34 citations · 43 across the 10 of their papers we have counts for
10 papers
Objective-Aligned Direct Answer SFT for Robust Multi-Frame Medical VQA
Site Li, Jianyi Hao, Xiaofeng Liu
Multi-frame medical VQA appears to reward increasingly complex adaptation: controller-style inference, localization-aware reranking, static hard-negative mixing, and staged continu…
Inference-Time Agentic Decision Rules Beat Longer Evolving Search for Multi-Image Medical Reasoning
Site Li, Jianyi Hao, Xiaofeng Liu
Multi-image medical VQA is not merely a prompt-length problem; it is a fundamental challenge of agentic decision-making. Medical vision-language agents must aggregate evidence acro…
5IDER: Unified Query Rewriting for Steering, Intent Carryover, Disfluencies, Entity Carryover and Repair
Jiarui Lu, Bo-Hsiang Tseng, Joel Ruben Antony Moniz +4
Providing voice assistants the ability to navigate multi-turn conversations is a challenging problem. Handling multi-turn interactions requires the system to understand various con…
Towards Modern Card Games with Large-Scale Action Spaces Through Action Representation
Zhiyuan Yao, Tianyu Shi, Site Li +5
Axie infinity is a complicated card game with a huge-scale action space. This makes it difficult to solve this challenge using generic Reinforcement Learning (RL) algorithms. We pr…
Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation
Xiaofeng Liu, Site Li, Yubin Ge +3
The unsupervised domain adaptation (UDA) has been widely adopted to alleviate the data scalability issue, while the existing works usually focus on classifying independently discre…
Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate
Xiaofeng Liu, Zhenhua Guo, Site Li +5
In this work, we propose an adversarial unsupervised domain adaptation (UDA) approach with the inherent conditional and label shifts, in which we aim to align the distributions w.r…
Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk Minimization
Yubin Ge, Site Li, Xuyang Li +4
The widely-used cross-entropy (CE) loss-based deep networks achieved significant progress w.r.t. the classification accuracy. However, the CE loss can essentially ignore the risk o…
Optimal Control-Based Baseline for Guided Exploration in Policy Gradient Methods
Xubo Lyu, Site Li, Seth Siriya +2
In this paper, a novel optimal control-based baseline function is presented for the policy gradient method in deep reinforcement learning (RL). The baseline is obtained by computin…
Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving
Xiaofeng Liu, Yimeng Zhang, Xiongchang Liu +3
Semantic segmentation is important for many real-world systems, e.g., autonomous vehicles, which predict the class of each pixel. Recently, deep networks achieved significant progr…
Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
Tong Che, Xiaofeng Liu, Site Li +4
AI Safety is a major concern in many deep learning applications such as autonomous driving. Given a trained deep learning model, an important natural problem is how to reliably ver…