Han Zhou

The paper introduces PassNet, a large-scale ecosystem for generating compiler passes using LLMs, demonstrating that LLMs can significantly accelerate graph compilation for long-tail workloads, suggesting that consistency is the primary bottleneck.

The paper introduces AMix-2, a novel protein-text foundation model that unifies protein understanding and sequence design by embedding both modalities in a shared token space, achieving state-of-the-art performance on comprehensive benchmarks.

FlowTime proposes a novel Continuous Generative Regression framework using a Flow-based Personalized Prior to accurately model the multimodal and heterogeneous nature of user watch time prediction, significantly outperforming existing state-of-the-art methods.

The paper establishes that finding approximate Hylland-Zeckhauser equilibria (a type of market allocation) is computationally hard, specifically showing it is PPAD-hard under certain complexity assumptions.

The paper proposes RPCASSM, a novel state space model leveraging Robust PCA (RPCA) to accurately detect and segment infrared small targets by separately modeling background and target information based on their unique spatial properties.

AutoACSL is a framework that uses Code Property Graphs and large language models to generate formal specifications for C programs with improved success ratio and full proof ratio.

Introduce PerceptionRubrics, a rubric-based evaluation framework for addressing real-world brittleness of models using 1,038 images and over 12,000 instance-specific rubrics.

The paper introduces MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal Language Models with an executable mechanism for mental visualization using SVG graphics.