Self-Supervised 3D Face Reconstruction via Conditional Estimation

Yandong Wen, Weiyang Liu, Bhiksha Raj +1

Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence

Xiang Bai, Hanchen Wang, Liya Ma +43

Nonparametric Iterative Machine Teaching

Chen Zhang, Xiaofeng Cao, Weiyang Liu +2

Structured Occlusion Coding for Robust Face Recognition

Yandong Wen, Weiyang Liu, Meng Yang +3

Generating Symbolic World Models via Test-time Scaling of Large Language Models

Zhouliang Yu, Yuhuan Yuan, Tim Z. Xiao +5

Meta Architecture Search

Albert Shaw, Wei Wei, Weiyang Liu +2

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization

Weiyang Liu, Zeju Qiu, Yao Feng +11

Manifold-Constrained Nucleus-Level Denoising Diffusion Model for Structure-Based Drug Design

Shengchao Liu, Divin Yan, Weitao Du +6

JWST Insights into Narrow-line Little Red Dots

Zijian Zhang, Linhua Jiang, Weiyang Liu +2

Deep Hyperspherical Learning

Weiyang Liu, Yan-Ming Zhang, Xingguo Li +4

Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling

Tim Z. Xiao, Johannes Zenn, Zhen Liu +3

Neural Similarity Learning

Weiyang Liu, Zhen Liu, James M. Rehg +1

SphereFace2: Binary Classification is All You Need for Deep Face Recognition

Yandong Wen, Weiyang Liu, Adrian Weller +2

Iterative Machine Teaching

Weiyang Liu, Bo Dai, Ahmad Humayun +5

A Portrait of the Cosmic Reionisation History in the Context of the Early Dark Energy Model

Weiyang Liu, Xin Wang, Hu Zhan +3

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Longhui Yu, Weisen Jiang, Han Shi +7

Suppressing Coherent Two-Qubit Errors via Dynamical Decoupling

Jiawei Qiu, Yuxuan Zhou, Chang-Kang Hu +21

CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection

Xinlin Zhuang, Yichen Li, Xiwei Liu +11

Iterative Teaching by Data Hallucination

Zeju Qiu, Weiyang Liu, Tim Z. Xiao +5

Large-Margin Softmax Loss for Convolutional Neural Networks

Weiyang Liu, Yandong Wen, Zhiding Yu +1

Data-Efficient Learning via Minimizing Hyperspherical Energy

Xiaofeng Cao, Weiyang Liu, Ivor W. Tsang

Efficient Implementation of Arbitrary Two-Qubit Gates via Unified Control

Zhen Chen, Weiyang Liu, Yanjun Ma +16

Towards Principled Disentanglement for Domain Generalization

Hanlin Zhang, Yi-Fan Zhang, Weiyang Liu +3

Simultaneous Edge Alignment and Learning

Zhiding Yu, Weiyang Liu, Yang Zou +4

ChatHuman: Chatting about 3D Humans with Tools

Jing Lin, Yao Feng, Weiyang Liu +1

Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles

Zhanghan Ni, Yanjing Li, Zeju Qiu +4

Continual Learning by Modeling Intra-Class Variation

Longhui Yu, Tianyang Hu, Lanqing Hong +3

The Magellan M2FS spectroscopic survey of high-redshift galaxies: the brightest Lyman-break galaxies at $z \sim 6$

Shuqi Fu, Linhua Jiang, Yuanhang Ning +2

On the Effect of Sampling Diversity in Scaling LLM Inference

Tianchun Wang, Zichuan Liu, Yuanzhou Chen +5

Additive Margin Softmax for Face Verification

Feng Wang, Weiyang Liu, Haijun Liu +1

Regularizing Neural Networks via Minimizing Hyperspherical Energy

Rongmei Lin, Weiyang Liu, Zhen Liu +5

Jointly Learning Non-negative Projection and Dictionary with Discriminative Graph Constraints for Classification

