Joshua Liu

Wesley Chen, Andrew Edgley, Raunak Hota et al.

In recent years, supervised learning has become the dominant paradigm for training deep-learning based methods for 3D object detection. Lately, the academic community has studied 3D object detection in the context of autonomous vehicles (AVs) using publicly available datasets such as nuScenes and Argoverse 2.0. However, these datasets may have incomplete annotations, often only labeling a small subset of objects in a scene. Although commercial services exists for 3D bounding box annotation, these are often prohibitively expensive. To address these limitations, we propose ReBound, an open-source 3D visualization and dataset re-annotation tool that works across different datasets. In this paper, we detail the design of our tool and present survey results that highlight the usability of our software. Further, we show that ReBound is effective for exploratory data analysis and can facilitate active-learning. Our code and documentation is available at https://github.com/ajedgley/ReBound

Joshua Liu, Aarav Jain, Soham Takuri et al.

Rapid improvements in large language models have unveiled a critical challenge in human-AI interaction: sycophancy. In this context, sycophancy refers to the tendency of models to excessively agree with or flatter users, often at the expense of factual accuracy. While previous studies have primarily analyzed this behavior in single-turn interactions, its persistence and evolution in multi-step conversations remain largely unexplored. We introduce TRUTH DECAY, a benchmark specifically designed to evaluate sycophancy in extended dialogues, where language models must navigate iterative user feedback, challenges, and persuasion. We prompt models to elicit four types of sycophantic biases. We then propose and test sycophancy reduction strategies, evaluating their effectiveness beyond single-step interactions.

Wanghao Ye, Sihan Chen, Yiting Wang et al.

We present an LLM-powered social discovery platform that uses digital twins to autonomously evaluate interpersonal compatibility through behavioral simulation. The platform unifies three key pillars: (1) digital twins that engage in autonomous multi-turn conversations on behalf of users to estimate compatibility, (2) gamified territory conquest mechanics that incentivize real-world exploration and create organic settings for in-person encounters, and (3) AI companions that preserve persistent shared memory across devices. Built upon CogniPair's cognitive architecture (Ye et al., 2026), validated on the Columbia Speed Dating dataset (551 participants), our system extends prior simulation-only matching into a fully deployed social discovery environment. Through deployment, we derive empirical cost-quality baselines and identify fundamental scaling bottlenecks that remain hidden in component-level testing alone.

Shahriar Kabir Nahin, Wenxiao Xiao, Joshua Liu et al.

Data-centric learning seeks to improve model performance from the perspective of data quality, and has been drawing increasing attention in the machine learning community. Among its key tools, influence functions provide a powerful framework to quantify the impact of individual training samples on model predictions, enabling practitioners to identify detrimental samples and retrain models on a cleaner dataset for improved performance. However, most existing work focuses on the question: "what data benefits the learning model?" In this paper, we take a step further and investigate a more fundamental question: "what is the performance ceiling of the learning model?" Unlike prior studies that primarily measure improvement through overall accuracy, we emphasize category-wise accuracy and aim for Pareto improvements, ensuring that every class benefits, rather than allowing tradeoffs where some classes improve at the expense of others. To address this challenge, we propose category-wise influence functions and introduce an influence vector that quantifies the impact of each training sample across all categories. Leveraging these influence vectors, we develop a principled criterion to determine whether a model can still be improved, and further design a linear programming-based sample reweighting framework to achieve Pareto performance improvements. Through extensive experiments on synthetic datasets, vision, and text benchmarks, we demonstrate the effectiveness of our approach in estimating and achieving a model's performance improvement across multiple categories of interest.

Wei-Lun Huang, Joshua Liu, Davood Tashayyod et al.

Total Body Photography (TBP) is becoming a useful screening tool for patients at high risk for skin cancer. While much progress has been made, existing TBP systems can be further improved for automatic detection and analysis of suspicious skin lesions, which is in part related to the resolution and sharpness of acquired images. This paper proposes a novel shape-aware TBP system automatically capturing full-body images while optimizing image quality in terms of resolution and sharpness over the body surface. The system uses depth and RGB cameras mounted on a 360-degree rotary beam, along with 3D body shape estimation and an in-focus surface optimization method to select the optimal focus distance for each camera pose. This allows for optimizing the focused coverage over the complex 3D geometry of the human body given the calibrated camera poses. We evaluate the effectiveness of the system in capturing high-fidelity body images. The proposed system achieves an average resolution of 0.068 mm/pixel and 0.0566 mm/pixel with approximately 85% and 95% of surface area in-focus, evaluated on simulation data of diverse body shapes and poses as well as a real scan of a mannequin respectively. Furthermore, the proposed shape-aware focus method outperforms existing focus protocols (e.g. auto-focus). We believe the high-fidelity imaging enabled by the proposed system will improve automated skin lesion analysis for skin cancer screening.