The WCog-VLA framework integrates semantic world forecasting and generative world evolution to enable proactive decision-making in end-to-end autonomous driving.
This study introduces a method that uses multimodal language models to visually evaluate reinforcement learning agent behaviors to design more effective training curricula.
Insta360 has introduced CameraMan, a conceptual intelligent photography robot that integrates its AI chip, camera, and audio technologies.
Insta360 has announced its vision for CameraMan, an AI agent concept designed for autonomous filming and photography.
Researchers evaluated the reliability of Gemini models acting as audio judges to score full-duplex voice agent conversations directly from raw waveforms.
Researchers have developed AUTOPILOT-VQA, a benchmark designed to evaluate how well vision-language models can reason about safety-critical traffic incidents using dashcam footage.
An analysis of over two thousand real patient-chatbot interactions led to the development of a patient simulator that models clinical, emotional, and conversational variations.
This study evaluates the limitations of large language models in applying Cognitive Behavioral Therapy, finding that they struggle to transition from theoretical knowledge to practical, user-specific guidance.
The Phasor Transformer block is introduced as a phase-native alternative to standard self-attention, representing sequence states on a unit-circle manifold to bypass quadratic bottlenecks.
AegisDx is a new clinical reasoning framework that coordinates multiple specialized language models to reduce diagnostic errors and verify medical reasoning.
Researchers have introduced PolyWorkBench, a benchmark designed to evaluate the performance of large language model agents on long-horizon tasks in multilingual environments.
Researchers have introduced RetailBench, a simulation benchmark designed to evaluate the long-horizon decision-making and strategic stability of language model agents in a virtual retail environment.
An empirical study of reasoning-capable vision-language models reveals distinct patterns in how their internal uncertainty behaves during multi-step thinking processes.
A new open-source multi-agent firewall architecture secures user interactions with large language models by intercepting and filtering sensitive data across web and programmatic traffic.
Hugging Face has introduced a native-speed vLLM backend for transformers to optimize and accelerate large language model serving.
Japanese data center provider At Tokyo has announced plans to open a new facility in Nagoya next year.
OpenAI Academy has partnered with the Walton Family Foundation to launch interactive training sessions aimed at helping primary and secondary school educators integrate artificial intelligence skills into their classrooms.
Chinese printed circuit board manufacturers are significantly increasing capital expenditure and expanding factory capacity to meet surging global demand driven by the artificial intelligence boom.
The paper introduces a method for identifying and localizing failures within complex, multi-agent systems powered by large language models.
Researchers introduced G-Frame, a multi-agent framework based on game theory principles designed to reduce hallucinations in lightweight language models applied to scientific domains.
MentalHospital is a virtual simulation environment designed to evaluate how effectively large language models handle complete psychiatric clinical encounters.
This paper outlines a multi-agent framework that coordinates solver, critic, and aggregator foundation models to build more reliable cooperative reasoning systems.
The paper explores methods to effectively utilize synthetic speech generated by text-to-speech systems to train automatic speech recognition models in privacy-restricted domains.
DeepTutor is an open-source agentic framework that combines citation-grounded tutoring with calibrated feedback to personalize educational interactions.