AI News Archive: June 15, 2026 — Part 14
Sourced from 500+ daily AI sources, scored by relevance.
- Instance-Aware Knowledge Distillation for Semi-Supervised Learning of an On-Board Multi-Task Dense Prediction Model for Collision Avoidance System
Collision avoidance systems have evolved toward camera-based deep learning approaches for driving scene understanding. However, deployment in edge environments such as country clubs is constrained by limited computational resources and unreliable communication infrastructure. Moreover, constructing ...
- GraphBEV++: Multi-Modal Feature Alignment for Autonomous Driving
Feature misalignment in BEV perception is a critical yet often overlooked challenge in autonomous driving, especially under calibration uncertainties between LiDAR and camera sensors. To address this issue, we propose a robust multi-modal fusion framework, GraphBEV++, which systematically mitigates ...
- Robust Spoofed Speech Detection via Temporal Pyramid Modeling
Spoofed speech detection is increasingly challenged by realistic synthesis, voice conversion, and replay attacks, with cross-dataset generalization remaining a major limitation. This work we propose a Temporal Pyramid Adapter that utilize parallel temporal convolutions with varying receptive fields ...
- WaveDINO: Learning-Based Atmospheric Correction of Unwrapped InSAR Interferograms Validated by GNSS: Results at Laguna del Maule and Campi Flegrei Volcanoes
Interferometric Synthetic Aperture Radar (InSAR) enables effective monitoring of volcanic deformation; however, the observed signals are often corrupted by atmospheric phase delays, seasonal surface changes, and decorrelation effects. Existing atmospheric correction methods, such as numerical weathe...
- Text-Vision Co-Instructed Image Editing
Existing image editing methods can be generally categorized into textual instruction-based and visual prompt-based ones. Textual instructions are semantically expressive, but are limited by the coarse granularity of spatial control of the editing results. In contrast, visual prompts such as drag and...
- 3D Classification of Paramagnetic Rim Lesions in Multiple Sclerosis via Asymmetric QSM-FLAIR Modeling
Paramagnetic rim lesions (Rim$^+$) identified on susceptibility-sensitive MRI have recently emerged as a specific biomarker of chronic active inflammation in Multiple Sclerosis (MS) and are associated with long-term disability progression. However, susceptibility imaging and expert interpretation re...
- Structure-aware Knowledge-guided Heterogeneous Mamba for Zygomaticomaxillary Suture Assessment
The Zygomaticomaxillary Suture is a key circummaxillary structure that connects the zygomatic bone and the maxilla, which serves as a primary site of resistance during maxillary advancement, and its maturation status directly influences the timing and efficacy of orthopedic interventions. However, a...
- PATCH: Action-Chunk-Conditioned Latent Patch Innovation Monitoring for Robot Manipulation
Learning-based manipulation policies have made substantial progress in real-world robot manipulation, particularly for short-horizon action generation. However, deployment in open workspaces remains fragile under unexpected local scene dynamics, such as moving objects, transient occlusions, or distu...
- Sinkhorn-CPD: Robust point cloud registration via unbalanced entropic optimal transport
Coherent Point Drift (CPD) is widely used for rigid point cloud registration because of its soft correspondences and closed-form parameter updates. However, CPD's target-side marginal constraint forces every observation, including outliers, to receive exactly unit probability mass. This assumption d...
- Vision-Language Models as Zero-Annotation Oracles in Histopathology
Foreground segmentation is the critical first step of every computational pathology pipeline, yet existing methods rely on hand-tuned heuristics or supervised models that overfit to narrow stain and scanner distributions, failing silently on specialised stains such as Jones silver or Elastica van Gi...
- DCP-Prune: Ultra-Low Token Pruning with Distribution Consistency Preservation
Recent vision token pruning methods effectively preserve model performance under moderate token budgets but become unstable under ultra-low token budget. Our analysis shows that as the pruning budget decreases, accuracy degradation is often accompanied by larger feature distribution shifts. Critical...
- Rotational Symmetry based Object Pose Estimation from Point Clouds in the Absence of Known 3D Models
Object pose estimation is crucial to many industrial applications, with one example being automated spray painting using a robot. However, confidentiality concerns often limit access to high-quality 3D models, posing a significant challenge for point-cloud-based pose estimation. In such scenarios, r...
- PROSE: Training-Free Egocentric Scene Registration with Vision-Language Models
Registering two captures of the same indoor space taken at different times underpins persistent spatial memory for robots and AR systems, yet the realistic version of this task is egocentric and its most scalable form is RGB-only. Head-mounted cameras yield blurry, fast-moving, partially overlapping...
- Local-GS: Accelerating 3D Gaussian Splatting via Tile-Local Warp Coherence
3D Gaussian Splatting (3DGS) has significantly advanced real-time novel view synthesis by representing scenes as dense collections of anisotropic 3D Gaussian primitives. However, the irregular spatial distribution of Gaussians often leads to poor GPU utilization, as warp divergence and redundant com...
