. This leads to consistent quality gains across bench...
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03317
• PDF: https://arxiv.org/pdf/2511.03317
• Github: https://github.com/AIDC-AI/Diffusion-SDPO
🔹 Models citing this paper:
• https://huggingface.co/AIDC-AI/Diffusion-SDPO
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#DiffusionModels #DPO #TextToImage #GenerativeAI #AI
✨VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models
📝 Summary:
VADER is an LLM framework enhancing video anomaly understanding. It integrates keyframe object relations and visual cues to provide detailed, causally grounded denoscriptions and robust question answering, advancing explainable anomaly analysis.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07299
• PDF: https://arxiv.org/pdf/2511.07299
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #VideoAnalytics #AnomalyDetection #Causality #ExplainableAI
📝 Summary:
VADER is an LLM framework enhancing video anomaly understanding. It integrates keyframe object relations and visual cues to provide detailed, causally grounded denoscriptions and robust question answering, advancing explainable anomaly analysis.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07299
• PDF: https://arxiv.org/pdf/2511.07299
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #VideoAnalytics #AnomalyDetection #Causality #ExplainableAI
✨MPJudge: Towards Perceptual Assessment of Music-Induced Paintings
📝 Summary:
MPJudge is a new framework for assessing music-induced paintings. It integrates music features into a visual encoder using a modulation-based fusion mechanism, outperforming existing emotion models by directly modeling perceptual coherence. It also identifies music-relevant regions better.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07137
• PDF: https://arxiv.org/pdf/2511.07137
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MusicAndArt #ComputerVision #MachineLearning #DeepLearning #MultimodalAI
📝 Summary:
MPJudge is a new framework for assessing music-induced paintings. It integrates music features into a visual encoder using a modulation-based fusion mechanism, outperforming existing emotion models by directly modeling perceptual coherence. It also identifies music-relevant regions better.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07137
• PDF: https://arxiv.org/pdf/2511.07137
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MusicAndArt #ComputerVision #MachineLearning #DeepLearning #MultimodalAI
❤1
✨Do LLMs Feel? Teaching Emotion Recognition with Prompts, Retrieval, and Curriculum Learning
📝 Summary:
PRC-Emo is a new framework that significantly improves LLMs' emotion recognition in conversations. It combines prompt engineering, demonstration retrieval, and curriculum learning, achieving state-of-the-art results on benchmark datasets.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07061
• PDF: https://arxiv.org/pdf/2511.07061
• Github: https://github.com/LiXinran6/PRC-Emo
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #EmotionRecognition #NLP #AIResearch #MachineLearning
📝 Summary:
PRC-Emo is a new framework that significantly improves LLMs' emotion recognition in conversations. It combines prompt engineering, demonstration retrieval, and curriculum learning, achieving state-of-the-art results on benchmark datasets.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07061
• PDF: https://arxiv.org/pdf/2511.07061
• Github: https://github.com/LiXinran6/PRC-Emo
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #EmotionRecognition #NLP #AIResearch #MachineLearning
✨10 Open Challenges Steering the Future of Vision-Language-Action Models
📝 Summary:
This paper identifies 10 principal challenges in vision-language-action VLA models, including multimodality, reasoning, and safety. It also explores emerging trends like spatial understanding and data synthesis. The goal is to accelerate VLA model development and wider acceptance.
🔹 Publication Date: Published on Nov 8
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.05936
• PDF: https://arxiv.org/pdf/2511.05936
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#VLA #AI #MachineLearning #ComputerVision #NLP
📝 Summary:
This paper identifies 10 principal challenges in vision-language-action VLA models, including multimodality, reasoning, and safety. It also explores emerging trends like spatial understanding and data synthesis. The goal is to accelerate VLA model development and wider acceptance.
🔹 Publication Date: Published on Nov 8
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.05936
• PDF: https://arxiv.org/pdf/2511.05936
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#VLA #AI #MachineLearning #ComputerVision #NLP
✨Qwen-Image Technical Report
📝 Summary:
Qwen-Image is an image generation model that significantly advances complex text rendering through a comprehensive data pipeline and progressive training across languages. It also improves precise image editing via a dual-encoding mechanism and multi-task training for enhanced consistency and vis...
