arXiv||1 min read
GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems
Focuses on GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems.
Topic archive
Vision AI news
Perception, multimodal systems, 3D, and visual generation. This page collects the latest briefings that match the topic so readers can follow one area without scanning the full feed.
Indexed briefings
709
Latest source-linked updates, ordered newest first.
Latest
Recent briefings
arXiv||1 min read
SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles
Focuses on SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles.
arXiv||1 min read
Group-invariant Coresets for Data-efficient Active Learning
Focuses on Group-invariant Coresets for Data-efficient Active Learning.
arXiv||1 min read
GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision
Focuses on GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision.
arXiv||1 min read
PointSplat: Compact Gaussian Splatting via Human-Centric Prediction
Focuses on PointSplat: Compact Gaussian Splatting via Human-Centric Prediction.
arXiv||1 min read
SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE
Focuses on SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE.
arXiv||1 min read
Slope-Guided Mamba and Angular-Refined Transformer for Light Field Super-Resolution
Focuses on Slope-Guided Mamba and Angular-Refined Transformer for Light Field Super-Resolution.
arXiv||1 min read
LUNA: Learning Universal 3D Human Animation Beyond Skinning
Focuses on LUNA: Learning Universal 3D Human Animation Beyond Skinning.
arXiv||1 min read
Post-Training Pruning for Diffusion Transformers
Focuses on Post-Training Pruning for Diffusion Transformers.
arXiv||1 min read
Condensing Large-Scale Datasets Directly with Minimal Information Loss
Focuses on Condensing Large-Scale Datasets Directly with Minimal Information Loss.
arXiv||1 min read
FlexViT: A Flexible FPGA-based Accelerator for Edge Vision Transformers
Focuses on FlexViT: A Flexible FPGA-based Accelerator for Edge Vision Transformers.
arXiv||1 min read
MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization
Focuses on MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization.
arXiv||1 min read
Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference
Focuses on Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference.
arXiv||1 min read
Geometry-Aware Cross-Height Channel Knowledge Map Prediction for UAV-Assisted Communications With Uncertainty-Guided 3D Sensing
Focuses on Geometry-Aware Cross-Height Channel Knowledge Map Prediction for UAV-Assisted Communications With Uncertainty-Guided 3D Sensing.
arXiv||1 min read
Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning
Focuses on Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning.
arXiv||1 min read
Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlook
Focuses on Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlook.
arXiv||1 min read
Towards High-Resolution Visual Perception via Hierarchical Entity Exploration
Focuses on Towards High-Resolution Visual Perception via Hierarchical Entity Exploration.
arXiv||1 min read
SpiralFovea: Input-Adaptive Foveated Tokenization as a Third Lever of Resource-Adaptive Inference
Focuses on SpiralFovea: Input-Adaptive Foveated Tokenization as a Third Lever of Resource-Adaptive Inference.
arXiv||1 min read
An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping
Focuses on An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping.
arXiv||1 min read
Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers
Focuses on Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers.
arXiv||1 min read
Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior
Focuses on Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior.
arXiv||1 min read
Decoupled Guidance: Disentangling Subject and Context Pathways in Text-to-Image Personalization
Focuses on Decoupled Guidance: Disentangling Subject and Context Pathways in Text-to-Image Personalization.
arXiv||1 min read
MuSViT: A Foundation Vision Model for Sheet Music Representation
Focuses on MuSViT: A Foundation Vision Model for Sheet Music Representation.
arXiv||1 min read
GKDT: General Keypoint Detection Transformer
Focuses on GKDT: General Keypoint Detection Transformer.
arXiv||1 min read
ConRTF: Edge-Constrained Boundary Distribution Refinement for Realtime TransFormer Table Structure Recognition
Focuses on ConRTF: Edge-Constrained Boundary Distribution Refinement for Realtime TransFormer Table Structure Recognition.
arXiv||1 min read
SpikeLogBERT: Energy-Efficient Log Parsing Using Spiking Transformer Networks
Focuses on SpikeLogBERT: Energy-Efficient Log Parsing Using Spiking Transformer Networks.
arXiv||1 min read
Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach
Focuses on Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach.
arXiv||1 min read
LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter
Focuses on LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter.
arXiv||1 min read
Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation
Focuses on Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation.
arXiv||1 min read
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model
Focuses on ABot-M0.5: Unified Mobility-and-Manipulation World Action Model.
arXiv||1 min read
JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering
Focuses on JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering.
arXiv||1 min read
UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization
Focuses on UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization.
arXiv||1 min read
Active Spatial Guidance: Eliminating Injected Positional Mechanisms in Vision Transformers
Focuses on Active Spatial Guidance: Eliminating Injected Positional Mechanisms in Vision Transformers.
arXiv||1 min read
Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization
Focuses on Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization.
arXiv||1 min read
Semantic Occupancy Prediction with Dual Range-Voxel Representation
Focuses on Semantic Occupancy Prediction with Dual Range-Voxel Representation.
arXiv||1 min read
GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine
Focuses on GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine.