A new scheduling method for heterogeneous edge GPUs aims to improve the efficiency and throughput of vision transformer models in autonomous vehicle applications.
ActiveFly-Bench is a new benchmark designed to evaluate aerial embodied perception by linking high-level task understanding, behavior planning, and low-level control for unmanned aerial vehicles.
Embodied-R1.5 is a new foundation model designed to unify embodied reasoning and physical intelligence using a large-scale dataset of 15 billion tokens.
The study identifies a critical inefficiency in Chain-of-Thought prompting where models generate redundant but logically valid reasoning steps that current evaluators fail to penalize.
This paper proposes a learnable Dirichlet-process cache that stores only novel inputs to bridge the gap between state-space models and attention mechanisms.
This paper outlines a deployment-focused pathway for transitioning medical AI agents from simple assistants to autonomous clinical systems.
IdeaTrail is a new dataset designed to capture the complete, multi-stage workflow of AI agents performing scientific ideation and research tasks.
Researchers have introduced SDABench, a new benchmark designed to evaluate the scientific data analysis capabilities of large language models across six distinct areas.
The authors introduce SWE-MERA, a dynamic benchmark designed to mitigate data contamination and improve the evaluation of LLMs on software engineering tasks.
This paper provides a comprehensive survey and a new two-level taxonomy of Graph Neural Network methodologies applied across knowledge graph technologies.
MemDecay is a new memory management technique that optimizes LLM agent inference by using region-aware KV cache eviction based on semantic structure.
This paper examines the phenomenon of model collapse from both engineering and creative perspectives, exploring how recursive training on AI-generated data affects model output.
Researchers propose a new speculative decoding method that improves large language model inference speed by utilizing progressive tree drafting to better exploit parallel processing.
The Mako project introduces a self-evolving agentic operating system capable of autonomously synthesizing and testing new security exploits.
Researchers have introduced a new benchmark dataset of mathematical constant formulas to evaluate the advanced mathematical reasoning capabilities of AI systems.
The authors introduce FARS, a fully automated system that enables AI agents to conduct research, generate hypotheses, and write manuscripts at scale.
Agentic-DPO is a new training framework designed to optimize AI agent policies on expert trajectories by teaching them to avoid plausible mistakes rather than just imitating sequences.
This study analyzes the internal attention dynamics of vision-language models to explain why visual grounding degrades and proposes scheduling visual relay windows to stabilize reasoning.
The paper introduces HCRMap, a mapping framework designed to mitigate compute and communication imbalances caused by uneven expert activation in Mixture-of-Experts models on multi-chiplet systems.
Researchers released FindMyText, an open-source Python package designed to detect near-verbatim text containment within large web-crawled datasets using document fingerprinting.
AutoNavi has launched ABot-World Studio, a tool that enables the generation of interactive 3D scenes and videos using a single consumer-grade GPU.
Amazon has introduced a new user interface in SageMaker AI Studio to help developers easily benchmark and deploy optimized generative AI models.
A new framework has been introduced to assist data center operators in managing regulatory compliance and operational complexity on a global scale.
IM Motors addressed concerns regarding dealer management issues following the launch of its new SUV model.