AI News Archive: April 28, 2026 — Part 26

Sourced from 500+ daily AI sources, scored by relevance.

• R$^3$-SQL: Ranking Reward and Resampling for Text-to-SQL

  Modern Text-to-SQL systems generate multiple candidate SQL queries and rank them to judge a final prediction. However, existing methods face two limitations. First, they often score functionally equivalent SQL queries inconsistently despite identical execution results. Second, ranking cannot recover...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25325v1
• Magnification-Invariant Image Classification via Domain Generalization and Stable Sparse Embedding Signatures

  Magnification shift is a major obstacle to robust histopathology classification, because models trained on one imaging scale often generalize poorly to another. Here, we evaluated this problem on the BreaKHis dataset using a strict patient-disjoint leave-one-magnification-out protocol, comparing sup...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25817v1
• Improving Diversity in Black-box Few-shot Knowledge Distillation

  Knowledge distillation (KD) is a well-known technique to effectively compress a large network (teacher) to a smaller network (student) with little sacrifice in performance. However, most KD methods require a large training set and internal access to the teacher, which are rarely available due to var...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25795v1
• Diverse Image Priors for Black-box Data-free Knowledge Distillation

  Knowledge distillation (KD) represents a vital mechanism to transfer expertise from complex teacher networks to efficient student models. However, in decentralized or secure AI ecosystems, privacy regulations and proprietary interests often restrict access to the teacher's interface and original dat...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25794v1
• Quantum-Inspired Robust and Scalable SAR Object Classification

  SAR image classification naturally has to deal with huge noise and a high dynamic range particularly requiring robust classification models. Additionally, the deployment of these models on edge devices, such as drones and military aircraft, requires a careful balance between model size and classific...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25755v1
• QB-LIF: Learnable-Scale Quantized Burst Neurons for Efficient SNNs

  Binary spike coding enables sparse and event-driven computation in spiking neural networks (SNNs), yet its 1-bit-per-timestep representation fundamentally limits information throughput. This bottleneck becomes increasingly restrictive in deep architectures under short simulation horizons. We propose...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25688v1
• Asa by Spryt

  The medical receptionist in your pocket

  🧰 ToolsApr 28, 2026https://www.producthunt.com/products/spryt?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+the500feed+%28ID%3A+283491%29
• Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models

  Unified multimodal models (UMMs) integrate visual understanding and generation within a single framework. For text-to-image (T2I) tasks, this unified capability allows UMMs to refine outputs after their initial generation, potentially extending the performance upper bound. Current UMM-based refineme...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25636v1
• Control Your Queries: Heterogeneous Query Interaction for Camera-Radar Fusion

  In autonomous driving, camera-radar fusion offers complementary sensing and low deployment cost. Existing methods perform fusion through input mixing, feature map mixing, or query-based feature sampling. We propose a new fusion paradigm, termed heterogeneous query interaction, and present ConFusion,...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25574v1
• TopoMamba: Topology-Aware Scanning and Fusion for Segmenting Heterogeneous Medical Visual Media

  Visual state-space models (SSMs) have shown strong potential for medical image segmentation, yet their effectiveness is often limited by two practical issues: axis-biased scan ordering weakens the modeling of oblique and curved structures, and naive multi-branch fusion tends to amplify redundant res...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25545v1
• The Surprising Effectiveness of Canonical Knowledge Distillation for Semantic Segmentation

  Recent knowledge distillation (KD) methods for semantic segmentation introduce increasingly complex hand-crafted objectives, yet are typically evaluated under fixed iteration schedules. These objectives substantially increase per-iteration cost, meaning equal iteration counts do not correspond to eq...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25530v1
• DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing

  Recent image editing models have achieved strong visual fidelity but often struggle with tasks requiring complex reasoning. To investigate and enhance the reasoning-grounded planning for image editing, we propose DDA-Thinker, a Thinker-centric framework designed for the independent optimization of a...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25477v1
• GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution

  Despite recent advances, single-image super-resolution (SR) remains challenging, especially in real-world scenarios with complex degradations. Diffusion-based SR methods, particularly those built on Stable Diffusion, leverage strong generative priors but commonly rely on text conditioning derived fr...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25457v1
• SARU: A Shadow-Aware and Removal Unified Framework for Remote Sensing Images with New Benchmarks

  Shadows are a prevalent problem in remote sensing imagery (RSI), degrading visual quality and severely limiting the performance of downstream tasks like object detection and semantic segmentation. Most prior works treat shadow detection and removal as separate, cascaded tasks, which can lead to cumb...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25432v1
• A Systematic Post-Train Framework for Video Generation

  While large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content, a significant gap remains between their pretraining performance and real-world deployment requirements due to critical issues such as prompt sensitivity, te...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25427v1
• Beyond Fidelity: Semantic Similarity Assessment in Low-Level Image Processing

  Low-level image processing has long been evaluated mainly from the perspective of visual fidelity. However, with the rise of deep learning and generative models, processed images may preserve perceptual quality while altering semantic content, making conventional Image Quality Assessment (IQA) insuf...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25408v1
• Leveraging Previous-Traversal Point Cloud Map Priors for Camera-Based 3D Object Detection and Tracking

