What changed in AI
Every material change the connectors observe becomes an event with a source. Dates are when the change occurred (effective date when known); hover a date for the observation time. Older events load with a cursor.
3,040 events until 16 Sept 2026 · ordered by occurrence
15 Sept 2026 50
- Property changedPaperMoPA: Coordinated Mobile Manipulation via Subsystem-Specific Perception Alignment
MoPA: Coordinated Mobile Manipulation via Subsystem-Specific Perception Alignment: arxiv announce type changed from cross to replace
Arxiv announce typecross→replacearxiv - Property changedPaperMoPA: Coordinated Mobile Manipulation via Subsystem-Specific Perception Alignment
MoPA: Coordinated Mobile Manipulation via Subsystem-Specific Perception Alignment: published at changed from 2026-09-14T04:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published14 Sept 2026→15 Sept 2026arxiv - Property changedPaperMGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modeling
MGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modeling: arxiv announce type changed from new to replace
Arxiv announce typenew→replacearxiv - Property changedPaperMGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modeling
MGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modeling: published at changed from 2026-09-14T04:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published14 Sept 2026→15 Sept 2026arxiv - Property changedPaperRecursive Code World Models: Building Complex Worlds through Recursive Scene Programs
Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs: arxiv announce type changed from new to replace
Arxiv announce typenew→replacearxiv - Property changedPaperRecursive Code World Models: Building Complex Worlds through Recursive Scene Programs
Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs: published at changed from 2026-09-11T04:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published11 Sept 2026→15 Sept 2026arxiv - Property changedPaperFreeTransformSR: Efficient Lightweight Image Super-Resolution via Free Low-Rank Learnable Transform
FreeTransformSR: Efficient Lightweight Image Super-Resolution via Free Low-Rank Learnable Transform: published at changed from 2026-09-11T04:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published11 Sept 2026→15 Sept 2026arxiv - Property changedPaperMRI-based Deep Radiomic Phenotyping of Neuromuscular Disorders: A Topology-driven Characterization
MRI-based Deep Radiomic Phenotyping of Neuromuscular Disorders: A Topology-driven Characterization: published at changed from 2026-09-11T04:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published11 Sept 2026→15 Sept 2026arxiv - Property changedPaperMRI-based Deep Radiomic Phenotyping of Neuromuscular Disorders: A Topology-driven Characterization
MRI-based Deep Radiomic Phenotyping of Neuromuscular Disorders: A Topology-driven Characterization: authors changed from ["Martyna \\.Zur", "{\\L}ukasz Pi\\'orecki", "Marek Socha… to ["Ana Topf", "Benedikt Schoeser", "Filippo Santorelli", "…
AuthorsMartyna \.Zur, {\L}ukasz Pi\'orecki, Marek Socha, Jordi Diaz-Manera, Jose Verdu Diaz, Volker Straub, Rossella Tupler, Joanna Pola\'nska→Ana Topf, Benedikt Schoeser, Filippo Santorelli, Joanna Pola\'nska, Jocelyn Laporte, Jordi Diaz-Manera, Jose Verdu Diaz, Marco Savarese, Marek Socha, Martyna \.Zur, Michael Obach, Rossella Tupler, Volker Straub, {\L}ukasz Pi\'oreckiarxiv - Property changedPaperV-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval
V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval: published at changed from 2026-09-11T04:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published11 Sept 2026→15 Sept 2026arxiv - Property changedPaperMARE: Multimodal Alignment and Reinforcement for Explainable Deepfake Detection via Vision-Language Models
MARE: Multimodal Alignment and Reinforcement for Explainable Deepfake Detection via Vision-Language Models: published at changed from 2026-09-14T04:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published14 Sept 2026→15 Sept 2026arxiv A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv- Property changedPaperPredicting build orientation for SLM dental parts: a comparison of rotation representations and direct vector regression
Predicting build orientation for SLM dental parts: a comparison of rotation representations and direct vector regression: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv- Property changedPaperRSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv - Property changedPaperAttention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning
Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning: published at changed from 2026-09-10T00:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published10 Sept 2026→15 Sept 2026arxiv - Property changedPaperClinical Reasoning Under a Partially Observed Objective in Cone Beam CT Report Generation
Clinical Reasoning Under a Partially Observed Objective in Cone Beam CT Report Generation: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv - Property changedPaperDiscovering and Preserving Category Correlation Knowledge via Adaptive Reciprocal Knowledge Distillation
Discovering and Preserving Category Correlation Knowledge via Adaptive Reciprocal Knowledge Distillation: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv - Property changedPaperSPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanation
SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanation: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv Land Art as a Big-Data Climate Sensor: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxivPhysMent: An Interactive Approach For LLM Reasoning In Physics Problems: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv- Property changedPaperAnatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRI
Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRI: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv - Property changedPaperLynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows
LynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows: published at changed from 2026-09-14T00:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published14 Sept 2026→15 Sept 2026arxiv - Property changedPaperDon't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language Models
Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language Models: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv Benchmarking Intra-Patient 3D Deformable Multimodal Image Registration: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv- Property changedPaperCircuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic Understanding
Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic Understanding: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv - Property changedPaperHuman-Grounded Calibration for Long-Text Image-Text Congruence in Vision-Language Models
Human-Grounded Calibration for Long-Text Image-Text Congruence in Vision-Language Models: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMs: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv- Property changedPaperVideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding
VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv - Property changedPaperA Unified Vision-Language Model for PSMA PET/CT Report Generation, Visual Question Answering, and Lesion Segmentation
A Unified Vision-Language Model for PSMA PET/CT Report Generation, Visual Question Answering, and Lesion Segmentation: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv- Property changedPaperBVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender
BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender: published at changed from 2026-09-14T00:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published14 Sept 2026→15 Sept 2026arxiv - Property changedPaperA Conservative OCR-Enabled Workflow for R214 Sodium Screening of South African Packaged Foods
A Conservative OCR-Enabled Workflow for R214 Sodium Screening of South African Packaged Foods: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv - Property changedPaperMarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding
MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv End-to-End Cell Detection via Instance-aware Graph Modeling: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv- Property changedPaperConcept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation
Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv - Property changedPaperPre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VLM Vision Encoders
Pre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VLM Vision Encoders: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv PACE: Progressive Angular-to-Norm Contrastive Embedding: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv- Property changedPaperSparseTalk - Sparsifying 3D Gaussian Language Fields for Efficient 3D Visual Question Answering
SparseTalk - Sparsifying 3D Gaussian Language Fields for Efficient 3D Visual Question Answering: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv - Property changedPaperAdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference
AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv - Property changedPaperChatGPT Images 2.5 in the Wild: A Launch-Period Dataset and Detector Evaluation
ChatGPT Images 2.5 in the Wild: A Launch-Period Dataset and Detector Evaluation: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv - Property changedPaperTwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals
TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models: published at changed from 2026-09-14T00:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published14 Sept 2026→15 Sept 2026arxivPhysBrain 1.5: From Vision-Language Models to Physical Foundation Models: authors changed from ["Changti Wu", "Chaoyi Ruan", "Chenliu Hao", "Cong Huang"… to ["Changti Wu", "Chaoyi Ruan", "Chenliu Hao", "Cong Huang"…
AuthorsChangti Wu, Chaoyi Ruan, Chenliu Hao, Cong Huang, DeepCybo Team, Haibao Liu, Haipeng Cao, Hang Yuan, Hanwen Zhang, Hao Wu, Haochen Liu, Haoyang Ge, Hong Li, Jiyan He, Kai Chen, Kai Hu, Kailin Deng, Peize Li, Peng Ren, Qiuzhi Liu, Qiyuan Su, Ruimeng Zhang, Ruoqi Yang, Shengcai Liu, Shijie Lian, Shuo Ren, Tao Luo, Tuopusen Huang, Xiaopeng Lin, Xiaotong Fu, Xueyin Xu, Xuguo He, Yakun Hou, Yao Zhang, Yibo Zhang, Yichao Du, Yining Wang, Youning Chen, Yu Bin, Yu Huang, Yukun Shi, Yun Lin, Yunlong Guo, Yuxiang Zhang, Yuxuan Tian, Zhaolong Shen, Zhaoyang Yang, Zhaoyang Zeng, Zheng Chang, Zhiqiang Liu→Changti Wu, Chaoyi Ruan, Chenliu Hao, Cong Huang, DeepCybo Team, Haibao Liu, Haipeng Cao, Hang Yuan, Hanwen Zhang, Hao Wu, Haochen Liu, Haoyang Ge, Hong Li, Jiyan He, Kai Chen, Kai Hu, Kailin Deng, Peize Li, Peng Ren, Qiuzhi Liu, Qiyuan Su, Ruimeng Zhang, Ruoqi Yang, Shengcai Liu, Shijie Lian, Shuo Ren, Tao Luo, Tuopusen Huang, Xiaopeng Lin, Xiaotong Fu, Xueyin Xu, Xuguo He, Yakun Hou, Yao Zhang, Yibo Zhang, Yichao Du, Yining Wang, Youning Chen, Yu Bin, Yu Huang, Yukun Shi, Yun Lin, Yunlong Guo, Yuxiang Zhang, Yuxuan Tian, Zhaolong Shen, Zhaoyang Yang, Zhaoyang Zeng, Zheng Chang, Zhiqiang Liu, Zhirui Zhang, Zishen Zhuang, Ziyi Zhang, Zubin ZhengarxivRAIN: Region-Aware Inversion Network for Semantic Watermark Extraction: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv- Property changedPaperFrom Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Image-Grounded Review Assistance
From Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Image-Grounded Review Assistance: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv- Property changedPaperOpen-UniMo: Towards Unified Motion-Language Understanding and Generation in the Open World
Open-UniMo: Towards Unified Motion-Language Understanding and Generation in the Open World: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv Sharing standardized image-derived data in computational pathology using DICOM: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv- Property changedPaperAlayaVista: Streaming World Modeling from Panoramic States to Perspective Video
AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video: published at changed from 2026-09-13T00:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published13 Sept 2026→15 Sept 2026arxiv
Feed keyed on occurred_at. Backfill = history imported when a source is first crawled (excluded — tick the box in the rail to include it). Times are UTC.