AI News Archive: July 27, 2026 — Part 16
Sourced from 500+ daily AI sources, scored by relevance.
- DeepFaith: Evidence-Grounded LLMs for Faithful Incident Reporting in Multi-Stage APT Defense
Advanced Persistent Threats (APTs) are difficult to detect and interpret due to their multi-stage and stealthy nature. While recent autonomous defense systems leverage provenance graphs and learning-based models for detection and mitigation, their outputs remain largely machine-oriented and difficul...
- Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
Language-model agents act through structured tool calls whose arguments carry different risks. Untrusted content may safely influence an email body but should not determine a recipient, account, command, or credential. Existing statistical methods typically control risk over the entire action, allow...
- Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guidance (CFG), a default component of modern diffusion systems, remains poorly understood. Existing OPD methods naturally ex...
- ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams
Entity-Relationship Diagrams (ERDs) are central to conceptual database design, yet they are typically available only as rendered images rather than machine-readable schemas, limiting AI-assisted database engineering. We introduce ERUnderstand, the first large-scale benchmark for structured understan...
- Denial of Deadline: Network-Driven Accuracy Collapse in Distributed Inference Pipelines
Inference systems increasingly combine a fast path that returns predictions within the application's latency deadline together with a higher-accuracy slow path that runs higher-compute methods on stronger, remote hardware, so its results can be returned on time and combined with the fast path predic...
- quickstud-e
Educational AI platform
- Prompt Visible
See how invisible your business is to AI, and fix it
- A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility
Scientific user facilities accumulate decades of operational knowledge that no single search index covers: electronic logbooks, technical documents, internal wikis, operations chat messages, maintenance records, and live control-system data. We present APS-RAG, Advanced Photon Source Retrieval Augme...
- Efficiency Matters in Autonomous Research
AI-driven autonomous research (AR) systems are becoming increasingly effective across a broad range of tasks. Their performance, however, is still evaluated primarily by the quality of the final outcome. In this paper, we argue that the efficiency of the solution-search process is an equally importa...
- WoW Cut Video
Turn long videos into subtitled Shorts with AI
- Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior. Features with clear activation descriptions may have weak or unexpected causal effects; steering can vary across prompts or oppose the intended directi...
- LabForge
AI research plans, grants, and paper drafts from one prompt
- Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair
Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee. We study the gap between finding a correct patch and retaining, verifying, and submitting it. A sealed five-seed study over 30 HumanEval repairs produces 900 three-revision trajectories....
- Converg3nce
Get brands verified and trusted by agents and ai
- AutoReg
AI Desktop tool that puts your app's quality on autopilot.
- BashPilot
An AI server admin that gets the work done
- CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding
Long-video understanding increasingly relies on large vision-language models and tool-augmented reasoning, but most systems apply the same inference procedure to every example regardless of difficulty. This uniform strategy invokes unnecessary tool-assisted processing for easy questions and provides...
- PhysiqAI
Your all-in-one fitness trainer
- RyFine
Refine rough ideas into detailed prompts for any LLM
- RSP Editing AI Prompts
Free AI photo editing prompts and builder for creators
- Fit Ninja
Interactive AI workout builder, diet planner & macro tracker
- The Visual Bottleneck: Sparse-Frame Adaptation of MLLMs for Joint Spatial-Temporal Video Grounding
Large-scale video platforms process millions of uploads hourly, requiring moderation systems that can localize when and where policy violations occur within each video. Processing every frame is infeasible at scale, so systems are constrained to sparse inputs of 8 to 16 frames per video. Yet state-o...
- SmartNotesAi
AI medical scribe that writes your clinical notes for you
- Hierarchical Group-Conditional Conformal Risk Control for Selective Prediction in Language Models
Large language models serve heterogeneous populations structured by domain, topic difficulty, and linguistic style. Conformal risk control (CRC) gives rigorous marginal risk guarantees for selective prediction with abstention, but marginal guarantees do not imply per-group ones: a model can meet the...
- LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding
Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step. Attention keys are locally low-rank though globally high-rank: shared low-rank bases discard page-specific directions that a page's own compact basis retains. LOCKS ...
- QuantStudio
Quant trading using Python and Block Code. Live and Backtest
- VeggieFit: AI Nutrition Coach
The AI companion for healthy vegetarian living.
- EchoBridge: Long-Tail-Aware ECG-Echocardiography Text Alignment for Echocardiography-Derived Cardiac Findings
Standardized echocardiography conclusions provide meaningful supervision for learning ECG representations of echocardiography-derived cardiac findings. Global ECG--text alignment may entangle modality-specific factors, while long-tailed finding distributions provide sparse positive supervision for l...
