Publications (37)
Quantum Circuit Synthesis and Compilation Optimization: Overview and Prospects
Ge Yan, Wenjie Wu, Yuheng Chen +6
Quantum computing is a promising paradigm that may overcome the current computational power bottlenecks. The increasing maturity of quantum processors provides more possibilities f…
Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulation
Yuelei Li, Ge Yan, Annabella Macaluso +3
The recent advancements in visual reasoning capabilities of large multimodal models (LMMs) and the semantic enrichment of 3D feature fields have expanded the horizons of robotic ca…
Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
Tuomas Oikarinen, Ge Yan, Tsui-Wei Weng
Understanding the function of individual units in a neural network is an important building block for mechanistic interpretability. This is often done by generating a simple text e…
Entropy-stable discontinuous Galerkin difference methods for hyperbolic conservation laws
Ge Yan, Sharanjeet Kaur, Jeffery W. Banks +1
The paper describes the construction of entropy-stable discontinuous Galerkin difference (DGD) discretizations for hyperbolic conservation laws on unstructured grids. The construct…
ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability
Chung-En Sun, Ge Yan, Akshay Kulkarni +1
Recent advances in long chain-of-thought (CoT) reasoning have largely prioritized answer accuracy and token efficiency, while overlooking aspects critical to trustworthiness. We ar…
Efficient foundation decoders for fault-tolerant quantum computing
Ge Yan, Shanchuan Li, Shiyi Xiao +4
Foundation decoders, a class of high-capacity neural decoders, are leading candidates for fault-tolerant quantum computing, with accurate and efficient decoding at large code dista…
ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
Chung-En Sun, Ge Yan, Tsui-Wei Weng
Recent studies have shown that Large Language Models (LLMs) augmented with chain-of-thought (CoT) reasoning demonstrate impressive problem-solving abilities. However, in this work,…
Movable and Reconfigurable Antennas for 6G: Unlocking Electromagnetic-Domain Design and Optimization
Lipeng Zhu, Haobin Mao, Ge Yan +3
The growing demands of 6G mobile communication networks necessitate advanced antenna technologies. Movable antennas (MAs) and reconfigurable antennas (RAs) enable dynamic control o…
Channel Autocorrelation Estimation for IRS-Aided Wireless Communications Based on Power Measurements
Ge Yan, Lipeng Zhu, Rui Zhang
Intelligent reflecting surface (IRS) can bring significant performance enhancement for wireless communication systems by reconfiguring wireless channels via passive signal reflecti…
Provably Robust Conformal Prediction with Improved Efficiency
Ge Yan, Yaniv Romano, Tsui-Wei Weng
Conformal prediction is a powerful tool to generate uncertainty sets with guaranteed coverage using any predictive model, under the assumption that the training and test data are i…
Universal 2-Local Symmetry-Preserving Quantum Neural Networks for Fermionic Systems
Ge Yan, Kaisen Pan, Ruocheng Wang +3
Simulating quantum many-body systems represents a fundamental challenge where classical machine learning methods are severely bottlenecked by the exponential curse of dimensionalit…
Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability
Tuomas Oikarinen, Ge Yan, Akshay Kulkarni +1
Interpreting individual neurons or directions in activation space is an important topic in mechanistic interpretability. Numerous automated interpretability methods have been propo…
Power Measurement Enabled Channel Autocorrelation Matrix Estimation for IRS-Assisted Wireless Communication
Ge Yan, Lipeng Zhu, Rui Zhang
By reconfiguring wireless channels via passive signal reflection, intelligent reflecting surface (IRS) can bring significant performance enhancement for wireless communication syst…
VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
Divyansh Srivastava, Ge Yan, Tsui-Wei Weng
Concept Bottleneck Models (CBMs) provide interpretable prediction by introducing an intermediate Concept Bottleneck Layer (CBL), which encodes human-understandable concepts to expl…
ReflCtrl: Controlling LLM Reflection via Representation Engineering
Ge Yan, Chung-En Sun, Tsui-Wei +1
Large language models (LLMs) with Chain-of-Thought (CoT) reasoning have achieved strong performance across diverse tasks, including mathematics, coding, and general reasoning. A di…
LLM Agents Already Know When to Call Tools -- Even Without Reasoning
Chung-En Sun, Linbo Liu, Ge Yan +2
Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark…
Constructing stable, high-order finite-difference operators on point clouds over complex geometries
Jason Hicken, Ge Yan, Sharanjeet Kaur
High-order difference operators with the summation-by-parts (SBP) property can be used to build stable discretizations of hyperbolic conservation laws; however, most high-order SBP…
Slow Movable Antenna System Design Based on Cell-Specific Long-Term Angular Power Spectrum
Ge Yan, Lipeng Zhu, Wenyan Ma +1
Movable antenna (MA) has recently emerged as a promising paradigm for enhancing wireless communication performance by exploiting spatial degrees of freedom through flexible antenna…
