AI News Archive: April 28, 2026 — Part 17

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

• AI Core Updates

  Your daily dose of AI news, breakthroughs, and core updates

  🧰 ToolsApr 28, 2026https://www.producthunt.com/products/ai-core-updates?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+the500feed+%28ID%3A+283491%29
• GeniLoop | AI Image to Video Generator

  Transform any photo into stunning dynamic videos.

  🧰 ToolsApr 28, 2026https://theresanaiforthat.com/ai/geniloop-ai-image-to-video-generator/
• SEOForge.ai

  Get Customers from SEO & AI Search

  🧰 ToolsApr 28, 2026https://theresanaiforthat.com/ai/seoforge-ai/
• img2.ai

  Create consistent photo variations in any style.

  🧰 ToolsApr 28, 2026https://theresanaiforthat.com/ai/img2-ai/
• Thumix AI

  Generate viral YouTube thumbnails with AI in seconds.

  🧰 ToolsApr 28, 2026https://theresanaiforthat.com/ai/thumix-ai/
• TrajectoryAI

  Real-time company monitoring with AI insights on competitors and clients

  🧰 ToolsApr 28, 2026https://theresanaiforthat.com/ai/trajectory-ai/
• Anijam.ai

  Simplified AI animation tool for stable, character-consistent anime videos with automatic lip-sync.

  🧰 ToolsApr 28, 2026https://saasaitools.com/listing/anijam-ai/
• Workflows Mistral

  Workflows Mistral

  🧰 ToolsApr 28, 2026https://www.aixploria.com/en/workflows-mistral/
• TRELLIS.2

  TRELLIS.2

  🧰 ToolsApr 28, 2026https://www.aixploria.com/en/trellis-2-microsoft/
• Miadance

  Miadance

  🧰 ToolsApr 28, 2026https://www.aixploria.com/en/miadance/
• Scaling Biomolecular Modeling Using Context Parallelism in NVIDIA BioNeMo

  For decades, computational biology has operated under a reductionist compromise. To fit complex biological systems into the limited memory of a single GPU,...

  📄 ResearchApr 28, 2026https://developer.nvidia.com/blog/scaling-biomolecular-modeling-using-context-parallelism-in-nvidia-bionemo/
• Pythia: Toward Predictability-Driven Agent-Native LLM Serving

  As LLM applications grow more complex, developers are increasingly adopting multi-agent architectures to decompose workflows into specialized, collaborative components, introducing structure that constrains agent behavior and exposes useful semantic predictability. Unlike traditional LLM serving, wh...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25899v1
• Volitional Multiagent Atomic Transactions: Describing People and their Machines

  Formal models for concurrent and distributed systems describe machines; the people who operate them are either ignored or treated as external environment. Yet key distributed systems -- notably grassroots platforms -- include people operating their personal machines (smartphones), and their faithful...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25596v1
• Should I Replan? Learning to Spot the Right Time in Robust MAPF Execution

  During the execution of Multi-Agent Path Finding (MAPF) plans in real-life applications, the MAPF assumption that the fleet's movement is perfectly synchronized does not apply. Since one or more of the agents may become delayed due to internal or external factors, it is often necessary to use a robu...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25567v1
• Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents

  Embodied agents in safety-critical applications such as Vision-Language Navigation (VLN) rely on multiple interdependent capabilities (e.g., perception, memory, planning, decision), making failures difficult to localize and attribute. Existing testing methods are largely system-level and provide lim...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25161v1
• Lexical Anthropomorphization Influences on Moral Judgments of AI Bad Behavior

  Anthropomorphic language describing artificial intelligence (AI) is widespread in media, policy, and everyday discourse; so too are discussions of AI bad behavior, from hallucinations to inappropriate comments. How does humanizing language about AI shape moral judgments when AI behaves badly? Across...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25814v1
• Recommending Usability Improvements with Multimodal Large Language Models