🔹 Publication Date: Published on Aug 4
🔹 Paper Links:
• arXiv Page: https://arxivexplained.com/papers/qwen-image-technical-report
• PDF: https://arxiv.org/pdf/2508.02324
• Github: https://github.com/QwenLM/Qwen-Image
🔹 Models citing this paper:
• https://huggingface.co/Qwen/Qwen-Image
• https://huggingface.co/Qwen/Qwen-Image-Edit
• https://huggingface.co/Qwen/Qwen-Image-Edit-2509
✨ Spaces citing this paper:
• https://huggingface.co/spaces/linoyts/Qwen-Image-Edit-Angles
• https://huggingface.co/spaces/tori29umai/Qwen-Image-2509-MultipleAngles
• https://huggingface.co/spaces/linoyts/Qwen-Image-Edit-next-scene
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#ImageGeneration #AI #DeepLearning #ComputerVision #TextToImage
📝 Summary:
Qwen-Image is an image generation model that significantly advances complex text rendering through a comprehensive data pipeline and progressive training across languages. It also improves precise image editing via a dual-encoding mechanism and multi-task training for enhanced consistency and vis...
🔹 Publication Date: Published on Aug 4
🔹 Paper Links:
• arXiv Page: https://arxivexplained.com/papers/qwen-image-technical-report
• PDF: https://arxiv.org/pdf/2508.02324
• Github: https://github.com/QwenLM/Qwen-Image
🔹 Models citing this paper:
• https://huggingface.co/Qwen/Qwen-Image
• https://huggingface.co/Qwen/Qwen-Image-Edit
• https://huggingface.co/Qwen/Qwen-Image-Edit-2509
✨ Spaces citing this paper:
• https://huggingface.co/spaces/linoyts/Qwen-Image-Edit-Angles
• https://huggingface.co/spaces/tori29umai/Qwen-Image-2509-MultipleAngles
• https://huggingface.co/spaces/linoyts/Qwen-Image-Edit-next-scene
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#ImageGeneration #AI #DeepLearning #ComputerVision #TextToImage
Arxivexplained
Qwen-Image Technical Report - Explained Simply
By Chenfei Wu, Jiahao Li, Jingren Zhou et al.. # Qwen-Image: Breaking Through AI's Text and Image Editing Barriers
**The Problem:** Current AI ima...
**The Problem:** Current AI ima...
✨Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads
📝 Summary:
This paper introduces lightweight UHeads, transformer-based uncertainty quantification heads, to efficiently verify LLM reasoning steps. UHeads estimate uncertainty from the LLM's internal states, outperforming larger verification models while being scalable and effective across various domains.
🔹 Publication Date: Published on Nov 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06209
• PDF: https://arxiv.org/pdf/2511.06209
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #AI #MachineLearning #UncertaintyQuantification #ModelVerification
📝 Summary:
This paper introduces lightweight UHeads, transformer-based uncertainty quantification heads, to efficiently verify LLM reasoning steps. UHeads estimate uncertainty from the LLM's internal states, outperforming larger verification models while being scalable and effective across various domains.
🔹 Publication Date: Published on Nov 9
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.06209
• PDF: https://arxiv.org/pdf/2511.06209
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #AI #MachineLearning #UncertaintyQuantification #ModelVerification
✨Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models
📝 Summary:
Omni-AVSR is a unified audio-visual LLM that efficiently supports ASR, VSR, and AVSR. It uses multi-granularity training and parameter-efficient adaptation to achieve high accuracy while significantly reducing resource use compared to separate models.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07253
• PDF: https://arxiv.org/pdf/2511.07253
• Project Page: https://umbertocappellazzo.github.io/Omni-AVSR
• Github: https://github.com/umbertocappellazzo/Omni-AVSR
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#SpeechRecognition #LLM #MultimodalAI #DeepLearning #AIResearch
📝 Summary:
Omni-AVSR is a unified audio-visual LLM that efficiently supports ASR, VSR, and AVSR. It uses multi-granularity training and parameter-efficient adaptation to achieve high accuracy while significantly reducing resource use compared to separate models.
