AI News Archive: August 11, 2026 — Part 16
Sourced from 500+ daily AI sources, scored by relevance.
- DeepBliss.me
Personalized mental wellness platform for future-self practice, in your own voice.
- conw.ai
The AI that learns from you.
- SongStory
Turn any story into a personalized AI song.
- MusicRemover.ai
Remove background music, keep the voice.
- Ecom Visual Ai
Turn one jewelry photo into model shots and video.
- Muse Glimmer
Muse Glimmer
- Kitesurf Cloudflare
Kitesurf Cloudflare
- VlogMe AI
VlogMe AI
- ASCon: A Direction-Aware Reciprocal Agent--Step Contextualization Model for Failure Attribution in Multi-Agent Systems
Failure attribution in LLM-based multi-agent systems (MAS) aims to answer who caused failures, when they occurred, and why by identifying responsible targets including faulty agents, erroneous steps, and failure modes. Existing methods have primarily focused on developing dedicated models for specif...
- Who Are You Explaining To? A Multi-Agent System for Audience-Aware XAI Narratives
Feature-attribution methods such as SHAP provide useful evidence about individual model predictions, but their numerical outputs are rarely sufficient for audiences with different expertise, goals, and risks of misinterpretation. In medical AI, the same local explanation must reach patients, clinici...
- Reifying Research Logic: AI-Assisted Workflow Construction and Incremental Refinement for Quantitative Syntax
Quantitative language research often depends on long chains of computational steps, yet the logic connecting those steps usually remains buried in scripts. This makes analyses harder to inspect, share, and revise than they need to be. Focusing on quantitative syntax, we present QLWF, a visual workfl...
- GeoForge: Non-Parametric Self-Evolving Agents for Earth-Observation Reasoning
Earth observation (EO) agents construct scientifically valid tool workflows and ground their conclusions in current geospatial evidence. This is challenging because EO workflows are constrained by sensing semantics, product dependencies, spatial and temporal compatibility, and parameter requirements...
- Persistent Recursive Worlds Enable Autonomous Software Evolution
Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis (hereafter, Genesis), which instead makes the softw...
- AI-Generated Interactive Fiction for Educational Use: A Pilot Study of Perceived Comprehensibility, Coherence, and Engagement
Generative artificial intelligence (AI) can produce educational content at scale, including interactive and narrative learning experiences, but technical generation alone is not sufficient: scenarios that are confusing, narratively inconsistent, or unengaging are unlikely to be useful in practice. T...
- When the Interviewer Is a Bot: Behavior, Breakdowns, and Trust in MLLM-Led Interviews
Semi-structured interviews are a cornerstone of qualitative research but remain labor-intensive. We report an empirical study of what actually happens when the interviewer is an off-the-shelf real-time multimodal LLM (MLLM). We built InterviewBot, a voice-based interviewing system that wraps a real-...
- Visual-to-Haptic Augmentation in XR: A Wearable Glove for Perceptual Grounding in Multimodal Interaction
Extended Reality (XR) systems increasingly deliver high-fidelity visual and auditory experiences, yet tactile perception remains comparatively underutilized as a modality for enriching embodied interaction. This work presents a visual-to-haptic wearable glove and a feature-based visual-to-haptic map...
- Auditable AI-Assisted Research Writing: An Engineering Discipline with Pre-Registered Process Observation
Language models now draft, classify and criticise inside research production, yet the artifacts they help produce carry little accountable history. Rather than detecting machine involvement afterwards, we specify an auditability discipline built at production time: git sealing with an anchor lineage...
- Leveraging Human Reading Behavior for Keyphrase Extraction: A Webcam-based Eye-tracking Corpus
Purpose: Keyphrases are statistically and semantically important textual units that can also attract readers' attention during comprehension. However, existing keyphrase extraction (KPE) studies mainly focus on improving textual representation while largely overlooking human reading behavior. This s...
- ProtoGIB-Workload: Learning Workload-Specific Neural Topology Prototypes across Subjects
Reliable electroencephalography (EEG)-based mental workload recognition is crucial for adaptive human-centered systems, yet practical deployment requires models to generalize to users unseen during training. Although functional connectivity graphs are widely adopted to capture workload-related neura...
