计算机科学

Deep generative models are increasingly used as simulators for downstream decision-making under data scarcity, but in risk-sensitive applications their usefulness depends on rare adverse scenarios rather than typical samples. Standard…

The problem of constrained online convex optimization is considered, where at each round, once a learner commits to an action $x_t \in \mathcal{X} \subset \mathbb{R}^d$, a convex loss function $f_t$ and a convex constraint function $g_t$…

Quantifying abstractiveness in generated summaries is essential for evaluating summarization models beyond surface-level metrics like ROUGE. We introduce Reference Abstraction (RA), Summary Abstraction (SA), and Abstraction Ratio (AR) -- a…

On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs). However, in complex reasoning tasks, OPSD paradoxically degrades downstream performance. In this paper, we…

Graph neural networks (GNNs) are increasingly deployed in real-world applications where distribution shift is un-avoidable. However, how such shifts affect model calibration, defined as the agreement between predictive confidence and actual…

Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability. We introduce Weight-Adjusted Gradients (WAG), a simple yet effective approach for…

Reinforcement learning is usually introduced through the Bellman update, yet the equation often remains abstract to undergraduates: they watch policy arrows converge but rarely observe how each value is computed or why an action is chosen.…

Editing images with pre-trained text-to-image flow models typically requires carefully balancing target alignment with the desired prompt and source consistency with the original image. Existing approaches either rely on inversion-based…

Multimodal retrieval-augmented generation (RAG) is often evaluated with clean evidence, yet real retrieval can return topically relevant but unreliable content: false text and misleading images from corrupted metadata, entity swaps,…

Assembly action understanding is a key enabler for effective human-robot collaborative assembly, yet it remains challenging due to subtle motions and fine-grained hand-object interactions. We adapt vision-language models (VLMs) to this…

Large Vision Language Models (LVLMs) require strong reasoning over both visual and textual input. Recent work suggests that cognitive elements, especially diverse representations and metacognition, correlate with better performance. Many of…

In open-domain multi-hop question answering (QA), LLM-based search agents offer a promising approach to knowledge-intensive QA by combining retrieval with reasoning. Existing methods mainly improve open-domain multi-hop QA through reasoning…

Model stealing attacks have recently been introduced, enabling the extraction of precise information from black-box commercial language models. In this work, we propose defense methods against a recent attack of \cite{carlini2024stealing}…

Numerical integration is a cornerstone of various scientific computing applications, such as engineering simulations and model evidence computations in probabilistic machine learning. Bayesian Quadrature uses Gaussian process surrogates…

Reconstructing high-fidelity 3D scenes from sparse-views remains a central problem in generalizable neural rendering. Existing generalizable 3D Gaussian Splatting (3DGS) methods often exhibit geometric artifacts in sparse-view settings,…

Computational imaging, which recovers hidden signals from indirect, noisy measurements, underpins quantitative discovery across scientific disciplines, yet building a correct reconstruction pipeline demands deep domain expertise and remains…

Pre-Charge Half Buffer (PCHB) is a promising asynchronous digital design paradigm for harsh-environment operation; however, its soft-error characteristics remain largely unexplored. This paper presents a systematic soft-error…

The evolving realism of AI-generated Videos (AIGC-V) is rapidly rendering traditional artifact-centric detection insufficient, necessitating a paradigm shift from low-level inspection to high-level semantic verification. This paper presents…

Deploying deep learning models for automated electrocardiogram classification on resource-constrained wearable devices remains challenging due to high computational costs. To address this, we propose LSTrans, a lightweight hybrid model…

Whole-slide images (WSIs) provide rich tissue-level and cellular-level information, but storing and transmitting high-magnification pathology data is resource-intensive. Moreover, annotating WSIs at the pixel level is labor-intensive and…