Real-time AI-curated news from 66,614+ articles across 50+ sources. Sentiment analysis, importance scoring, and key takeaways — updated every 15 minutes.
Researchers developed a multi-agent LLM system that translates legal statutes into executable software, using U.S. tax preparation as a test case. The system achieved a 45% success rate using GPT-4o-mini, significantly outperforming larger frontier models like GPT-4o and Claude 3.5 which only achieved 9-15% success rates on complex tax code tasks.
Researchers introduce AxelGNN, a new Graph Neural Network architecture inspired by cultural dissemination theory that addresses key limitations of existing GNNs including oversmoothing and poor handling of heterogeneous relationships. The model demonstrates superior performance in node classification and influence estimation while maintaining computational efficiency across both homophilic and heterophilic graphs.
Researchers developed Uni-NTFM, a new foundation model for EEG signal analysis that incorporates biological neural mechanisms and achieved record-breaking 1.9 billion parameters. The model was pre-trained on 28,000 hours of EEG data and outperformed existing models across nine downstream tasks by aligning architecture with actual brain functionality.
Researchers introduce PDR-Bench, the first benchmark for evaluating personalization in Deep Research Agents (DRAs), featuring 250 realistic user-task queries across 10 domains. The benchmark uses a new PQR Evaluation Framework to measure personalization alignment, content quality, and factual reliability in AI research assistants.
Researchers introduce Vision-Zero, a self-improving AI framework that trains vision-language models through competitive games without requiring human-labeled data. The system uses strategic self-play and can work with arbitrary images, achieving state-of-the-art performance on reasoning and visual understanding tasks while reducing training costs.
Researchers have developed a new training-free framework for reward-guided image editing using diffusion models. The approach treats image editing as a trajectory optimal control problem, allowing for better preservation of source image content while enhancing target rewards compared to existing methods.
Researchers developed ELMUR, a new AI architecture that uses external memory to help robots make better decisions over extremely long time periods. The system achieved 100% success on tasks requiring memory of up to one million steps and nearly doubled performance on robotic manipulation tasks compared to existing methods.
Researchers have developed TIGeR, a framework that enhances Vision-Language Models with precise geometric reasoning capabilities for robotics applications. The system enables VLMs to execute centimeter-level accurate computations by integrating external computational tools, moving beyond qualitative spatial reasoning to quantitative precision required for real-world robotic manipulation.
Researchers from KAIST propose AMiD, a new knowledge distillation framework that improves the efficiency of training smaller language models by transferring knowledge from larger models. The technique introduces α-mixture assistant distribution to address training instability and capacity gaps in existing approaches.
Researchers have introduced Kaleido, an open-source AI model for generating consistent videos from multiple reference images of subjects. The framework addresses key limitations in subject-to-video generation through improved data construction and a novel Reference Rotary Positional Encoding technique.
Researchers introduce Agent Data Protocol (ADP), a standardized format for unifying diverse AI agent training datasets across different formats and tools. The protocol enabled training on 13 unified datasets, achieving ~20% performance gains over base models and state-of-the-art results on coding, browsing, and tool use benchmarks.
New research reveals that per-sample Adam optimizer's implicit bias differs significantly from full-batch Adam in machine learning training. The study shows incremental Adam can converge to different solutions than expected, potentially impacting AI model optimization strategies.
Researchers successfully developed multimodal large language models for Basque, a low-resource language, finding that only 20% Basque training data is needed for solid performance. The study demonstrates that specialized Basque language backbones aren't required, potentially enabling MLLM development for other underrepresented languages.
Researchers demonstrate that multi-agent competitive training enables AI agents to develop agile flight capabilities and strategic behaviors that outperform traditional single-agent training methods. The approach shows superior sim-to-real transfer and generalization when applied to drone racing scenarios with complex environments and obstacles.
A comprehensive study analyzed four major large language models (LLMs) across political, ideological, alliance, language, and gender dimensions, revealing persistent biases despite efforts to make them neutral. The research used various experimental methods including news summarization, stance classification, UN voting patterns, multilingual tasks, and survey responses to uncover these systematic biases.
Research examines epistemological risks of widespread LLM adoption, arguing that while AI can reliably transmit information, it lacks reflective justification capabilities. The study warns that over-reliance on LLMs could weaken human critical thinking and proposes a three-tier framework to maintain epistemic standards.
Researchers studied reinforcement learning with verifiable rewards (RLVR) for training large language models on causal reasoning tasks, finding it outperforms supervised fine-tuning but only when models have sufficient initial competence. The study used causal graphical models as a testbed and showed RLVR improves specific reasoning subskills like marginalization strategy and probability calculations.
Researchers developed WCC-Net, a 3D wavelet-based diffusion model that significantly improves low-dose PET imaging denoising while reducing patient radiation exposure. The AI framework uses frequency-domain structural priors to maintain anatomical accuracy and outperforms existing CNN, GAN, and diffusion baselines across multiple dose levels.
A study of 1,725 recruiters across the UK, US, and Germany found that AI skills significantly increase job interview invitation rates by 8-15 percentage points across graphic design, office assistance, and software engineering roles. The research demonstrates that AI skills can partially or fully offset traditional hiring disadvantages like older age or lower education levels.
Researchers developed an automated AI pipeline for detecting cervical spine fractures in medical imaging using a novel 2D-to-3D projection approach. The system achieved clinically relevant performance comparable to expert radiologists while reducing computational complexity through optimized 2D projections instead of traditional 3D methods.
Researchers developed NRR-Phi, a framework that prevents large language models from prematurely committing to single interpretations of ambiguous text. The system maintains multiple valid interpretations in a non-collapsing state space, achieving 1.087 bits of mean entropy compared to zero for traditional collapse-based models.
Researchers developed a new training method combining Chain-of-Thought supervision with reinforcement learning to teach large language models when to abstain from answering temporal questions they're uncertain about. Their approach enabled a smaller Qwen2.5-1.5B model to outperform GPT-4o on temporal question answering tasks while improving reliability by 20% on unanswerable questions.
Chimera introduces a framework that enables neural network inference directly on programmable network switches by combining attention mechanisms with symbolic constraints. The system achieves line-rate, low-latency traffic analysis while maintaining predictable behavior within hardware limitations of commodity programmable switches.
Researchers developed a new AI-powered framework for crystal structure prediction that uses large language models and symmetry-driven generation to overcome computational bottlenecks. The approach achieves state-of-the-art performance in discovering new materials without relying on existing databases, potentially accelerating materials science research.
Researchers introduce PhysMem, a memory framework that enables vision-language model robot planners to learn physical principles through real-time interaction without updating model parameters. The system records experiences, generates hypotheses, and verifies them before application, achieving 76% success on brick insertion tasks compared to 23% for direct experience retrieval.