  Usability describes quality attributes of application user interfaces that determine how effectively users can interact with them. Traditional usability evaluation methods require considerable expertise and resources, which can be challenging, especially for small teams and organizations. Automating...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25420v1
• Designing and Evaluating Next-Generation Learning Interfaces: Linking AI, HCI, and the Learning Sciences

  This workshop addresses this gap by bringing together researchers and practitioners from AI, HCI, and the learning sciences to explore how interactive systems can better support learning. We focus on the design and evaluation of human-AI collaborative learning interfaces that are technically robust,...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25721v1
• ClayScape: A GenAI-Supported Workflow for Designing Chinese Style Ceramics with Clay 3D Printing

  Chinese ceramic-making involves complex and interdependent steps, making it technically demanding. Digital fabrication methods attempt to make the process more accessible, but for craft-creators, technical challenges such as CAD and CAM skills remain major obstacles. To address this, we designed a h...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25657v1
• Generative UI as an Accessibility Bridge: Lessons from C2C E-Commerce

  Web accessibility rests on static standards and developer compliance. That model frays in platforms where content is user-generated: photos arrive blurry or off-frame, descriptions skip size and condition, and page structure shifts from listing to listing. Drawing on six studies conducted between 20...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25455v1
• One-shot emergency psychiatric triage across 15 frontier AI chatbots

  AI chatbots are increasingly used for health advice, but their performance in psychiatric triage remains undercharacterized. Psychiatric triage is particularly challenging because urgency must often be inferred from thoughts, behavior, and context rather than from objective findings. We evaluated ...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25415v1
• Co-Writing with AI: An Empirical Study of Diverse Academic Writing Workflows

  Despite AI tools becoming increasingly embedded in academic practice, little is known about how university students integrate them into their writing processes. We examine how students engage with AI across different writing tasks, and how this engagement is shaped by individual factors including AI...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25389v1
• Value-Sensitive AI for Prayer: Balancing the Agencies Between Human and AI Agents in Spiritual Context

  We present four conceptual value-sensitive AI systems to examine how the presence of AI could influence praying experiences. Drawing on key values and practices associated with praying identified through a diary study, we designed AI systems intended to "assist" prayer practices. These designs were ...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25230v1
• The Dynamics of Delusion: Modeling Bidirectional False Belief Amplification in Human-Chatbot Dialogue

  There is growing concern that AI chatbots might fuel delusional beliefs in users. Some have suggested that humans and chatbots mutually reinforce false beliefs over time, but quantitative evidence is lacking. Using a unique dataset of chat logs from individuals who exhibited delusional thinking, we ...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25096v1
• From CRUD to Autonomous Agents: Formal Validation and Zero-Trust Security for Semantic Gateways in AI-Native Enterprise Systems

  Enterprise software engineering is shifting away from deterministic CRUD/REST architectures toward AI-native systems where large language models act as cognitive orchestrators. This transition introduces a critical security tension: probabilistic LLMs weaken classical mechanisms for validation, acce...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25555v1
• MARD: A Multi-Agent Framework for Robust Android Malware Detection

  With the rapid evolution of Android applications, traditional machine learning-based detection models suffer from concept drift. Additionally, they are constrained by shallow features, lacking deep semantic understanding and interpretability of decisions. Although Large Language Models (LLMs) demons...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25264v1
• R-CoT: A Reasoning-Layer Watermark via Redundant Chain-of-Thought in Large Language Models

  Large language models (LLMs) are widely deployed in multiple scenarios due to reasoning capabilities. In order to prevent the models from being misused, watermarking is generally employed to ensure ownership. However, most existing watermarking methods rely on superficial modifications to the model'...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25247v1
• Making AI-Assisted Grant Evaluation Auditable without Exposing the Model

  Public agencies are beginning to consider large language models (LLMs) as decision-support tools for grant evaluation. This creates a practical governance problem: the model and scoring rubric should not be exposed in a way that allows applicants to optimize against them, yet the evaluation process ...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25200v1
• SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents

  Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious instructions into webpage content to induce unintended actions. This threat is further amplified for screenshot-based web...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25562v1
• ReTokSync: Self-Synchronizing Tokenization Disambiguation for Generative Linguistic Steganography

  Generative linguistic steganography (GLS) enables covert communication by embedding secret messages into the natural language generation process. In practical deployment, however, GLS is vulnerable to tokenization ambiguity: the same surface text may be re-tokenized into a different token sequence a...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25486v1
• AgentDID: Trustless Identity Authentication for AI Agents

  AI agents are autonomous entities that can be instantiated on demand, migrate across platforms, and interact with other agents or services without continuous human supervision. In such environments, identity is critical for establishing reliable interaction semantics among agents that may lack prior...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25189v1
• MGTEVAL: An Interactive Platform for Systemtic Evaluation of Machine-Generated Text Detectors

  We present MGTEVAL, an extensible platform for systematic evaluation of Machine-Generated Text (MGT) detectors. Despite rapid progress in MGT detection, existing evaluations are often fragmented across datasets, preprocessing, attacks, and metrics, making results hard to compare and reproduce. MGTEV...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25152v1
• Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills

  Agent Skills package SKILL.md files, scripts, reference documents, and repository context into reusable capability units, turning pre-load auditing from single-prompt filtering into cross-file security review. Existing guardrails often flag risk but recover malicious intent inconsistently under sema...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25109v1
• From Threads to Trajectories: A Multi-LLM Pipeline for Community Knowledge Extraction from GitHub Issue Discussions

  Resolution of complex post-production issues in large-scale open-source software (OSS) projects requires significant cognitive effort, as developers need to go through long, unstructured and fragmented issue discussion threads before that. In this paper, we present SWE-MIMIC-Bench, an issue trajecto...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25880v1
• Using Large Language Models for Black-Box Testing of FMU-Based Simulations

  We propose a human in the loop approach for black-box testing of Functional Mock-up Units (FMUs) using Large Language Models (LLMs). The goal is to reduce the manual effort in defining test scenarios for dynamic simulation models and to improve the interpretability of results. The approach takes the...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25650v1
• CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction

  Despite strong performance on code generation tasks, it remains unclear whether large language models (LLMs) genuinely reason about code execution. Existing code reasoning benchmarks primarily evaluate final output correctness under a single canonical implementation, leaving two critical aspects und...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25399v1
• AI as Consumer and Participant: A Co-Design Agenda for MBSE Substrates and Methodology

  AI tools are being deployed over MBSE models today, and those models were not designed for this kind of consumption. The problem is not simply that tools hallucinate: well-prompted frontier models produce competent, useful output over a conformant SysML model, but the reasoning they produce is drawn...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25526v1
• DiRe-RAPIDS: Topology-faithful dimensionality reduction at scale

  Dimensionality reduction methods such as UMAP and t-SNE are central tools for visualising high-dimensional data, but their local-neighborhood objectives can preserve sampling noise while distorting global topology. We show that standard local metrics reward this noise memorisation: top-performing em...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25209v1
• ML-SAN: Multi-Level Speaker-Adaptive Network for Emotion Recognition in Conversations

  To establish empathy with machines, it is essential to fully understand human emotional changes. However, research in multimodal emotion recognition often overlooks one problem: individual expressive traits vary significantly, which means that different people may express emotions differently. In ou...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25383v1
• UNet-Based Fusion and Exponential Moving Average Adaptation for Noise-Robust Speaker Recognition

  The joint training of speech enhancement and speaker embedding networks for speaker recognition is widely adopted under noisy acoustic environments. While effective, this paradigm often fails to leverage the generalization and robustness benefits inherent in large-scale speech enhancement pre-traini...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25624v1
• K-CARE: Knowledge-driven Symmetrical Contextual Anchoring and Analogical Prototype Reasoning for E-commerce Relevance

