AI
PromptResponse: Optimizing Prompts for LLM Coding Tasks
Researchers have developed PromptResponse, a study on optimizing prompts for large language models (LLMs) used in coding tasks. They found that consis...
AI
AI
Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems
Researchers have proposed an Evaluation Agent to detect misinformation and knowledge poisoning in Generative AI systems. The agent uses a combination ...
AI
A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration
Researchers propose a new approach to multi-modal object detection called A2DINOv3. This method combines data from different sources, such as RGB and ...
AI
ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents
A new security system called ClawSentry has been developed to protect large language model (LLM) agents from malicious attacks. The system uses a mult...
AI
Atom Learning Model (ALM): how a real classroom got tokenised
The Atom Learning Model (ALM) tokenises a school curriculum by breaking down math textbooks into individual 'atoms' - specific actions or steps that l...
AI
CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agents
Researchers have developed a new type of attack on visual world-model agents, such as DreamerV3. These attacks, called Critic-Induced Value-Subspace A...
AI
A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans
Researchers have developed a modular agent that can reliably verify spatial relations in CT scans. The system works by breaking down the task into thr...
AI
Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
Researchers have proposed a new approach to developing artificial intelligence called Graph Engineering. This method involves creating dynamic graph s...
AI
HIERA: Workload-Aware Planning Across Implementation Spaces for GPU Kernel Optimization
Researchers have proposed HIERA, a new approach to optimizing GPU kernel performance. Unlike existing methods that focus on a single implementation sp...
AI
AID-Guard: Stateful Authorization for Delegated Agent Effects
Researchers have developed AID-Guard, a protocol for stateful authorization in AI agents. The protocol ensures that only approved requests are execute...
AI
Is Visual Prompting All You Need? Studying VLM Spatial Reasoning under Progressive Visual Scaffolds
Researchers have found that visual presentation can significantly impact the performance and failure modes of vision-language models (VLMs) in spatial...
AI
SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control
Researchers have developed a new method for safe and efficient navigation in crowded areas with heterogeneous shapes. The Shape-Aware Reinforcement Le...