- Kairos: A Native World Model Stack for Physical AI
World models are transitioning from passive visual generators to foundational, operational infrastructure for Physical AI: they must natively acquire world knowledge from heterogeneous experience, maintain persistent states over long horizons, and execute efficiently within real deployment constrain...
- stackd.cc
The answer to "what's your AI stack?"
- BadWorld: Adversarial Attacks on World Models
Visual world models (VWMs) synthesize interactive, action-conditioned rollouts from a single context image. However, it remains an open question how robust these models are to adversarial perturbations. Standard adversarial attacks fail to assess this vulnerability because attackers lack ground-trut...
- Active Reference Acquisition in Few-Shot Font Generation
Few-shot font generation aims to synthesize the remaining glyphs of a font given one or a few reference glyphs while preserving stylistic consistency, thereby supporting font designers in efficiently completing a typeface. Existing methods primarily focus on improving generation quality given a fixe...
- Uncertainty Quality of VGGT: An Analysis on the DTU Benchmark Dataset
Visual Geometry Grounded Transformer (VGGT) has already attracted a great deal of attention in a short period of time, not least due to the Best Paper Award at CVPR-2025. Similar to DUSt3R and MASt3R, VGGT aims to bring about a paradigm shift by replacing established methods like bundle adjustment a...
- AURA: Active-Response Attribution under Treatment Ambiguity in Bacterial Cytological Profiling
When a bacterial sample is exposed to several antibiotics, not every applied drug necessarily acts: if the organism is resistant to one of them, that drug leaves no morphological trace. The clinically meaningful quantity is therefore not which antibiotics were applied, but which ones were active. We...
- MVOFormer: Flow-Semantic Transformer for Robust Monocular Visual Odometry
Monocular visual odometry (MVO) is foundational to autonomous navigation and robotic localization. However, existing learning-based MVO approaches often struggle with either a lack of interpretable, complementary features or overly complex multi-stage architectures. These limitations inherently rest...
- Decoupled Object-Centric Video Understanding for Generating Robotic Manipulation Commands
Translating video demonstrations into executable robot commands remains challenging because existing methods often fail to identify which objects are functionally involved in the demonstrated action. As a result, they may generate commands that are linguistically plausible but operationally ambiguou...
- PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory
Consistent video generation under editing operations requires persistence: when edits modify scene appearance or layout, subsequent generations should remain coherent across time and viewpoints. However, existing memory designs struggle to maintain long-term consistency after such modifications, as ...
- V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videos
Achieving autonomous robotic dexterous manipulation requires precise, human-like action sequences at scale. As a scalable supplement to costly teleoperation data, extracting trajectories with both visual fidelity and physical plausibility from monocular videos represents a promising frontier in embo...
- RGFVR: Reference-Guided Face Video Restoration with Flow Matching
Face video restoration from degraded observations is challenging, as it requires simultaneously recovering visual fidelity, temporal consistency, and subject identity. Existing approaches are often either reference-free, which can lead to identity loss when person-specific facial details are lost, o...
- SP$^3$: Spherical Priors for Plug-and-Play Restoration
In this paper, we introduce SP$^3$, a novel Plug-and-Play algorithm that accelerates maximum a posteriori image restoration by replacing denoisers with Spherical Encoders (SE) as generative priors. SP$^3$ approximates the intractable proximal prior step by utilizing the SE tightly structured latent ...
- Towards UAV Image Dehazing: A UAV Atmospheric Scattering Model, Benchmark, and Geometry-Aware Deep Unfolding Network
In UAV applications, haze significantly obscures distant details and weaken structural information, hindering the recovery of details. Current UAV scenarios still face two key challenges: (i) paired hazy/clean images from the real world are unobtainable, while the classical atmospheric scattering mo...
- Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data
The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets. However, generating high-utility synthetic data often carries the risk of memorizing and regurgitating private information...
- A nonparametric two-sample test using a parametric integral probability metric
Detecting distributional differences between two independent samples is a fundamental problem in statistics and machine learning. Nonparametric two-sample testing provides a principled framework for determining whether two samples are drawn from the same underlying distribution, without assuming any...
- Scalable Circuit Learning for Interpreting Large Language Models
A prominent research direction in mechanistic interpretability is learning sparse circuits over LLM components to reveal how they jointly produce model behavior. However, raw neurons are polysemantic, making learned circuits hard to interpret. Sparse autoencoder (SAE) features alleviate this, but th...
- A Unified Causal-Origin Taxonomy of Distributional Shifts in Reinforcement Learning
Reinforcement learning (RL) systems often degrade when operating conditions differ from those previously encountered, reflecting distributional shifts in the underlying data-generating process. Such shifts may occur between training and evaluation, as in In-Distribution (ID) and Out-of-Distribution ...
- Functional Gradient Descent with Adaptive Representations
Functional optimization problems are typically solved by optimizing the parameters of a fixed representation, such as a neural network, resulting in highly nonconvex losses that complicate both training and theoretical analysis. An interesting alternative is functional gradient descent (FGD), that i...
