49 citations · 78 across the 25 of their papers we have counts for
30 papers
SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise
Xupeng Chen, Chenqian Le, Jiayi Cheng +2
A model diff credits post-training with whatever separates a base checkpoint from one post-trained descendant, presuming a rerun would land close by. On the sparse co-activation gr…
Suggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gate
Xupeng Chen, Chenqian Le
Long-term memory for assistants needs a gate that decides when a new utterance retires an old stored claim. Benchmark labels for this step mark a pair as changed or not, so they ca…
Scoring Explanations Without Reading Them: Structural Shortcuts in Automated-Interpretability Evaluation Data
Xupeng Chen
Automated interpretability scores an explanation of a sparse-autoencoder (SAE) feature by asking a model to predict, token by token, where the feature fires on evaluation examples…
Multi-Subject Pretraining Enables Short-Calibration Personalization for Closed-Corpus Surface EMG Speech Decoding
Chenqian Le, Beatrice Fumagalli, Yasamin Esmaeili +5
Surface electromyography (sEMG)-based silent speech interfaces are limited by cross-user variability and calibration burden. We study a limited-data setting in which each of 27 spe…
Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence
Chenqian Le, Jiayi Cheng, Qijia He +3
Recent systems train coding agents with reinforcement learning (RL) on trajectories collected through multiple execution harnesses. However, gains under the training harnesses leav…
MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations
Sky Ng, Brihi Joshi, Ishan Gupta +47
Long-horizon, multi-agent language model (LM) simulations are widely proposed for studying social behavior, yet instruments to measure whether persona-conditioned agents maintain i…
PersonaEval: Persona-Based User Simulation for Evaluating Interactive Applications
Yifan Simon Liu, Qianfeng Wen, Yilan Fan +40
Real user studies are important for understanding how people interact with systems under test or already deployed. In practice, however, they are often costly, time-consuming, and…
CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents
Qijia He, Jiayi Cheng, Chenqian Le +8
Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect answer. Existing cost-aware system…
PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention
