activity
20212026
most citedMeta-Auxiliary Learning for Micro-Expression Recognition

5 citations · 12 across the 31 of their papers we have counts for

collaborators

31 papers

cs.MM2026

Mind the Couch! Eliciting MLLM Reasoning in Interior Design via Weak-to-Strong Task Vector Injection

Yuxuan Yang, Jingyao Wang, Luntian Mou

Multimodal Large Language Models (MLLMs) have demonstrated great performance, yet they often suffer from severe modality misalignment when confronted with densely constrained space…

math.CO2026

Inversion Diameter of Planar Graphs

Yichen Wang, Yuxuan Yang

Given an oriented graph and a subset of vertices , the \emph{inversion} of is the operation that reverses the orientation of every arc with bo…

cs.RO2026

Towards General Language-Conditioned Latent Safety Filters

Ihab Tabbara, Yuxuan Yang, Hussein Sibai

Robot policies are becoming increasingly general, with vision-language-action (VLA) models enabling a single policy to execute diverse tasks specified in natural language. Safe dep…

math.NT2026

Optimal embeddings for maximal orders of central simple algebras of degree 3 over number fields

Yuxuan Yang

Let be a central simple algebra of degree 3 over a number field and be a finite extension of degree 3. For an order of , we determine exactly when cannot b…

cs.LG2026

Evaluating Uplift Modeling under Structural Biases: Insights into Metric Stability and Model Robustness

Yuxuan Yang, Dugang Liu, Yiyan Huang

In personalized marketing, uplift models estimate the incremental effect of an intervention by modeling how customer behavior would change under alternative treatments using counte…

cs.MM2026

Design-MLLM: A Reinforcement Alignment Framework for Verifiable and Aesthetic Interior Design

Yuxuan Yang, Xiaotong Mao, Jingyao Wang

Interior design is a requirements-to-visual-plan generation process that must simultaneously satisfy verifiable spatial feasibility and comparative aesthetic preferences. While rec…

cs.RO2025

Single-View Shape Completion for Robotic Grasping in Clutter

Abhishek Kashyap, Yuxuan Yang, Henrik Andreasson +1

In vision-based robot manipulation, a single camera view can only capture one side of objects of interest, with additional occlusions in cluttered scenes further restricting visibi…

cs.LG2025

Statistically Assuring Safety of Control Systems using Ensembles of Safety Filters and Conformal Prediction

Ihab Tabbara, Yuxuan Yang, Hussein Sibai

Safety assurance is a fundamental requirement for deploying learning-enabled autonomous systems. Hamilton-Jacobi (HJ) reachability analysis is a fundamental method for formally ver…

math.NT2025

Maximal orders optimal embedding of central simple algebras over number fields

Yuxuan Yang

Given a number field and be the ring of integers of , the problem of embedding a field extension into a central simple algebra is classical. This paper proves…

cs.RO2025

Can Context Bridge the Reality Gap? Sim-to-Real Transfer of Context-Aware Policies

Marco Iannotta, Yuxuan Yang, Johannes A. Stork +2

Sim-to-real transfer remains a major challenge in reinforcement learning (RL) for robotics, as policies trained in simulation often fail to generalize to the real world due to disc…

cs.AI2025

Learning Neural Control Barrier Functions from Expert Demonstrations using Inverse Constraint Learning

Yuxuan Yang, Hussein Sibai

Safety is a fundamental requirement for autonomous systems operating in critical domains. Control barrier functions (CBFs) have been used to design safety filters that minimally al…

math.AG2025

Derived categories of generalized Kummer varieties: extended Mukai vector

Yuxuan Yang

We use the extended Mukai vectors for hyper-Kähler manifolds to investigate the derived equivalences of the hyper-Kähler manifolds which are deformation equivalent to generalized K…

cs.RO2025

Designing Latent Safety Filters using Pre-Trained Vision Models

Ihab Tabbara, Yuxuan Yang, Ahmad Hamzeh +2

Ensuring safety of vision-based control systems remains a major challenge hindering their deployment in critical settings. Safety filters have gained increased interest as effectiv…

cs.LG2025

Unsupervised Multi-Attention Meta Transformer for Rotating Machinery Fault Diagnosis

Hanyang Wang, Yuxuan Yang, Hongjun Wang +1

The intelligent fault diagnosis of rotating mechanical equipment usually requires a large amount of labeled sample data. However, in practical industrial applications, acquiring en…

cs.HC2025

Human-Machine Collaboration-Guided Space Design: Combination of Machine Learning Models and Humanistic Design Concepts

Yuxuan Yang

The integration of machine learning (ML) into spatial design holds immense potential for optimizing space utilization, enhancing functionality, and streamlining design processes. M…

math.AG2025

Lifting derived equivalences of abelian surfaces to generalized Kummer varieties

Yuxuan Yang

In this article, we study the -autoequivalences of the derived category of -equivariant objects for an abelian variety with being a finite subgrou…

cs.RO2025

The First WARA Robotics Mobile Manipulation Challenge -- Lessons Learned

David Cáceres Domínguez, Marco Iannotta, Abhishek Kashyap +21

The first WARA Robotics Mobile Manipulation Challenge, held in December 2024 at ABB Corporate Research in Västerås, Sweden, addressed the automation of task-intensive and repetitiv…

math.CO2025

The minimum edge-pancyclic graph of a given order

Xiamiao Zhao, Yuxuan Yang

A graph of order is called edge-pancyclic if, for every integer with , every edge of lies in a cycle of length . Determining the minimum size $f…

cs.CV2024★ 1 cited

Spatio-Temporal Fuzzy-oriented Multi-Modal Meta-Learning for Fine-grained Emotion Recognition

Jingyao Wang, Wenwen Qiang, Changwen Zheng +1

Fine-grained emotion recognition (FER) plays a vital role in various fields, such as disease diagnosis, personalized recommendations, and multimedia mining. However, existing FER m…

cs.CV2024★ 2 cited

DiffDesign: Controllable Diffusion with Meta Prior for Efficient Interior Design Generation

Yuxuan Yang, Tao Geng

Interior design is a complex and creative discipline involving aesthetics, functionality, ergonomics, and materials science. Effective solutions must meet diverse requirements, typ…

cs.CV2024

Pre-Trained Vision Models as Perception Backbones for Safety Filters in Autonomous Driving

Yuxuan Yang, Hussein Sibai

End-to-end vision-based autonomous driving has achieved impressive success, but safety remains a major concern. The safe control problem has been addressed in low-dimensional setti…

math.GT2024★ 1 cited

On the Volume Conjecture for hyperbolic Dehn-filled 3-manifolds along the twist knots

Huabin Ge, Yunpeng Meng, Chuwen Wang +1

For a twist knot , let be the closed -manifold obtained by doing Dehn-filling along . In this article, we prove that Chen-Yang's…

math.CO2024

Inversion diameter and treewidth

Yichen Wang, Haozhe Wang, Yuxuan Yang +1

In an oriented graph , the inversion of a subset of vertices is the operation that reverses the orientation of all arcs with both end-vertices in . The i…

math.CO2024★ 1 cited

The inversion number of dijoins and blow-up digraphs

Haozhe Wang, Yuxuan Yang, Mei Lu

For an oriented graph , the of in is the digraph obtained from by reversing the direction of all arcs with both ends in . The inversion…