Researchers have developed a new approach using the Artifact-Transform Workflow Language (ATWL) and an AI assistant that reduces visual-analytics testing from months to hours. The method, which involv…
Researchers have developed a new framework for detecting backdoor attacks in large language models, addressing the challenge of discrete input spaces. The framework introduces Class Subspace Orthogona…
Researchers have developed a compact fingerprint model for AI skill identity that uses locality-sensitive hashing to preserve skill relationships, achieving 0.974 AUC on pairwise comparisons with 77 t…
Researchers have developed a failure-driven self-improvement loop for AI training that leverages failed trajectories to boost performance, challenging the traditional focus on successes. The approach …
A new unified AI model integrates textual reasoning and graph processing into a single masked diffusion language model, outperforming graph neural networks, graph transformers, and LLM-based baselines…
New research reveals that large language models like GPT-4o-mini, Gemini-2.0-Flash, and Qwen3-Coder-Next frequently overestimate the security of generated code, posing risks in software development. T…
Researchers introduced LINet, a multi-stream neural network for RGB-D scene classification that outperforms existing methods through a continuous integration strategy. LINet uses a novel Linear Integr…
SkillSpotter, a new AI system using augmented reality glasses, provides real-time performance analysis and coaching for skilled activities like sports and music. It achieved a 76% improvement in class…
Self-driving cars perform well in simulations but struggle with real-world prediction and planning, often relying on brittle heuristics rather than genuine understanding. Researchers warn that current…
The Vanilla-SPDE Exchange introduces a hybrid scheme that reduces Gaussian process inference costs in spatio-temporal settings by combining standard Gaussian processes with SPDE formulations. This inn…
RosettaSim, a new framework from researchers, integrates Large Language Model attention mechanisms into traffic simulations to improve multi-agent interactions, outperforming existing methods in the W…
Large language model agents have improved lower bounds on two classic mathematical inequalities, the first autocorrelation inequality and the Erdős minimum-overlap constant, using automated constraint…
New research explores multi-agent deliberation (MAD) frameworks for legal reasoning using large language models, showing that multi-agent systems can match or complement traditional models in handling…
AI is revolutionizing simulation model discovery using transformer-based embeddings and retrieval strategies, enabling natural language queries to find relevant models. A recent study shows open-sourc…
TF-MoE, a sparse Mixture-of-Experts framework, enhances speech separation model capacity without increasing computational costs, outperforming existing methods. It achieves a +3.8 dB SDR improvement o…
NVIDIA's Nemotron Model Reasoning Challenge saw researchers achieve 96% validation accuracy and a 7th-place finish by abandoning traditional arithmetic logic for bit manipulation puzzles. Instead, the…
Researchers developed HS2C, a method that compresses graph data by leveraging homophily to improve large language models' reasoning accuracy. Tested on 10 node-level benchmarks, HS2C enhances compress…
Researchers developed CRAFT, a framework that reduces collisions by 31.2% and traffic violations by 33.2% in traffic simulations by aligning local training contexts with global deployment conditions, …
Researchers introduced RT-SFOD, a new object detection method that improves speed and accuracy by building on YOLOv10 and using dual-head pseudo-label fusion and multi-scale feature diversification. T…
REMSA, an AI-driven agent, revolutionizes remote sensing by automating foundation model selection using the RSFM Database of over 160 models. It outperformed competitors in benchmark tests, enabling f…