  This paper targets e-commerce search relevance. While Large Language Models (LLMs) have demonstrated significant potential in this field, they often encounter performance bottlenecks in persistent 'corner cases' within complex industrial scenarios. Existing research primarily focuses on optimizing r...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25683v1
• Make Any Collection Navigable: Methods for Constructing and Evaluating Hypergraph of Text

  One reason the Web is more useful than a simple collection of documents is that the structure created by hyperlinks enables flexible navigation from one web page to another. However, hyperlinks are typically created manually and cannot fully capture a corpus' implicit semantic structures. Is there a...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25906v1
• Break the Inaccessible Boundary: Distilling Post-Conversion Content for User Retention Modeling

  User retention is a key metric to measure long-term engagement in modern platforms. In real-time bidding (RTB) advertising system for user re-engagement, the retention model is required to predict future revisit probability at bidding time, before the user converts and consumes any content. Although...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25839v1
• Harmonizing Generative Retrieval and Ranking in Chain-of-Recommendation

  Generative recommender systems have recently emerged as a promising paradigm by formulating next-item prediction as an auto-regressive semantic IDs generation, such as OneRec series works. However, with the next-item-agnostic prediction paradigm, its could beam out some next potential items via Sema...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25787v1
• Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users

  Cross-domain recommendation (CDR) has demonstrated to be an effective solution for alleviating the user cold-start issue. By leveraging rich user-item interactions available in a richly informative source domain, CDR could improve the recommendation performance for cold-start users in the target dom...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25732v1
• From Citation Selection to Citation Absorption: A Measurement Framework for Generative Engine Optimization Across AI Search Platforms

  Generative search engines increasingly determine whether online information is merely discoverable, cited as a source, or actually absorbed into generated answers. This paper proposes a two-stage measurement framework for Generative Engine Optimization (GEO): citation selection, where a platform tri...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25707v1
• The Attention Market: Interpreting Online Fair Re-ranking as Manifold Optimization under Walrasian Equilibrium

  Fair re-ranking aims to promote long-tail items and enhance diversity within groups in information retrieval. While previous research on online fairness-aware re-ranking has shown promising outcomes, our comprehensive evaluation of online fair re-ranking methods over 20 settings reveals significant ...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25577v1
• From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space

  In modern recommender systems, list-wise reranking serves as a critical phase within the multi-stage pipeline, finalizing the exposed item sequence and directly impacting user satisfaction by modeling complex intra-list item dependencies. Existing methods typically formulate this task as selecting i...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25291v1
• UnIte: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval

  Unsupervised domain adaptation generalizes neural retrievers to an unseen domain by generating pseudo queries on target domain documents. The quality and efficiency of this adaptation critically depend on which documents are selected for pseudo query generation. The existing document sampling method...

  📄 ResearchApr 28, 2026http://arxiv.org/abs/2604.25142v1
• Improving Biological Sequence Prediction with AlphaFold2 Representation

  Motivation: Accurate prediction of functional sites from primary sequences is essential for elucidating biological mechanisms and advancing rational drug design. However, traditional sequence-based features areinherently unable to capture complex structural protein contexts. Recently, AlphaFold2 (AF2) revolutionized protein structure prediction, raising expectations of AF2 to serve as a feature extractor providing structure- rich representation, which can be useful for sequence-based prediction, particularly for unknown sequences. Results: We present a novel feature-engineering paradigm that leverages a high-dimensional latent representation matrix (of L multiply D, where L is the sequence length and D is the feature dimension size) extracted directly from the AF2 Evoformer module. We systematically evaluated the AF2 representation, comparing with conventional sequence-based features, such as hidden Markov model profiles, using a variety of machine learning models, on two structurally

  📄 ResearchApr 28, 2026https://www.biorxiv.org/content/10.64898/2026.04.26.720550v1?rss=1