Related papers: From catch-up to frontier: The utility model as a …
We consider scenarios where a very accurate (often small) predictive model using restricted features is available when training a full-featured (often larger) model. This restricted model may be thought of as side-information'', and can…
Investigating better ways to reuse the released pre-trained language models (PLMs) can significantly reduce the computational cost and the potential environmental side-effects. This paper explores a novel PLM reuse paradigm, Knowledge…
Large language models (LLMs) commonly risk copyright infringement by reproducing protected content verbatim or with insufficient transformative modifications, posing significant ethical, legal, and practical concerns. Current inference-time…
This doctoral dissertation shows State of the Art of techno-economic modeling for access network technologies, presents the characteristics a universal techno-economic model should have, and shows a classification and analysis of…
The options framework in reinforcement learning models the notion of a skill or a temporally extended sequence of actions. The discovery of a reusable set of skills has typically entailed building options, that navigate to bottleneck…
In imitation learning, an agent learns how to behave in an environment with an unknown cost function by mimicking expert demonstrations. Existing imitation learning algorithms typically involve solving a sequence of planning or…
Research and industry are rapidly advancing the innovation and adoption of foundation model-based systems, yet the tools for managing these models have not kept pace. Understanding the provenance and lineage of models is critical for…
The discovery of utility-driven patterns is a useful and difficult research topic. It can extract significant and interesting information from specific and varied databases, increasing the value of the services provided. In practice, the…
Modeling and forecasting forward citations to a patent is a central task for the discovery of emerging technologies and for measuring the pulse of inventive progress. Conventional methods for forecasting these forward citations cast the…
Deep generative models, particularly diffusion and flow matching models, have recently shown remarkable potential in learning complex policies through imitation learning. However, the safety of generated motions remains overlooked,…
Recent advances in Large Language Models (LLMs) and Text-to-Image (T2I) models have led to the emergence of Unified Multimodal Models (UMMs), where multimodal understanding and image generation are tightly integrated within a shared…
Deep learning has achieved recognition for its impact within natural sciences, however scientists are inhibited by the prohibitive technical cost and computational complexity of training project specific models from scratch. Following…
We address the Continual Learning (CL) problem, wherein a model must learn a sequence of tasks from non-stationary distributions while preserving prior knowledge upon encountering new experiences. With the advancement of foundation models,…
Deploying machine learning (ML) models often requires both fairness and privacy guarantees. Both of these objectives present unique trade-offs with the utility (e.g., accuracy) of the model. However, the mutual interactions between…
This paper tackles the challenge of learning a generalizable minimum-time flight policy for UAVs, capable of navigating between arbitrary start and goal states while balancing agile flight and stable hovering. Traditional approaches,…
Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…
Robot models, particularly those trained with large amounts of data, have recently shown a plethora of real-world manipulation and navigation capabilities. Several independent efforts have shown that given sufficient training data in an…
Unified models (UMs) hold promise for their ability to understand and generate content across heterogeneous modalities. Compared to merely generating visual content, the use of UMs for interleaved cross-modal reasoning is more promising and…
Despite decades of research, existing navigation systems still face real-world challenges when deployed in the wild, e.g., in cluttered home environments or in human-occupied public spaces. To address this, we present a new class of…
In the era of m-Learning, it is found that educational institutions have onus of incorporating the latest technological innovations that can be accepted and understood widely. While investigating the important theme of fast-paced…