- Demystifying Variance in Circuit Discovery of LLMs
Circuit discovery is a key technique in mechanistic interpretability to pinpoint the model components that are crucial for performing a given task. Although the current state-of-the-art method (EAP-IG) performs well on the metric of (un)faithfulness, it suffers from substantial variability. This inc...
- Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization
Matrix based optimizers such as Muon can substantially speed up language model pretraining, but their gains over AdamW are observed to shrink as model size and data scale grow when using standard constant decoupled weight decay. We propose Hyperball, a simple optimizer wrapper that addresses this is...
- Beyond Weights and Gradients: A Taxonomy of Federated Learning Messages
Federated Learning is rapidly evolving beyond the exchange of traditional model weights and gradients, yet existing definitions fail to capture the full scope of modern payloads like synthetic data and federated analytics. This paper addresses the gap by proposing a formal mathematical definition of...
- Upper Bounds on the Generalization Error of Deep Learning Models via Local Robustness and Stability
Generalization is a critical property of data-driven models, particularly deep learning models deployed in safety-critical applications. Robustness-based generalization bounds have gained attention as a principled way to link robustness properties to generalization performance, often in a data-depen...
- Deep Q-Learning on Hölder Spaces
We study the operator-theoretic core of Q-learning in continuous-time stochastic control with continuous states and actions. In value-based reinforcement learning, each Q-learning or DQN update is built from a Bellman optimality target; our analysis isolates this target in a diffusion setting and st...
- A Perception vs. Distortion Perspective on Score-Based Generative Channel Estimation
Driven by their remarkable success in computer vision and inverse problem solving, score-based models are increasingly applied to wireless communications, where they show promise across a range of physical-layer tasks. However, despite this growing interest, the current literature often lacks a rigo...
- GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization
As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities. This shift demands new algorithms capable of optimizing diverse and potentially competing objectives simultaneously. To address this, existing methods ...
- Maximum Entropy Inverse Reinforcement Learning for Mean-Field Games with Average Reward
We study inverse reinforcement learning for discrete-time, infinite-horizon mean-field games (MFGs) under an average-reward criterion. Expert demonstrations are assumed to arise from a stationary mean-field equilibrium under an unknown reward, and the goal is to recover a policy explaining the obser...
- Attention is Just Another Name for Coupling?: A Fast-Slow ODE Perspective on Hierarchical Pretraining
Causal self-attention is a coupling mechanism: each token's hidden state is updated by a learned mixture of preceding tokens at the same timescale. This paper asks whether a second, temporally slower coupling-a slow sub-system operating on a temporally-downsampled view of the sequence and fed back i...
- Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process
While there is an extensive body of work characterizing the sample complexity of discounted cumulative-reward MDPs, finite sample analyses for average-reward MDPs have been limited, and most existing works rely on restrictive assumptions such as ergodicity or access to a generative model. In this wo...
- Beyond Defensive Reporting: Machine Learning for Active Anti-Money Laundering Control in Insurance
Money laundering through insurance claims poses a threat to insurers both through fraudulent payouts and reputational and regulatory risk. Despite this, little research has examined how such laundering can be prevented. This paper examines whether machine learning can help insurers flag suspicious c...
- Distribution Alignment for One-Shot Federated Learning via Optimal Transport
One-Shot Federated Learning (OSFL) addresses extreme communication regimes in which clients interact with the server only once, amplifying the impact of heterogeneous client data distributions. In particular, the interaction of domain shift and label shift across clients induces misaligned feature r...
- SPICE: Synergy and Partial Information Based Curriculum Evolution
Multimodal learning exploits complementary information across heterogeneous modalities. The informativeness of each modality can vary widely across samples and training stages. Existing multimodal curriculum learning strategies often assume that the relative complexity of samples remains unchanged t...
- TCHG: Tri-Trust Conditioned Heterogeneous Graph Learning for Reliable Dynamic Trust Prediction
Trust prediction infers latent user-user trust relations and provides important support for social recommendation, fake-review and manipulation detection, and risk identification. Graph neural networks have become a prominent approach to trust prediction because of their ability to learn network str...
- PhysGuard: Fisher-Guided Gradient Projection for Sim-to-Real Neural PDE Surrogates
Neural operator models trained on simulation data often lose accuracy when applied to experimental measurements due to the sim-to-real gap. Standard fine-tuning with limited real data can reduce this gap, but it may also damage the core physics-relevant representations learned during pretraining. Al...
- ColibotAI
Translate, summarize & explain any text on-device
- TreeGRNG: Binary Tree Gaussian Random Number Generator for Efficient Probabilistic AI Hardware
Bayesian Neural Networks (BNNs) offer opportunities for greatly enhancing the trustworthiness of conventional neural networks by monitoring the uncertainties in decision-making. A significant drawback for BNN inference at the extreme edge, however, is the imperative need to incorporate Gaussian Rand...
- Infant Spontaneous Movement Noise Improves Exploration in Deep RL
Exploration in deep reinforcement learning (RL) is commonly implemented as temporally uncorrelated white noise. However, recent works show that temporally correlated colored noise can improve exploration efficiency by producing smooth trajectories with better coverage of the state space. We inquire ...