Weiyang Liu, Zhiding Yu, Yandong Wen +2

Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning

Yuhuan Yuan, Zhouliang Yu, Minghao Liu +2

Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets

Zhen Liu, Tim Z. Xiao, Weiyang Liu +2

Ghost on the Shell: An Expressive Representation of General 3D Shapes

Zhen Liu, Yao Feng, Yuliang Xiu +4

POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation

Zeju Qiu, Lixin Liu, Adrian Weller +2

Reparameterized LLM Training via Orthogonal Equivalence Transformation

Zeju Qiu, Simon Buchholz, Tim Z. Xiao +3

Nonparametric Teaching for Multiple Learners

Chen Zhang, Xiaofeng Cao, Weiyang Liu +2

Vacuum-gap transmon qubits realized using flip-chip technology

Xuegang Li, Yingshan Zhang, Chuhong Yang +26

Human-in-the-Loop Mixup

Katherine M. Collins, Umang Bhatt, Weiyang Liu +4

Transmon qubit with relaxation time exceeding 0.5 milliseconds

Chenlu Wang, Xuegang Li, Huikai Xu +25

Rethinking Easy-to-Hard: Limits of Curriculum Learning in Post-Training for Deductive Reasoning

Maximilian Mordig, Andreas Opedal, Weiyang Liu +1

Orthogonal Model Merging

Sihan Yang, Kexuan Shi, Weiyang Liu

Can Early Dark Energy be Probed by the High-Redshift Galaxy Abundance?

Weiyang Liu, Hu Zhan, Yan Gong +1

FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models

Zhouliang Yu, Ruotian Peng, Keyi Ding +10

Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector

Andi Zhang, Tim Z. Xiao, Weiyang Liu +2

Efficient Face Alignment via Locality-constrained Representation for Robust Recognition

Yandong Wen, Weiyang Liu, Meng Yang +1

Learning Disentangled Avatars with Hybrid 3D Representations

Yao Feng, Weiyang Liu, Timo Bolkart +3

Angular Visual Hardness

Beidi Chen, Weiyang Liu, Zhiding Yu +4

Robust Elastic Net Regression

Weiyang Liu, Rongmei Lin, Meng Yang

Pre-training Molecular Graph Representation with 3D Geometry

Shengchao Liu, Hanchen Wang, Weiyang Liu +3

Learning with Hyperspherical Uniformity

Weiyang Liu, Rongmei Lin, Zhen Liu +3

Performing SU($d$) operations and rudimentary algorithms in a superconducting transmon qudit for $d=3$ and $d=4$

Pei Liu, Ruixia Wang, Jing-Ning Zhang +11

Agentic Design of Compositional Machines

Wenqian Zhang, Weiyang Liu, Zhen Liu

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

Zeju Qiu, Weiyang Liu, Haiwen Feng +6

One-shot Implicit Animatable Avatars with Model-based Priors

Yangyi Huang, Hongwei Yi, Weiyang Liu +6

Iterative Graph Self-Distillation

Hanlin Zhang, Shuai Lin, Weiyang Liu +4

PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective

Yangyi Huang, Ruotian Peng, Zeju Qiu +4

SphereFace Revived: Unifying Hyperspherical Face Recognition

Weiyang Liu, Yandong Wen, Bhiksha Raj +2

Provable Lifelong Learning of Representations

Xinyuan Cao, Weiyang Liu, Santosh S. Vempala

Disjoint Mapping Network for Cross-modal Matching of Voices and Faces

Yandong Wen, Mahmoud Al Ismail, Weiyang Liu +2

Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering

Xianliang Li, Zihan Zhang, Weiyang Liu +1

Learning towards Minimum Hyperspherical Energy

Weiyang Liu, Rongmei Lin, Zhen Liu +4

Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision

Zhiqing Sun, Longhui Yu, Yikang Shen +4

Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation

Kexuan Shi, Hanxuan Li, Zeju Qiu +3

Structural Causal 3D Reconstruction

Weiyang Liu, Zhen Liu, Liam Paull +2

SphereFace: Deep Hypersphere Embedding for Face Recognition

Weiyang Liu, Yandong Wen, Zhiding Yu +3

Error per single-qubit gate below $10^{-4}$ in a superconducting qubit

Zhiyuan Li, Pei Liu, Peng Zhao +10

Orthogonal Over-Parameterized Training

Weiyang Liu, Rongmei Lin, Zhen Liu +5

Explanation of high redshift luminous galaxies from JWST by early dark energy model

