AI News Archive: June 24, 2026 — Part 19
Sourced from 500+ daily AI sources, scored by relevance.
- SurgAtlas: A Large-Scale Surgical Video-Language Dataset with 2,391 Hours of Open and Minimally Invasive Surgery
We introduce SurgAtlas, the largest surgical video-language dataset to date, comprising 15,291 videos (2,391 hours) spanning 18 surgical specialties and over 5,000 procedure types, sourced entirely from publicly available YouTube content. SurgAtlas is also the first surgical video-language dataset t...
- Enhancing Brain MRI Anomaly Detection and Reasoning with ROI Rethink and Synthetic Data
Medical vision-language models typically generate diagnoses through single-pass inference without indicating which image regions support their conclusions. This lack of spatial grounding limits clinical utility: outputs cannot be audited, and models may hallucinate findings on normal scans. We prese...
- USS: Unified Spatial-Semantic Prompts for Embodied Visual Tracking with Latent Dynamics Learning
Embodied Visual Tracking (EVT) requires an agent to continuously follow a specified target while actively moving through dynamic environments. However, prevailing EVT paradigms predominantly rely on language-based target indication. While language is expressive and convenient, cluttered scenes often...
- Naturalness Predicts but Does Not Cause Transferability in Image Encodings of Real-World Streams
A common practice converts a one-dimensional signal into an image so that a vision backbone pretrained on natural photographs can be reused for recognition, yet the encoded image is rarely examined. We ask how the visual naturalness of an encoded image relates to its transfer accuracy under a frozen...
- Shift Variant Image Degradation and Restoration Using Singular Value Decomposition
Shift-variant image degradation is frequently encountered in practical imaging systems where the point spread function (PSF) varies across the image field due to motion, optical aberrations, atmospheric turbulence, or sensor-related effects. Unlike shift-invariant, shift-variant degradation presents...
- $S^{2}$-FracMix: Label-Preserving Self-Saliency Mixup Augmentation
Data augmentation is known to improve generalization of deep visual models. Recent methods favor mixup strategies that generate interpolated samples to improve model performance. However, these techniques not only incur significant computational overhead, they also lead to semantic disruption of aug...
- Re-mixing Embeddings for Patient Augmentation in Data Scarce Multiple Instance Learning
Data scarcity is a major bottleneck in medical Multiple Instance Learning (MIL), especially for rare diseases or expensive modalities. We introduce a statistically grounded patient augmentation approach that generates realistic patients directly in embedding space. Using Gaussian Mixture Models as a...
- Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs
While test-time adaptation (TTA) empowers vision-language models to adapt without costly retraining, it remains highly vulnerable to out-of-distribution (OOD) outliers prevalent in real-world applications. This discrepancy motivates Noisy TTA (NTTA), an online task to filter noisy OOD samples on the...
- quyash - AI product visuals in 60 sec.
AI product visuals for Amazon, Etsy & Shopify in 60 seconds
- Point Cloud Diffusion with Global and Local Reconstruction for Instance-Level 3D Anomaly Detection
3D anomaly detection in point clouds is critical for high-precision industrial manufacturing. Reconstruction-based methods have laid a strong foundation by detecting 3D anomalies through comparisons between defective inputs and their reconstructed normal counterparts. However, existing methods still...
- Falcon: Functional Assembly and Language for Compositional Reasoning in X-ray
Conventional vision-language models are largely object-centric, focusing on detecting and describing individual entities. In safety-critical X-ray baggage screening, however, threat often emerges not from a single object but from the functional compatibility of spatially dispersed components, such a...
- Steering Vision-Language Models with Joint Sparse Autoencoders
Sparse Autoencoders (SAEs) have shown promise for analyzing language models, but applying them to vision-language models (VLMs) often yields representations that are difficult to use as controllable cross-modal steering directions. We introduce the Joint Sparse Autoencoder (JSAE), which uses an expl...
- VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks
Recent advancements in Image-to-Video (I2V) generation have transformed input images from simple appearance references into interactive control interfaces where visual cues such as arrows, sketches, and emojis orchestrate complex video dynamics with unprecedented controllability. However, these seem...