🔹 Publication Date: Published on Nov 10
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.07253
• PDF: https://arxiv.org/pdf/2511.07253
• Project Page: https://umbertocappellazzo.github.io/Omni-AVSR
• Github: https://github.com/umbertocappellazzo/Omni-AVSR
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#SpeechRecognition #LLM #MultimodalAI #DeepLearning #AIResearch
✨Ariadne: A Controllable Framework for Probing and Extending VLM Reasoning Boundaries
📝 Summary:
Ariadne is a framework using synthetic mazes and RLVR to enhance VLM visual-centric spatial reasoning. It expanded VLM capabilities, raising accuracy from 0 percent to over 50 percent, and significantly improved zero-shot generalization on real-world benchmarks.
🔹 Publication Date: Published on Nov 1
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.00710
• PDF: https://arxiv.org/pdf/2511.00710
• Project Page: https://mingheshen.github.io/Ariadne/
🔹 Models citing this paper:
• https://huggingface.co/KOKKKOKK/Ariadne
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#VLM #AI #MachineLearning #ComputerVision #SpatialReasoning
📝 Summary:
Ariadne is a framework using synthetic mazes and RLVR to enhance VLM visual-centric spatial reasoning. It expanded VLM capabilities, raising accuracy from 0 percent to over 50 percent, and significantly improved zero-shot generalization on real-world benchmarks.
🔹 Publication Date: Published on Nov 1
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.00710
• PDF: https://arxiv.org/pdf/2511.00710
• Project Page: https://mingheshen.github.io/Ariadne/
🔹 Models citing this paper:
• https://huggingface.co/KOKKKOKK/Ariadne
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#VLM #AI #MachineLearning #ComputerVision #SpatialReasoning
✨Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
📝 Summary:
Ovi is a unified audio-video generation model using twin-DiT modules with blockwise cross-modal fusion. This innovative design ensures natural synchronization and high-quality multimodal outputs, simplifying previous multi-stage approaches.
🔹 Publication Date: Published on Sep 30
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.01284
• PDF: https://arxiv.org/pdf/2510.01284
• Project Page: https://aaxwaz.github.io/Ovi
• Github: https://github.com/character-ai/Ovi
🔹 Models citing this paper:
• https://huggingface.co/chetwinlow1/Ovi
• https://huggingface.co/rkfg/Ovi-fp8_quantized
✨ Spaces citing this paper:
• https://huggingface.co/spaces/akhaliq/Ovi
• https://huggingface.co/spaces/deddytoyota/Ovi
• https://huggingface.co/spaces/alexnasa/Ovi-ZEROGPU
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#AudioVideoGeneration #MultimodalAI #DeepLearning #CrossModalFusion #AIResearch
📝 Summary:
Ovi is a unified audio-video generation model using twin-DiT modules with blockwise cross-modal fusion. This innovative design ensures natural synchronization and high-quality multimodal outputs, simplifying previous multi-stage approaches.
🔹 Publication Date: Published on Sep 30
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.01284
• PDF: https://arxiv.org/pdf/2510.01284
• Project Page: https://aaxwaz.github.io/Ovi
• Github: https://github.com/character-ai/Ovi
🔹 Models citing this paper:
• https://huggingface.co/chetwinlow1/Ovi
• https://huggingface.co/rkfg/Ovi-fp8_quantized
✨ Spaces citing this paper:
• https://huggingface.co/spaces/akhaliq/Ovi
• https://huggingface.co/spaces/deddytoyota/Ovi
• https://huggingface.co/spaces/alexnasa/Ovi-ZEROGPU
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#AudioVideoGeneration #MultimodalAI #DeepLearning #CrossModalFusion #AIResearch
arXiv.org
Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
Audio-video generation has often relied on complex multi-stage architectures or sequential synthesis of sound and visuals. We introduce Ovi, a unified paradigm for audio-video generation that...