- What We Know about Responsible AI Practices in Industry: A Half Decade of Empirical Research
Responsible AI (RAI) has become a central concern for technology companies, regulators, and the public. How industry practitioners interpret, implement, and sustain RAI work directly shapes the design and deployment of AI systems. As empirical scholarship examining RAI practices in industry has rapi...
- MazzikaAI: A knowledge-based performance-to-prompt compiler for real-time Arabic maqam accompaniment with a streaming text-to-music model
Arabic maqam music microtonal, modal, and built on ornamented call and response is among the traditions most underserved by generative music models, whose training frameworks remain predominantly Western and equaltempered. Real time accompaniment sharpens this gap: an AI partner must listen, adapt d...
- Narrative Keyframing for Generative Creative Writing
We introduce narrative keyframing, an interaction technique for AI-assisted creative writing that lets writers specify different types of narrative constraints at selected moments in a story, then use AI to generate intervening prose. Inspired by the use of keyframing in animation, narrative keyfram...
- A Gateway Architecture for Enterprise MCP Authentication: Unifying Heterogeneous Auth, Identity Delegation, and the User / Non-User Persona Problem
The Model Context Protocol (MCP) has become the de-facto interface for connecting LLM agents to enterprise tools, and adoption has been explosive: within a year, large organizations went from zero to dozens of internally built MCP servers. That speed created a governance crisis. Each team implemente...
- Trigger the Straggler: Load Hijack on Mixture-of-Experts LLMs
Expert parallelism (EP) is a common strategy for serving large Mixture-of-Experts (MoE) models across multiple GPUs by distributing experts among devices. Router decisions then determine both which experts process each token and which GPUs execute the resulting work. This procedure exposes a supply-...
- On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models
Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files, ...
- LLM Ensemble Fault Classification for Automotive HiL Validation
Automotive HiL validation generates large multivariate test recordings whose analysis remains challenging due to manual review effort, rule-based limitations, and the need for explainable diagnostic decisions. Recent machine-learning and deep-learning approaches have improved fault diagnosis, but th...
- CausalRepair: Bridging the Causality Gap in Large Language Model-Based Automated Program Repair via Dual-Slicing
Automated Program Repair (APR) has recently benefited from Large Language Models (LLMs), yet their effectiveness heavily depends on repair context. Existing LLM-based APR methods suffer from a causality gap: test contexts can be noisy or incomplete, while source contexts derived from static analysis...
- Agentic Configuration Management (ACM): A Reference Configuration Model for Governed Agentic Systems
Agentic systems are increasingly composed of heterogeneous agents, prompts, tools, models, skills, composite subsystems, policies, and execution workflows whose configurations evolve across frameworks and runtime environments. Existing LLMOps and AgentOps platforms support orchestration and observab...
- Understanding the Architecture of Coding Agents: An Exploratory Study Using a Research Prototype
Coding agents have rapidly emerged as the primary interface for AI-assisted software development. However, despite their growing adoption, relatively little is known about their internal architecture, and no systematic architectural description comparable to those available for compilers or operatin...
- Role of Personality in Conversational Information Seeking
Large language models (LLMs) are increasingly used for information seeking, where users find, compare, and evaluate information through dialogue. In this role, the assistant does more than retrieve or generate content: it shapes how users articulate constraints, ask follow-up questions, verify claim...
- Deciding When to Rely on Visual Information: Gated Multimodal Fusion in Sequential Recommendation
Multimodal sequential recommender systems commonly fuse visual and collaborative signals uniformly, treating visual features as generically informative regardless of item or user context. We argue that visual utility, defined as the contribution of visual signals to recommendation quality, is a late...
- When Do Anchor-Based Pointwise LLM Rerankers Help? Retriever Quality, Statistical Scope, and Anchor Design
Anchor-based pointwise LLM reranking scores each candidate against a shared reference passage to recover cross-document context at pointwise cost. We study when this actually helps, using GCCP/PAGC as a representative method. Our study is reproduction-first. We use reproduction as a starting point f...
- Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging
Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predictions, often achieving higher accuracy than fast-thinking models that predict directly. However, their reasoning traces are often unnecessarily verbo...
- Detecting an Effect Is Not Learning to Act on It: A Reward-SNR Floor for LLM Acquisition Agents
Many pipelines can pay a per-example cost to acquire an auxiliary, model-derived observation -- an LLM's structured reasoning, a slow oracle, an expensive measurement -- and then must decide when the acquired signal is worth using. Our thesis is a distinction that is easy to miss: detecting that suc...
- Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation
Large language models (LLMs) are increasingly used as relevance assessors in information retrieval (IR) evaluation, raising questions about how assessor framing affects judgment reliability and downstream system comparison. We study persona conditioning as a diagnostic mechanism for exposing LLM ass...
- Are We Really Making Progress in Group Recommendation? Unmasking the Tie-Breaking Illusion
Recent group recommendation methods have reported strong improvements on standard benchmarks, but it remains unclear whether these gains always reflect genuine advances in modeling group preferences. In this paper, we show that several recent methods are affected by a systematic evaluation bias caus...
- Multi Interests for Joint Search-Recommendation Modeling
Search and recommendation are crucial for understanding user preferences. More and more studies are attempting to jointly model search behavior and recommendation behavior, by integrating user active search and passive recommendation behavior data to better mine user preferences. However, although e...
- Post-Calibration Reliability Reranking of Relevance Decisions via Label-wise Monotone Projection
Web search, product search, and question-answering retrieval systems often assign a relevance label and confidence score to each query-candidate pair. The relevance label describes how well a page, product, or passage matches the query, while the confidence often guides downstream use or fallback de...
- AnchorR: A QuPath and R interface for collaborative exploration of spatial transcriptomics and histology
Single-cell spatial transcriptomics can connect molecular cell states with tissue morphology, but this promise depends on accurate registration to histopathology. In serial sections, however, tissue borders often differ because of sectioning artifacts, staining variability, and field-of-view acquisition, limiting conventional area-based registration. We developed AnchorR, an expert-guided workflow for coarse-grained alignment of hematoxylin and eosin (H&E) images with CosMx Spatial Molecular Imaging data. Bioinformaticians first define and color-code cell types in Seurat, and pathologists then identify corresponding internal landmarks using QuPath overlays. AnchorR combines these paired landmarks to estimate affine transformations, quantify residual error, and support visual quality control and anchor refinement. Using six oral pre-cancerous tissue sections, we identified 60 cross-modal landmarks. Fitting each section independently reduced mean landmark error from 121.5 m with a single whole-slide transformation to 14.6 m. Cross-validation further showed that increasing the number of anchors improved robustness, with nine-anchor fits achieving approximately 20 m error, or about one cell diameter. AnchorR is designed to complement automated computer-vision methods by providing reliable tissue-level alignment when border mismatch makes global registration difficult. By creating a shared workspace for pathologists and bioinformaticians, it operationalizes an expert-in-the-loop approach and makes feature-based multimodal registration accessible without specialized computer-vision expertise or high-performance computing.
- Data-Centric Evaluation of Protein Function Prediction Pipelines
Performance estimates in protein function prediction depend not only on model choice but also on upstream decisions that define the learning problem. Using antioxidant protein classification as a controlled case study, we evaluated how dataset harmonisation, protein representation, redundancy control, and partitioning strategy affect protein machine learning pipelines. We integrated 18,804 records from 12 publicly available dataset entries into a curated consensus dataset of 4,193 protein sequences. One-hot encoding and six pretrained protein language model representations were evaluated as model inputs and as similarity spaces for redundancy reduction and distance-aware splitting. Representation choice substantially altered dataset geometry, retained dataset size, class balance, and downstream evaluation. At representation-specific p90 thresholds, one-hot encoding retained the complete dataset, whereas pretrained embeddings retained between 5% and 25% of sequences. Distance-aware partitioning reduced apparent performance relative to random splitting by up to 0.15 MCC before redundancy control, while this difference narrowed after similarity filtering. Selected configurations nevertheless maintained high performance under stricter evaluation, reaching an MCC of 0.84. These findings show that performance estimates should be interpreted as outcomes of complete data-centric workflows rather than isolated properties of predictive models.
