Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 11 of 11 for “"Modal reasoning"”.
-
A Neuro-Symbolic Approach to Vision, Language, and Multi-Modal Reasoning
… foundation models for language, image, and multi-modal data, it is becoming feasible for end users to accomplish complex tasks that would otherwise require substantial domain expertise, engineered pipelines, and resources. Yet the capabilities of today's foundation models remain uneven, tracing a …
-
The development and format of possibility representations in young children
Reasoning about possibility is a foundational component of human cognition, supporting planning, learning, and decision-making under uncertainty. Although a substantial literature has examined the development of children’s modal reasoning, much of this work has focused on uncertainty about object …
-
Deep Visual Understanding and Beyond - Saliency, Uncertainty, and Bridges to Natural Language
… what go beyond are the capabilities of multi-modal reasoning which involve also other modalities. That is, a cognitive system is often faced with a daunting process – how to capitalize on the inputs, usually from one or more modalities – to adapt itself to the world of multiple modalities. …
-
Model checking for trustworthy reasoning in autonomous driving
… thesis proposes model checking for trustworthy reasoning in autonomous driving. We combine closed-loop input control and model checking to plan sequences of closed loop controllers for obstacle avoidance in real-time—the former for its superior reactivity to immediate stimuli, and the latter for …
-
Visual understanding of the physical world
… contribution on occlusion, we advance the amodal completion model to recover the complete shape of occluded objects, by utilising the prior of pre-trained Stable Diffusion model.<br><br>For 3D physical understanding, we start with static 3D physical properties in images. To this end, we set …
-
Protein Multimodal Learning for Variant Effect Prediction and Protein Engineering
… emerge at various junctures, marked by cross-modal reasoning, heterogeneous data fusion, interpretability and knowledge transfer to downstream tasks. To identify existing gaps in state-of-the-art protein language models (pLMs) for variant effect prediction (VEP) and motivate learning beyond …
-
Generalized Model to Enable Zero-shot Imitation Learning for Versatile Robots
… challenges by presenting the Cross-modal Reasoning Model (CMRM), a novel zero-shot Imitation Learning policy, to tackle long-horizontal robotic tasks. The RFID inventory task is a typical long-horizontal robotic task that can be formulated as a Partially Observable Markov Decision …
-
Scientifically Responsible Metaphysics: A Program for the Naturalization of Metaphysics
… made scientifically responsible — including modal metaphysics and grounding. I resolve the problem cases by showing how the topics can be made scientifically responsible. First, I articulate a methodology for scientifically responsible modal metaphysics that takes current science as an …
-
Investigating and Tackling Bias and Hackings in AI Alignment
… part of my work extends my inquiry beyond unimodal text generation to the burgeoning field of Omni-modality Language Models (OLMs). To probe the alignment of these more complex systems, we introduce OmnixR, a novel evaluation suite designed to test reasoning across a diverse mix of modalities, …
-
Developing a System for Free-Form Visual Question Answering
… on knowledge-demanding and general visual reasoning datasets.
-
Essence, Explanation, and Modal Knowledge
… a novel account of knowledge of metaphysical modality. I call this the “Essentialist Superexplanatory” account of modal knowledge, because it relies on the following two main theses: (a) knowledge of metaphysical necessity is grounded in knowledge of essence; and (b) essences are properties, …