  Camera-based 3D object detection and tracking are central to autonomous driving, yet precise 3D object localization remains fundamentally constrained by depth ambiguity when no expensive, depth-rich online LiDAR is available at inference. In many deployments, however, vehicles repeatedly traverse th...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25405v1
• GeoSearch: Augmenting Worldwide Geolocalization with Web-Scale Reverse Image Search and Image Matching

  Worldwide image geolocalization, which aims to predict the GPS coordinates of any image on Earth, remains challenging due to global visual diversity. Recent generative approaches based on Retrieval-Augmented Generation (RAG) and Large Multimodal Models (LMMs) leverage candidates retrieved from fixed...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25390v1
• Benchmarking and Improving GUI Agents in High-Dynamic Environments

  Recent advancements in Graphical User Interface (GUI) agents have predominantly focused on training paradigms like supervised fine-tuning (SFT) and reinforcement learning (RL). However, the challenge of high-dynamic GUI environments remains largely underexplored. Existing agents typically rely on a ...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25380v1
• GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment

  The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never been more difficult to discern. We introduce the GPT-Image-2 Twitter Dataset, the first published dataset of GPT-image-2 generated images, ...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25370v1
• Towards Robust Deep Learning-based Rumex Obtusifolius Detection from Drone Images

  Domain adaptation (DA) addresses the challenge of transferring a machine learning model trained on a source domain to a target domain with a different data distribution. In this work, we study DA for the task of Rumex obtusifolius (Rumex) image classification. We train models on a published, ground ...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25316v1
• SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation

  Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fundamental cause of this behavior lies in the geometry of learned representations:...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25315v1
• Nura Scan by Evolve Neuro

  30+ cognitive markers in one 5-minute brain scan

  🧰 ToolsApr 28, 2026https://www.producthunt.com/products/evolve-neuro?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+the500feed+%28ID%3A+283491%29
• Golden RPG: Confidence-Adaptive Region-Aware Noise for Compositional Text-to-Image Generation

  Compositional text-to-image (T2I) generation requires a model to honour multiple sub-prompts that describe distinct image regions. Recent work shows that the \emph{starting noise} of a diffusion model carries significant semantic information: ``golden'' noise predicted from text can substantially ra...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25314v1
• The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents

  Diffusion models have achieved success in high-fidelity data synthesis, yet their capacity for more complex, structured reasoning like text following tasks remains constrained. While advances in language models have leveraged strategies such as latent reasoning and recursion to enhance text understa...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25299v1
• Robust Deepfake Detection: Mitigating Spatial Attention Drift via Calibrated Complementary Ensembles

  Current deepfake detection models achieve state-of-the-art performance on pristine academic datasets but suffer severe spatial attention drift under real-world compound degradations, such as blurring and severe lossy compression. To address this vulnerability, we propose a foundation-driven forensic...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25889v1
• QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding

  Quantum computing calibration depends on interpreting experimental data, and calibration plots provide the most universal human-readable representation for this task, yet no systematic evaluation exists of how well vision-language models (VLMs) interpret them. We introduce QCalEval, the first VLM be...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25884v1
• Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation

  In this work, we propose Mutual Forcing, a framework for fast autoregressive audio-video generation with long-horizon audio-video synchronization. Our approach addresses two key challenges: joint audio-video modeling and fast autoregressive generation. To ease joint audio-video optimization, we adop...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25819v1
• Instruction-Evidence Contrastive Dual-Stream Decoding for Grounded Vision-Language Reasoning

  Vision-Language Models (VLMs) exhibit strong performance in instruction following and open-ended vision-language reasoning, yet they frequently generate fluent outputs that are weakly grounded in visual evidence. Prior works have shown that instruction prompting further worsens this issue by amplify...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25809v1
• Robustness Evaluation of a Foundation Segmentation Model Under Simulated Domain Shifts in Abdominal CT: Implications for Health Digital Twin Deployment

  Foundation segmentation models such as the Segment Anything Model (SAM) have demonstrated strong generalization across natural images; however, their robustness under clinically realistic medical imaging domain shifts remains insufficiently quantified. We present a systematic slice-level robustness ...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25685v1
• SAMe: A Semantic Anatomy Mapping Engine for Robotic Ultrasound

  Robotic ultrasound has advanced local image-driven control, contact regulation, and view optimization, yet current systems lack the anatomical understanding needed to determine what to scan, where to begin, and how to adapt to individual patient anatomy. These gaps make systems still reliant on expe...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25646v1
• Vision SmolMamba: Spike-Guided Token Pruning for Energy-Efficient Spiking State-Space Vision Models

  Spiking Transformers have shown strong potential for long-range visual modeling through spike-driven self-attention. However, their quadratic token interactions remain fundamentally misaligned with the sparse and event-driven nature of spiking neural computation. To address this limitation, we propo...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25570v1
• Generalizable Human Gaussian Splatting via Multi-view Semantic Consistency

  Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined structural representations to accurately position 3D Gaussians. Although these approac...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25466v1
• COMPASS: COmpact Multi-channel Prior-map And Scene Signature for Floor-Plan-Based Visual Localization

  Architectural floor plans are widely available priors which contain not only geometry but also the semantic information of the environment, yet existing localization methods largely ignore this semantic information. To address this, we present COMPASS, an algorithm that exploits both geometric and s...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25388v1
• CoRE: Concept-Reasoning Expansion for Continual Brain Lesion Segmentation

  Accurate brain lesion segmentation in MRI is vital for effective clinical diagnosis and treatment planning. Due to high annotation costs and strict data privacy regulations, universal models require employing Continual Learning (CL) to adapt to evolving clinical tasks without losing previously acqui...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25376v1
• PhyloSDF: Phylogenetically-Conditioned Neural Generation of 3D Skull Morphology via Residual Flow Matching

  Generating novel, biologically plausible three-dimensional morphological structures is a fundamental challenge in computational evolutionary biology, hampered by extreme data scarcity and the requirement that generated shapes respect phylogenetic relationships among species. In this work, we present...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25371v1
• Self-DACE++: Robust Low-Light Enhancement via Efficient Adaptive Curve Estimation

  In this paper, we present Self-DACE++, an improved unsupervised and lightweight framework for Low-Light Image Enhancement (LLIE), building upon our previous Self-Reference Deep Adaptive Curve Estimation (Self-DACE). To better address the trade-off between computational efficiency and restoration qua...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25367v1
• Benchmarking Layout-Guided Diffusion Models through Unified Semantic-Spatial Evaluation in Closed and Open Settings

  Evaluating layout-guided text-to-image generative models requires assessing both semantic alignment with textual prompts and spatial fidelity to prescribed layouts. Assessing layout alignment requires collecting fine-grained annotations, which is costly and labor-intensive. Consequently, current ben...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25358v1
• Edge-Cloud Collaborative Reconstruction via Structure-Aware Latent Diffusion for Downstream Remote Sensing Perception

  The exponential surge in high-resolution remote sensing data faces a severe bottleneck in satellite-to-ground transmission. Limited downlink bandwidth forces the use of extreme high-ratio compression, which irreversibly destroys high-frequency structural details essential for downstream machine perc...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25319v1
• Rapid tracking through strongly scattering media with physics-informed neuromorphic speckle analysis

  This work addresses the critical problem of tracking fast-moving objects through strongly scattering media in a low-light environment. Different from existing approaches that use frame-based cameras with fixed exposure times, which trade off signal-to-noise ratio for temporal resolution, we introduc...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25310v1
• Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds

  Practically, training diffusion models typically requires explicit time conditioning to guide the network through the denoising sampling process. Especially in deterministic methods like DDIM, the absence of time conditioning leads to significant performance degradation. However, other deterministic...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25289v1
• Teacher Forcing as Generalized Bayes: Optimization Geometry Mismatch in Switching Surrogates for Chaotic Dynamics

  Identity teacher forcing (ITF) enables stable training of deterministic recurrent surrogates for chaotic dynamical systems and has been highly effective for dynamical systems reconstruction (DSR) with recurrent neural networks (RNNs), including interpretable almost-linear RNNs (AL-RNNs). However, as...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25904v1
• Carbon-Taxed Transformers: A Green Compression Pipeline for Overgrown Language Models

  The accelerating adoption of Large Language Models (LLMs) in software engineering (SE) has brought with it a silent crisis: unsustainable computational cost. While these models demonstrate remarkable capabilities in different SE tasks, they are unmanageably large, slow to deploy, memory-intensive, a...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25903v1
• Variational Neural Belief Parameterizations for Robust Dexterous Grasping under Multimodal Uncertainty

  Contact variability, sensing uncertainty, and external disturbances make grasp execution stochastic. Expected-quality objectives ignore tail outcomes and often select grasps that fail under adverse contact realizations. Risk-sensitive POMDPs address this failure mode, but many use particle-filter be...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25897v1
• Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane

  Graph neural networks such as ParticleNet and transformer based networks on point clouds such as ParticleTransformer achieve state-of-the-art performance on jet tagging benchmarks at the Large Hadron Collider, yet the physical reasoning behind their predictions remains opaque. We present different m...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25885v1
• Adaptive Meta-Learning Stochastic Gradient Hamiltonian Monte Carlo Simulation for Bayesian Updating of Structural Dynamic Models

  In the last few decades, Markov chain Monte Carlo (MCMC) methods have been widely applied to Bayesian updating of structural dynamic models in the field of structural health monitoring. Recently, several MCMC algorithms have been developed that incorporate neural networks to enhance their performanc...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25710v1
• Residual-loss Anomaly Analysis of Physics-Informed Neural Networks: An Inverse Method for Change-point Detection in Nonlinear Dynamical Systems with Regime Switching

  Nonlinear dynamical systems with regime transitions are typically described by ordinary differential equations with jumping parameters parameters. Traditional methods often treat change-point detection and parameter estimation as separate tasks, ignoring the inherent coupling between them. To addres...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25655v1