- Learning Shared Residue Backgrounds and Modification-Specific Offsets for PTM Site Prediction
Post-translational modifications (PTMs) are chemical changes added to proteins after translation. These changes affect protein function and regulation, and their disruption is linked to disease-associated mechanisms. Because experimentally validating all possible modification sites is impractical, many computational predictors have been developed for PTM site prediction. In this work, we study whether a shared model can represent common residue-background patterns while learning modification-specific background-to-positive offsets. This framing is especially relevant for residues such as lysine (K), which can be acetylated, ubiquitinated, methylated, or sumoylated depending on the surrounding protein context. We propose an anchor-guided rectified flow matching framework for multi-type PTM site prediction from protein language model embeddings. For each PTM--residue pair, the model builds residue-background anchors from PTM-compatible unannotated residues and positive anchors from experimentally annotated modified residues. Given a candidate residue and target modification type, the model compares the residue embedding with these anchor sets and uses a rectified flow module to estimate a modification-conditioned background-to-positive offset. This offset is combined with anchor-based features and used for site scoring. We evaluate the framework on a dbPTM-derived benchmark covering six commonly studied PTMs: phosphorylation, acetylation, ubiquitination, methylation, sumoylation, and N-linked glycosylation. In the shared-model setting, our approach achieves a macro AUPRC of 0.4195, improving over the gated multi-anchor baseline of 0.4154, while independently trained per-modification models achieve 0.4353. These results suggest that multi-type PTM prediction can be modeled within a single shared framework by combining residue-background anchors with modification-conditioned offset features.
- Fast retrieval of structurally similar antibodies from large sequence databases with AbSLang
The first steps in antibody therapeutic discovery involve identification of sequences with desirable binding properties. A way of finding these lead molecules is through the search of large sequence databases. Current methods, due to the size of databases, rely on germline or complementarity-determining-region (CDR) sequence identities, overlooking structurally similar antibodies with divergent sequences which can have identical binding properties . To address this, we introduce AbSLang, a model trained for pairwise CDR RMSD prediction using a contrastive learning approach. We demonstrate that AbSLang has comparable accuracy to exact RMSD calculation after explicit structure prediction with state-of-the-art models. Building on this model, we implemented AbSLang-search, a pipeline for retrieval of structurally similar antibodies from large sequence databases. AbSLang-search is highly compute efficient and allows to search datasets with 10 million sequences in less than 2 seconds.
- A Practice on Antibody Hydrophobic Interaction Chromatography Retention Time Prediction using Pre-Trained Large Language Model Fine-Tuning
Hydrophobicity is a critical property associated with the risk of non-specific binding, and it is commonly assessed using hydrophobic interaction chromatography retention time. Several computational approaches have been developed to predict antibody developability based on pre-trained language models. Such models can be fine-tuned with limited labeled antibody sequences and, in principle, do not require structural information, which is often challenging to obtain. Nevertheless, few studies have achieved strong performance in hydrophobicity prediction without incorporating structural features. Here, we present a case study of fine-tuning the pre-trained model IgBert to predict antibody hydrophobicity. Using Herceptin as a reference, we performed hydrophobic interaction chromatography retention time experiments and generated Herceptin-adjusted datasets. The fine-tuned model achieved a best R2 of 0.916, underscoring the critical role of rigorous data quality control. We also synthesized and validated 20 commercially available antibody sequences, and the results showed that the predicted hydrophobic properties were correctly reflected. Our findings provide practical guidance and highlight considerations for future applications of fine-tuned pre-trained language models in antibody hydrophobicity prediction.
- Enhanced Detection of Age-related Macular Degeneration in Low-quality Retinal Images via Noise-Augmented YOLO and Adaptive Attention Mechanisms
This study aims to improve the detection performance of age-related macular degeneration (AMD) in low-quality retinal images. Background: AMD is a leading cause of vision loss among older adults globally, and accurate detection is crucial for clinical management. However, low-quality optical coherence tomography (OCT) images significantly com-promise diagnostic accuracy. Objective: To enhance AMD detection in low-quality images using noise-augmented data augmentation and an improved YOLO deep learning model. Methods: Public datasets from UCSD and Duke University were utilized; the training dataset comprised 24,980 OCT images (high-quality and noise-augmented low-quality), while the testing dataset included 1,000 images (584 AMD, 416 normal). The model is based on the YOLOv8n framework, integrated with Squeeze-and-Excitation blocks (SEblock) and Adaptive Sparse Self-Attention (ASSA), with an addition-al 160*160 detection layer for detecting small lesions. Evaluation metrics included accuracy, sensitivity, specificity, and F2-score. Results: The proposed model achieved an accuracy of 99.02%, sensitivity of 98.17%, specificity of 100%, and an F2-score of 98.50% on the Duke dataset. Detection rates were significantly improved compared to traditional methods, particularly in low-quality images, with a detection rate of 89.60%, markedly superior to original YOLOv8n (55.10%) and classical models like ResNet50. Conclusion: The enhanced model, employing noise-augmented training data and improved attention mechanisms, demonstrates excellent AMD detection capabilities in low-quality OCT images, showing broad potential for clinical applications.
