Bo Liu

RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons

Runyu Wang, Bo Liu, Xiaxin Zhang, et al.

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Bo Liu, Simon Yu, Yiding Jiang, et al.

GeoCache: Training-Free Acceleration of Multi-View Texture Diffusion via Geometric Delta Transport

Haotang Li, Zhenyu Qi, Shaohan Henry Wang, et al.

EchoBridge: Long-Tail-Aware ECG-Echocardiography Text Alignment for Echocardiography-Derived Cardiac Findings

Xiaocheng Fang, Jieyi Cai, Guangkun Nie, et al.

Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning

Pengxin Wang, Lihao Guo, Yi Xie, et al.

ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking

Jiawei Ge, Xintian Zhang, Jiuxin Cao, et al.

A Brain-Inspired Deep Separation Network for Single Channel Raman Spectra Unmixing

Gaoruishu Long, Jinchao Liu, Bo Liu, et al.

From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space

Yuqiao Tan, Minzheng Wang, Bo Liu, et al.

EndoVGGT: GNN-Enhanced Depth Estimation for Surgical 3D Reconstruction

Falong Fan, Yi Xie, Arnis Lektauers, et al.

Gumbel Distillation for Parallel Text Generation

Chi Zhang, Xixi Hu, Bo Liu, et al.

Reasoning over mathematical objects: on-policy reward modeling and test time aggregation

Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim, et al.

This paper tackles how AI language models can better solve complex math and science problems that require deriving formally structured mathematical expressions (like equations or proofs) rather than just picking a number or multiple choice answer. The researchers created a new training dataset called Principia, developed improved training methods using AI judges that learn during training, and showed how to use extra computation at test time to aggregate multiple solution attempts for better results.