The paper provides a theoretical framework linking Joint-Embedding Predictive Architectures to active inference principles through variational free energy.
A new defense mechanism called Traffic-Aware Randomized Smoothing has been proposed to improve the robustness of LLM-based network intrusion detection systems against traffic manipulation.
MedDiffuseMix provides a saliency-guided diffusion framework to augment medical imaging data while preserving critical diagnostic features.
HealthClaw is a proposed self-evolving agent architecture designed to provide longitudinal health management by maintaining private memory of user routines and medical history.
Researchers analyzed nearly 3,000 GitHub projects to understand how the integration of automated bots as active participants influences the organizational structure of open-source software teams.
Researchers have proposed a training-free approach for detecting human-object interactions in the wild by leveraging the capabilities of multimodal large language models.
A new method for test-time learning introduces learnable adaptation policies to help language agents improve their performance through iterative interaction.
The authors present a method for integrating compiler feedback directly into the autoregressive decoding process to improve the quality of AI-generated code.
A study evaluating root cause analysis in microservice failures reveals that current AI and classical methods struggle to effectively process large-scale, multimodal telemetry data.
This paper proposes a causal framework to determine when artificial intelligence systems should engage in theory of mind processes during conflict scenarios.
A new benchmark based on cognitive psychology tests has been developed to evaluate how AI agents adapt when the reliability of their tools changes during operation.
The study evaluates the impact of audio separation preprocessing on zero-shot automatic speech recognition performance, finding that cleaner audio does not always improve transcription accuracy.
This paper proposes a framework for networked intelligence that uses shared context graphs to facilitate collaboration among multiple AI agents in scientific research.
The Multi-Agent System Process Reward Model provides a method to evaluate and optimize message sequences between agents during inference-time search.
DIVE is a new dimensionality reduction technique for language model embeddings that uses self-limiting gradient updates to improve compression efficiency.
This review examines the integration of explainable AI techniques within federated learning architectures to improve transparency in privacy-preserving distributed model training.
A new error-correction method called Experience Memory Graph aims to help LLM agents recover from failures in long-horizon tasks more efficiently than traditional reflection techniques.
A new evaluation framework called STOCKTAKE aims to distinguish between perception errors and execution failures in LLM agents during long-term decision-making tasks.
A study demonstrates that the interaction protocols used in multi-agent debates significantly influence the moral reasoning and judgment outcomes of large language models.
A new auditing method uses predicate substitution to test whether large language models genuinely rely on stated premises during chain-of-thought reasoning.
Infineon and LS Electric have signed a non-binding memorandum of understanding to jointly develop next-generation direct current power systems for AI data centers.
CITIC Securities and Optics Valley Financial Holdings have entered a partnership to provide capital market services and investment support for emerging technology companies.
This article discusses the potential financial risks and market implications of including SpaceX in major index funds.
Healthcare compliance company Bluesight has utilized Amazon Bedrock AgentCore to develop and deploy Prism, a unified agentic AI assistant.