- Virtual-cell verification enables self-auditing AI discovery for immune rejuvenation
Artificial-intelligence agents propose drug-discovery hypotheses faster than experiments can test them, yet their conclusions are rarely verified, against the underlying biology, the predicted perturbation, or the agent's own scoring logic. We close this verification gap with an agentic framework built on three verifiers. First, PACE, a phenotype verifier, resolves immune aging into ten directionally scored, cell-type-resolved gene-set modules, selected for cross-cohort stability across four PBMC cohorts, and outperforms five established aging clocks in an independent in-house aging cohort of 434 elderly donors. Second, CellQ, a virtual-cell verifier built with multi-modal LLM, compresses each single-cell transcriptome into eight discrete tokens aligned to a language model's vocabulary through residual vector quantization; it attains state-of-the-art perturbation prediction and uniquely resolves the weak, module-level shifts that differential-expression recovery misses. Third, an Analyzer-Planner-Auditor agent verifies its own scoring logic: screening 110 compounds in primary human PBMCs, it found aged-down modules more reversible than aged-up modules and revised its objective from an equal-weight mean to a balance-constrained minimum, a self-correction that generalized to an independent 13-compound T-cell assay. By verifying its predictions and its own objective against experiment, the framework points beyond hypothesis-generating AI toward self-correcting AI scientists whose objectives could continuously evolve.
- High-throughput Virtual Screen of Endocrine-disrupting Chemicals Identifies Disruptors of EGFR Signaling
Chemical exposures during pregnancy are linked to an increased risk of pregnancy complications that contribute significantly to maternal and infant morbidity and mortality and can lead to long term health consequences for both the mother and the offspring. The placenta, a central regulator of pregnancy health, is a direct target of environmental toxicants. Epidermal growth factor receptor (EGFR), highly expressed in the placenta, regulates proliferation, migration, invasion, fusion, and cellular bioenergetics. To identify compounds of environmental concern with potential for EGFR-disrupting activity, we optimized a high-throughput virtual screening protocol for the identification of EGFR inhibitors and achieved enrichment factors of EF% = 10.09, EF% = 3.86, and EF% = 3.0 in a benchmarking dataset. We applied this protocol to screen the Collaborative Estrogen Receptor Activity Prediction Project database, finding that top-scoring compounds were enriched for aromatic and fused-ring chemical classes, including dyes. Kinase activity assays revealed that two out of thirteen selected compounds, Vat Red 32 and Reactive Red 136, inhibited EGFR kinase activity with micromolar IC values. Additionally, pose refinement with molecular dynamics simulations characterized the binding interactions of Reactive Red 136 within the EGFR kinase domain, and functional assays in HTR-8/SVneo placental trophoblast cells showed that Reactive Red 136, but not Vat Red 32, partially attenuated EGF-mediated cell migration despite both compounds inhibiting EGFR kinase activity. Together, this study has generated an enriched dataset of candidate environmental EGFR modulators, with experimental validation confirming enrichment for EGFR-disrupting activity among the selected compounds. These results provide a valuable resource for toxicological studies.
- MSGPCA: Multi-Slice Graph PCA for replicate-aware Spatial Omics analysis
As spatial transcriptomics (ST) and spatial proteomics (SP) technologies mature, experimental designs are increasingly moving beyond single-slice analyses toward multi-slice studies involving one or more donors and experimental conditions. Although these designs enable the identification of reproducible spatial signals, they also introduce substantial biological heterogeneity, particularly when integrating non-serial slices or anatomically distinct regions. If not modeled carefully, such variation can blur slice-specific tissue structure, mask conserved molecular patterns, and limit the discovery of biologically relevant latent structure. Although dimension reduction is essential for representing high-dimensional molecular data in a lower-dimensional space, existing multi-slice methods typically enforce a globally shared representation that inadequately accommodates slice-level heterogeneity. To address this limitation, we propose Multi-Slice Graph Principal Component Analysis (MSGPCA), which decomposes molecular variation into shared spatial factors conserved across slices and slice-specific factors that capture local tissue microarchitecture. In downstream analyses, MSGPCA-derived representations recover spatial tissue structure, denoise molecular profiles, and reveal biologically interpretable metafeatures associated with shared and slice-specific biology. In a mass spectrometry imaging dataset comprising nonserial slices of ductal carcinoma in situ (DCIS) and invasive breast cancer (IBC), the shared factors captured broad biological differences across tissue regions, whereas the slice-specific factors revealed intratumoral spatial variation within the IBC microenvironment. In human dorsolateral prefrontal cortex ST data, MSGPCA recovered laminar cortical architecture across adjacent slices, closely aligning with expert pathologist annotations. Together, these findings demonstrate that MSGPCA resolves shared tissue architecture while preserving local microenvironmental variation in complex multi-slice spatial omics datasets.