On Reducing the Execution Latency of Superconducting Quantum Processors via Quantum Job Scheduling
Wenjie Wu, Yiquan Wang, Ge Yan +3
Quantum computing has gained considerable attention, especially after the arrival of the Noisy Intermediate-Scale Quantum (NISQ) era. Quantum processors and cloud services have bee…
DNAct: Diffusion Guided Multi-Task 3D Policy Learning
Ge Yan, Yueh-Hua Wu, Xiaolong Wang
This paper presents DNAct, a language-conditioned multi-task policy framework that integrates neural rendering pre-training and diffusion training to enforce multi-modality learnin…
Humanoid Policy ~ Human Policy
Ri-Zhao Qiu, Shiqi Yang, Xuxin Cheng +12
Training manipulation policies for humanoid robots with diverse data enhances their robustness and generalization across tasks and platforms. However, learning solely from robot de…
Steer2Edit: From Activation Steering to Component-Level Editing
Chung-En Sun, Ge Yan, Zimo Wang +1
Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation…
SciDA: Scientific Dynamic Assessor of LLMs
Junting Zhou, Tingjia Miao, Yiyan Liao +15
Advancement in Large Language Models (LLMs) reasoning capabilities enables them to solve scientific problems with enhanced efficacy. Thereby, a high-quality benchmark for comprehen…
RAT: Boosting Misclassification Detection Ability without Extra Data
Ge Yan, Tsui-Wei Weng
As deep neural networks(DNN) become increasingly prevalent, particularly in high-stakes areas such as autonomous driving and healthcare, the ability to detect incorrect predictions…
Movable Antenna Aided Multiuser Communications: Antenna Position Optimization Based on Statistical Channel Information
Ge Yan, Lipeng Zhu, Rui Zhang
The movable antenna (MA) technology has attracted great attention recently due to its promising capability in improving wireless channel conditions by flexibly adjusting antenna po…
Wideband Coverage Enhancement for IRS-Aided Wireless Networks Based on Power Measurement
Ge Yan, Lipeng Zhu, He Sun +1
By applying tunable phase shifts to incident waves via passive signal reflection, intelligent reflecting surface (IRS) can offer significant performance improvement for wireless co…
Maximum Likelihood Decoding of Quantum Error Correction Codes
Hanyan Cao, Ge Yan, Yuxuan Du +1
Quantum error correction (QEC) is indispensable for realizing fault-tolerant quantum computation, yet its effectiveness hinges critically on the classical decoding algorithm that i…
Multimodal Concept Bottleneck Models
Tongqing Shi, Ge Yan, Tuomas Oikarinen +1
Concept Bottleneck Models (CBMs) enhance the interpretability of deep learning networks by aligning the features extracted from images with natural concepts. However, existing CBMs…
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Embodiment Collaboration, Abby O'Neill, Abdul Rehman +291
Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, thi…
Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability
Ge Yan, Tuomas Oikarinen, Tsui-Wei +1
Neuron identification is a popular tool in mechanistic interpretability, aiming to uncover the human-interpretable concepts represented by individual neurons in deep networks. Whil…
GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields
Yanjie Ze, Ge Yan, Yueh-Hua Wu +6
It is a long-standing problem in robotics to develop agents capable of executing diverse manipulation tasks from visual observations in unstructured real-world environments. To ach…
ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training
Ge Yan, Jiyue Zhu, Yuquan Deng +8
This paper introduces ManiFlow, a visuomotor imitation learning policy for general robot manipulation that generates precise, high-dimensional actions conditioned on diverse visual…
Interpretable Generative Models through Post-hoc Concept Bottlenecks
Akshay Kulkarni, Ge Yan, Chung-En Sun +2
Concept bottleneck models (CBM) aim to produce inherently interpretable models that rely on human-understandable concepts for their predictions. However, existing approaches to des…
Sample-efficient quantum error mitigation via classical learning surrogates
Wei-You Liao, Ge Yan, Yujin Song +5
The pursuit of practical quantum utility on near-term quantum processors is critically challenged by their inherent noise. Quantum error mitigation (QEM) techniques are leading sol…
Rethink the Role of Neural Decoders in Quantum Error Correction
Ge Yan, Shanchuan Li, Yuxuan Du
Quantum error correction (QEC) is essential for enabling quantum advantages, with decoding as a central algorithmic primitive. Owing to its importance and intrinsic difficulty, sub…
Distance Marching for Generative Modeling
Zimo Wang, Ishit Mehta, Haolin Lu +4
Time-unconditional generative models learn time-independent denoising vector fields. But without time conditioning, the same noisy input may correspond to multiple noise levels and…
OmniQEC: discovering practical quantum error-correcting codes by an AI scientist
Ge Yan, Shanchuan Li, Pengyue Ma +5
Quantum error correction (QEC) is indispensable for scalable fault-tolerant quantum computing. However, discovering QEC codes that remain effective is challenging, as logical perfo…