The paper presents Language Instruction grounding for Motion Planning (LIMP), a system that enables robots to follow complex language instructions by generating semantic maps. LIMP uses foundation models and temporal…
Continue readingThe rapid progress of foundation models has led to the prosperity of autonomous agents, which leverage the universal capabilities of these models for reasoning, decision-making, and environmental interaction. However, these…
Continue readingThis academic article introduces DeLF (Designing Learning Environments with Foundation Models), a method for designing components of the Reinforcement Learning (RL) environment for a specific, user-intended application. The authors focus…
Continue readingThis study introduces Surgical-DINO, a model for depth estimation in endoscopic surgery. This model is a low-rank adaptation of the DINOv2 for depth estimation. The authors integrated LoRA layers into…
Continue readingThis paper introduces a concept called One-shot Open Affordance Learning (OOAL), where a model is trained with just one example per base object category, but is expected to identify novel…
Continue readingThe article by Francesco Croce and Matthias Hein from University of Tübingen AI Center proposes a new approach to adversarial attacks on image segmentation models. These models typically generate segmentation…
Continue readingThe article presents an in-depth study of foundation models tailored for music informatics, a domain challenged by the scarcity of labeled data and generalization issues. The researchers conducted a comparative…
Continue readingThe paper introduces the Foundation Model Transparency Index, a system that assesses the transparency of major AI foundation models. This index uses 100 indicators to evaluate transparency, considering factors such…
Continue readingThe paper presents a framework for evaluating image-based anomaly detectors using synthetically generated validation data. This method, which does not require additional training or fine-tuning, uses a small support set…
Continue readingThe authors introduce a multitask, multilingual, dual-modal Speech and Language Model (SLM). The SLM uses pretrained foundational speech and language models, preserving their capabilities while training a simple adapter with…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