- Chromosome assembly for the Black bean aphid Aphis fabae
The black bean aphid, Aphis fabae is a crop pest and vector of insect-transmitted pathogens, comprising closely related sub-species with overlapping host ranges. In other Aphis species, over-expression of specific detoxification genes has been linked to insecticide tolerance. We present two chromosome-scale assemblies for a clonal A.fabae line, representing two phased haplotypes, generated using HiFi and Hi-C sequencing technologies. A comprehensive genome annotation, built with PacBio Iso- Seq data, was used to investigate genes underlying insecticide tolerance. Both genomes are comprised of four chromosomal blocks (haplotype 1: 427 Mb; haplotype 2: 396 Mb) with high BUSCO completeness (98.7%). Comparative genomics revealed an expansion of UDP-glycosyltransferases, whose expression is linked to insecticide detoxification in other Aphis species. These high-quality references provide a foundation for studying A. fabae sub-species and a genomic resource for investigating insecticide tolerance across the Aphis genus.
- Meta-analysis of Genes and Pathways that Protect Against Hypoxia.
Oxygen is essential for all terrestrial animals, but there is dramatic variability in how well different animals and even different cell types can adapt to reduced oxygen availability. We used a meta-analysis of the literature, with a focus on mouse studies, to identify pathways that might act to protect animals in low oxygen environments. We identified 108 genes whose mRNA levels change under hypoxia, and 55 genes critical for mounting a response to hypoxia. With this data, we developed a list of conserved genes, and we tested three C.elegans genes previously uncharacterized in hypoxia, mxl-3, yap-1, and ador-1, and found that loss of function altered egg-laying during and after hypoxia. Our method provides a more targeted approach of how to screen for hypoxic phenotypes and study in more genetically tractable organisms to show mechanisms.
- Age-corrected model for predicting pupil diameter in real-world conditions from melanopic equivalent daylight illuminance
Purpose: Pupil diameter in daily life depends on both the light reaching the eye and the observer's age, but established prediction formulas require laboratory quantities that are rarely measured in natural environments. We developed a compact age-corrected model that predicts pupil diameter from melanopic equivalent daylight illuminance (mEDI). Methods: We used an existing field dataset in which binocular pupil diameter and near-corneal spectral irradiance were recorded while 83 adults aged 18-87 years moved through indoor and outdoor environments. The analysis included 10,082 valid paired observations. We fitted a bounded sigmoid relating pupil diameter to mEDI and age, with each participant given equal influence, and assessed prediction in participants excluded from model fitting. Performance was compared with simpler models, a flexible generalised additive model (GAM), and Watson-Yellott predictions based on assumed field geometry. Results: Pupil diameter decreased smoothly as mEDI increased. Age primarily reduced the difference between pupils in dim and bright conditions, by 0.768 mm per decade, while the predicted bright-light diameter changed little with age. In held-out participants, the bounded model had a participant-balanced root mean squared error (RMSE) of 0.630 mm and mean absolute error of 0.537 mm. The GAM had a slightly lower point-estimate RMSE of 0.610 mm, but the difference was small and uncertain. The bounded model outperformed the tested log-linear, reduced, age-only, and Watson-Yellott alternatives. Conclusion: Age and mEDI are sufficient to provide useful population-average pupil predictions across the observed adult age and real-world light range. The model is transparent, physiologically bounded, and nearly as accurate as a flexible GAM, but predictions approaching darkness remain uncertain because valid mEDI measurements were not available in that range.