- Stress-Testing EEG Foundation Models for Clinical Decoding: Dataset Identity and Targeted Negative Controls
Pretrained EEG foundation models are increasingly proposed for clinical decoding, but their transfer across populations and robustness to negative controls remain unclear. We benchmark six models (LaBraM, EEGMamba, CBraMod, REVE, BENDR, and BIOT) on five clinical tasks across four datasets using fro...
- ZWPlayer
Free HTML5 video player with AI subtitles & interactivity
- KeywordStat
AI-powered keyword research for modern SEO
- DraftCheck
Honest AI feedback on your LinkedIn draft before you post
- OfficeHQ
The AI-powered virtual office for modern teams
- EasyCoda
Build apps by chatting with AI agent teams.
- Promptrack
Claude Code activity, right in your menu bar
- APICE-Py: An Open-Source MNE-Python Pipeline for Scalable EEG Preprocessing
Electroencephalography (EEG) is fundamental to cognitive neuroscience as it provides a direct measure of human neural activities with millisecond precision. Its noninvasive nature allows for the study of brain function across diverse age groups and experimental contexts-from newborns to adults, and from tightly controlled laboratory environments to more naturalistic real-world settings. However, EEG signals-especially those recorded from infants-are highly prone to noise and artifacts, posing significant challenges for data analysis. To address these issues, we present APICE-Py (Automated Preprocessing for Infants Continuous EEG), an open-source preprocessing pipeline originally designed as a matlab toolbox for infant EEG and now re-implemented in Python to support scalable and flexible analysis across developmental and adult datasets. APICE-Py is built upon three core principles: (i) adaptive artifact detection on continuous data using data-driven thresholds rather than fixed cutoffs; (ii) hierarchical artifact correction, combining short-segment correction via Principal Component Analysis (PCA) with broader segment and continuous data correction using Spherical Spline Interpolation (SSI); and (iii) transparent reporting, providing comprehensive quality logs and decision-tracking to ensure reproducibility and informed analysis. We summarize the underlying algorithms, release an implementation compatible with common EEG formats, and demonstrate its use on three datasets spanning neonates, 5-month-old infants, and child-parent hyperscanned data, acquired using high-density wet electrodes and mobile gel-based EEG systems. When benchmarked against the original MATLAB implementation, APICE-Py achieved comparable levels of data quality and trial retention. While the original pipeline was developed for early developmental EEG (e.g., infants), we show that the pipeline further extends its applicability to both children and adult datasets, enabling robust preprocessing across a broad age range. Moreover, it supports data acquired using a variety of EEG configurations and experimental settings, highlighting its flexibility across age groups, hardware systems, and paradigms. The APICE-Py source code and documentation are freely available at https://github.com/neurokidslab/apice-py.
- Glypad: Precision Engineering, with AI
glypad, engineering drawings, cad, metal ai
- Bee LLM
GEO, tracking chat gpt
- CSV Viewer
Visualize CSV data. Period.
- UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective
Existing methods mainly adapt pretrained autoregressive (AR) language models to masked diffusion, whereas we directly adapt them to uniform-noise diffusion, where every token remains editable during sampling. However, adapting AR checkpoints across corruption kernels remains challenging because exis...
- 123 PDF Editor PRO — Edit PDF offline
Edit, organize, sign and manage PDF pages onlne and offline
- BuildYour.Company
Know exactly why you're stuck.
- HELIOS: An LLM-Driven Autonomous Indirect Trajectory Optimization Agent
Low-thrust trajectory optimization is a core technology in deep-space mission design. Indirect methods based on Pontryagin's Minimum Principle (PMP) offer rigorous optimality guarantees, yet their practical application faces three bottlenecks: (1) transversality conditions must be derived case by ca...
- Rivault
Approve AI agent data access with Face ID
- Tackly
Map your thoughts in real time with AI.
- FindDiskKiller
See which apps are hammering your Mac's disk
- Cynative Security Research Agent
Ask your cloud anything without breaking prod. Read-only.
- From Execution to Capability: Scientific Experience Consolidation via Procedural Knowledge Synthesis
Large language models increasingly solve scientific-computing tasks, but executable feedback from one problem rarely becomes durable capability on subsequent problems. We study scientific-computing experience consolidation: converting verified runtime experience into transferable procedural knowledg...
- ESRVS: Extreme Semi-Supervised Retinal Vessel Segmentation with a Single Annotated Image
Learning from minimal human supervision is a long-standing goal in medical image analysis, where dense expert annotations are costly. We study retinal vessel segmentation in an extreme semi-supervised setting with one annotated image and a pool of unlabeled images. We propose ESRVS, which selects a ...
- Evaluating RAG for French immigration law: a benchmark and baseline study
International recruitment in France requires navigating a layered legal framework absent from existing legal AI benchmarks. We present a publicly available benchmark and first comparative evaluation for this domain, covering permit-type recommendation, required-document retrieval, and legal citation...