每天自动聚合 AI 领域最新动态
Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their d...
Existing benchmarks for scientific data analysis evaluate LLMs primarily on code execution or workflow completion, ov...
Multi-scene navigation (clearing an objective in one bounded space and then crossing a portal into the next) is a def...
Clinical notes contain many of the signs and symptoms that bring patients to care, yet this information rarely reache...
Modern robot learning systems increasingly rely on dense progress or value signals to evaluate intermediate states, g...
Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, mult...
Falling detection is vital for elderly care and intelligent surveillance; however, prevailing vision-based approaches...
In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each d...
Recommender-system research for Vietnamese remains limited by the absence of a public, well-documented hotel interact...
Frozen small code LLMs are deployed locally, yet the information guiding a retry after a failed attempt is still meas...
Math reasoning has achieved significant progress with the rapid advancement of Multimodal Large Language Models (MLLM...
Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user...