Jun-Qian Jiang, Weiyang Liu, Hu Zhan +1

Realisation of adiabatic and diabatic CZ gates in superconducting qubits coupled with a tunable coupler

Huikai Xu, Weiyang Liu, Zhiyuan Li +11

AGN ruled out as the dominant source of cosmic reionization

Danyang Jiang, Linhua Jiang, Shengxiu Sun +2

Vibe Calibration: Autonomous Bring-up of a 112-Qubit Superconducting Quantum Processor by a Skill-Orchestrating Language Agent

Huikai Xu, Jiaxiu Han, Shigang Ou +11

Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation

Yao Teng, Fuyun Wang, Xian Liu +7

Can Large Language Models Understand Symbolic Graphics Programs?

Zeju Qiu, Weiyang Liu, Haiwen Feng +7

Analysis of Multi-epoch JWST Images of $\sim 300$ Little Red Dots: Tentative Detection of Variability in a Minority of Sources

Zijian Zhang, Linhua Jiang, Weiyang Liu +1

VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models

Muchao Ye, Weiyang Liu, Pan He

SymbOmni: Evolving Agentic Omni Models via Symbolic Concept Learning

Jinxiu Liu, Jianru Li, Tanqing Kuang +4

The paper introduces SymbOmni, an agentic omni-model for visual generation that uses a symbolic concept memory to continuously learn and compose reusable instructions, enabling con…

Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap

Weiyang Liu, Longhui Yu, Adrian Weller +1

AMO: Adaptive Muon Orthogonalization

Xinlin Zhuang, Panyi Ouyang, Yichen Li +7

Streaming Autoregressive Video Generation via Diagonal Distillation

Jinxiu Liu, Xuanming Liu, Kangfu Mei +3

Symbolic Graphics Programming with Large Language Models

Yamei Chen, Haoquan Zhang, Yangyi Huang +4

Re-Thinking Inverse Graphics With Large Language Models

Peter Kulits, Haiwen Feng, Weiyang Liu +2

A high rate of foreground contaminants toward high-redshift galaxies resolved by JWST

Weiyang Liu, Linhua Jiang

Verbalized Machine Learning: Revisiting Machine Learning with Language Models

Tim Z. Xiao, Robert Bamler, Bernhard Schölkopf +1

Model Merging with Functional Dual Anchors

Kexuan Shi, Yandong Wen, Weiyang Liu

Towards Black-box Iterative Machine Teaching

Weiyang Liu, Bo Dai, Xingguo Li +3

Decoupled Networks

Weiyang Liu, Zhen Liu, Zhiding Yu +5

GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs

Gege Gao, Weiyang Liu, Anpei Chen +2

SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator

Guoxuan Chen, Han Shi, Jiawei Li +7

KCRC-LCD: Discriminative Kernel Collaborative Representation with Locality Constrained Dictionary for Visual Categorization

Weiyang Liu, Zhiding Yu, Lijia Lu +3

Iterative Learning with Open-set Noisy Labels

Yisen Wang, Weiyang Liu, Xingjun Ma +4

Mapping Topology-Localization Phase Diagram with Quasiperiodic Disorder Using a Programmable Superconducting Simulator

Xuegang Li, Huikai Xu, Junhua Wang +23

Pairwise Similarity Learning is SimPLE

Yandong Wen, Weiyang Liu, Yao Feng +5

A spectroscopic survey of Ly$α$ emitters and Ly$α$ luminosity function at Redshifts 3.7 and 4.8

Weiyang Liu, Linhua Jiang

MeshDiffusion: Score-based Generative 3D Mesh Modeling

Zhen Liu, Yao Feng, Michael J. Black +3

Representational Alignment Supports Effective Machine Teaching

Ilia Sucholutsky, Katherine M. Collins, Maya Malaviya +11

Quantum Control via Stimulated Raman User-defined Passage

Jingjing Niu, Bao-Jie Liu, Yuxuan Zhou +9

Beyond the Sampled Token: Preserving Candidate Support in RLVR

Ruotian Peng, Yi Ren, Zhouliang Yu +2

Realizing discrete time crystal in an one-dimensional superconducting qubit chain

Huikai Xu, Jingning Zhang, Jiaxiu Han +5