- Statistically Valid Hyperparameter Selection: From Tuning to Guarantees
Hyperparameter selection is a critical step in the deployment of modern artificial intelligence systems, given the need to tune degrees of freedom such as inference-time parameters, implementation-level settings, and thresholds driving decision rules. Despite its practical importance, hyperparameter...
- Stabilizing black-box algorithms through task-oriented randomization
As black-box models become foundational to modern research, ensuring their stability is paramount for the realization of trustworthy artificial intelligence. The inherent diversity of inputs - ranging from structured Gaussian distributions to complex data with unknown structures - poses a significan...
- When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?
Synthetic data augmentation is widely used to mitigate class imbalance, but its theoretical effects on score-based classification remain poorly understood. This paper develops a framework for characterizing when synthetic minority augmentation can improve threshold-integrated and threshold-optimized...
- Gaussian Mean Field Variational Inference can Overestimate Predictive Variance
Mean Field Variational Inference (MFVI) is widely understood to underestimate posterior variance. By analysing conjugate Bayesian Linear Regression (BLR), we show that this characterization is incomplete: while MFVI underestimates the variance in parameter space, it can overestimate the predictive v...
- A functional central limit theorem for kernel gradient flow and infinitesimal gradient boosting
Building on the large-sample analysis of infinitesimal gradient boosting (Dombry and Duchamps, 2024b), we study the fluctuations of the process around its deterministic limit and establish a functional central limit theorem: the rescaled deviations converge in distribution to a Gaussian process. The...
- Learning Interpretable Text Signals for Structured Responses
Textual data are often collected alongside structured response variables, but prediction and interpretation are commonly treated as separate tasks. This paper studies rating prediction as an initial case of interpretable text-response modelling, where the aim is to learn textual representations that...
- Tencent EdgeOne Makers
Ship AI agents like web apps, in minutes.
- Propane
Automatic customer context for product teams and agents
- Crewdle AI
Use every business AI tool without every subscription
- Stripe.Directory
New way for you & agents to search for businesses on Stripe
- Customer Relationship Agents by Clarify
The M in CRM shouldn't be you
- Mindstone Rebel
AI workspace for agents that know your work and ask first
- Buy by Agentcard
Order DoorDash from Claude
- StaleMate PR
Your menu bar turns red when PRs pile up
- Ruby
Ask better questions, live on every call
- Blinx
Blinx: UX feedback in minutes from a synthetic user
- AiTwin.me
Browser Rendered Realtime AI Avatars. Make your twin today.
- SoundGTM
Run your B2B partner program from Claude, ChatGPT, or Gemini
- Viral Worx Studio
Your AI operating system for video, image, social content.
- Cloudeval AI
Your cloud evaluated, reported, and agent-ready in CLI & Web
- GoodBarber - AI Extension Builder
Describe a feature, AI creates it in your app.
- ReplyGen
Personalized AI reply co-pilot for LinkedIn, X & Threads
- ScanEdge AI
Institutional Flow, Decoded for Retail Traders
- Primrose & Eve: Menopause
Privacy-first self-advocacy tool for perimenopause.
- Hour.is
A beautiful time app for every timezone
- Roger • The Google Ads AI Agent
Use AI to optimize your Google Ads
- Profile Bud - All Your Handles
Share your links with a swipe
- ClimaPal
Your personal stylist for weather, outfits & travel packing
- onsubmit.dev
No backend. Just onsubmit.
- Layah
AI lesson plans & PPTs — built by a teacher, for teachers
- Spagette
Stop searching for apps. Describe what you need.
- ZeroLink
Secure Messaging, Files & Secrets for Teams
- Bird Palette
Explore color palettes extracted from 10,000+ real birds.
- Infile
Automated document collection and secure client portals.
- Agents At Work
Monitor and control AI agents from your phone
- DocAudit: Knowledge Base Audits
Find content gaps, duplicates and stale docs in Notion+
- Heario.ai
Invisible AI Co-pilot for Interviews & Meetings