Institution profile

Case Western Reserve University

Academic institutionnorthamerica · us
Official website
Research library334linked papers
Opportunities0open roles
Selected work

Representative Papers

Topic-Based Watermarks for Large Language Models

Apr 02, 2024

To address the risks of misuse and data contamination arising from the difficulty of tracing LLM-generated text, existing watermarking methods struggle to balance robustness, generation quality, and deployment overhead. This paper proposes a lightweight, topic-guided watermarking scheme: it dynamically constructs a semantically aligned “green list” vocabulary via topic modeling and embeds detectable signatures solely through probability-biased sampling during standard autoregressive decoding—requiring no model architecture modification or dedicated framework. Its core innovation is the first-ever topic-aware dynamic green list mechanism. Experiments across multiple LLMs show that the method achieves perplexity on par with SynthID-Text, improves watermark detection accuracy by 12.7%, significantly enhances resilience against paraphrasing attacks (failure rate <8%), and incurs negligible inference overhead.

4 citationsRead paper

Trust The Typical

Feb 04, 2026

This work addresses the limitations of existing safety mechanisms in large language models, which rely on known threat detection and suffer from high false-positive rates and vulnerability to attacks. The authors propose modeling safety alignment as an out-of-distribution detection problem in semantic space, learning the typical distribution of benign prompts without requiring harmful examples. This approach enables generalizable, cross-domain, and multilingual protection. By integrating semantic space modeling, GPU-optimized inference, and real-time guardrailing within the vLLM framework, the method achieves state-of-the-art performance across 18 safety benchmarks, reduces false positives by up to 40×, supports over 14 languages, and incurs less than 6% inference overhead.

1 citationsRead paper

Fully Kolmogorov-Arnold Deep Model in Medical Image Segmentation

Feb 03, 2026

This work proposes ALL U-KAN, the first fully Kolmogorov–Arnold (KA)-based deep architecture for medical image segmentation, addressing the challenges of training instability and excessive GPU memory consumption that have hindered the application of deep KA networks in this domain. By entirely replacing conventional fully connected and convolutional layers with KA layers and KAonv layers, respectively, the model leverages the expressive power of KA representations. To enhance scalability, the authors introduce a Share-activation KAN to reduce parameterization complexity and design a gradient-free spline mechanism that drastically lowers both memory footprint and computational cost. Evaluated on three medical image segmentation benchmarks, ALL U-KAN achieves superior segmentation accuracy while using 10× fewer parameters and consuming over 20× less GPU memory compared to existing partial KA and traditional architectures.

1 citationsRead paper

UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving

Jan 07, 2026arXiv.org

This work proposes the first unified architecture for autonomous driving that integrates vision-language model (VLM)-driven scene understanding, trajectory planning, and conditional future image generation within a single end-to-end framework. By jointly training these components and enabling closed-loop iterative refinement, the system achieves holistic performance improvements over conventional modular pipelines that treat perception, prediction, and planning as separate stages. A key innovation lies in introducing trajectory-conditioned image generation, which allows explicit coupling between planned actions and anticipated visual futures. The study also provides a systematic comparison of discrete versus continuous representations for future prediction and their impact on driving behavior. Evaluated on the Bench2Drive benchmark, the method reduces L2 trajectory error by 5.9% and collision rate by 9.2% while generating high-fidelity future images, significantly outperforming current state-of-the-art approaches.

1 citationsRead paper

Imaging foundation model for universal enhancement of non-ideal measurement CT

Oct 02, 2024arXiv.org

Non-ideal computed tomography (NICT)—characterized by suboptimal acquisition protocols—suffers from degraded image quality and low clinical acceptance, while existing deep learning methods rely heavily on large-scale annotated datasets and exhibit poor generalizability. To address these challenges, we propose TAMP, the first foundation model tailored for NICT. Its core contributions are: (1) a multi-scale integrated Transformer amplifier that jointly incorporates physical priors and data-driven modeling; (2) a physics-informed large-scale synthetic pretraining paradigm, leveraging 10.8 million simulated scans to learn robust representations across diverse protocols, anatomical regions, and noise levels; and (3) parameter-efficient fine-tuning via LoRA-style adaptation requiring only a few slices. Extensive evaluation demonstrates significant PSNR/SSIM improvements across multiple NICT tasks. Clinical validation—including radiologist-blinded assessment and real-world deployment—confirms markedly enhanced diagnostic acceptability, underscoring TAMP’s readiness for clinical translation.

1 citationsRead paper
Recent publications

Latest Papers