Researchers have developed AuditFlow, a graph-grounded multi-agent framework that creates executable symbolic environments for structured financial reporting verification. The system, which separates adaptive search from…
Researchers have developed TriEval, a resource-efficient pipeline that simultaneously evaluates large language models for bias, toxicity, and truthfulness. The tool runs on standard laptops without GPU clusters and works…
Researchers have developed RelGT-AC, a relational graph transformer designed to predict missing column values in relational databases, functioning as an intelligent form-filling assistant. The model introduces a column m…
Researchers introduced ToolGate, a lightweight external controller that predicts whether to execute or skip tool calls proposed by vision-language agents, addressing the pre-call control problem where many tool execution…
Researchers introduced AVTrack, a new human-centric audio-visual instance segmentation dataset designed for dynamic real-world scenarios. The dataset features challenging conditions such as camera motion, visual occlusio…
Leading vision-language models (VLMs) produce view-invariant and consistent answers to spatial distance queries even when those answers are incorrect, revealing a weak link between predictions and actual visual evidence.…
Researchers have developed MetaWorld, a framework that scales multi-agent video world models to open-domain environments using only single-view video data. The system addresses data scarcity and world state alignment cha…
Researchers from multiple institutions evaluated machine learning and deep learning models for satellite-derived bathymetry using Sentinel-2 imagery, finding that preserving spatial continuity during training was the mos…
Researchers introduced GeoDrive-Bench, a benchmark of 5,053 human-validated multiple-choice questions across six countries to test vision-language models on region-specific traffic rules and driving behavior. Testing nin…
NVIDIA researchers introduced Cosmos 3, a family of omnimodal world models that jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. The …
Researchers developed an automated pipeline that generates multiple-choice visual question answering (VQA) benchmarks directly from private radiology reports and 3D oncology imaging, producing two question types without …
Researchers introduced Mixture of Pathway Experts (MoPE), a knowledge-distillation framework that uses RNA-derived pathway information during training to improve computational pathology models that only analyze whole-sli…
Researchers have developed a collaborative inference method for occlusion-robust object detection on edge devices with less than 1 MB SRAM, combining an MCUNet backbone, YOLOv2 detection head, and TensorFlow Lite quantiz…
Researchers introduced Any2Poster Bench, a benchmark for evaluating automatic poster generation across eight input modalities and five content domains, alongside Any2Poster Agent, a system that parses diverse sources and…
Researchers have developed Pixel Cube, a diffusion-based method for relighting dynamic portrait videos that achieves photorealism and temporal consistency. The system uses a hybrid dataset of real-captured and rendered v…
Researchers have developed a two-stage geometric registration method that aligns CAD models to CT scans of cylindrical objects by detecting elliptical cross-sections and estimating the 3D rotation axis. The approach achi…
A new study evaluating 31 large language models found that many LLMs express environmental attitudes more progressive than the average human survey respondent, recommending behaviors linked to greater CO2 reductions. Res…
A developer has identified that most AI agent projects fail due to architecture designed for SaaS features rather than autonomous systems. The 2026 guide outlines five main deployment architectures, including specialized…
A developer created CodeFootprint, a Mac app that tracks file changes in project folders without ever connecting to the internet. The tool records every edit with full diffs and deletions with recoverable content, requir…
A developer built MangoGuard, an edge AI system that detects mango diseases directly on an Arduino Nano microcontroller without requiring cloud connectivity or internet access. The quantized MobileNetV1 model classifies …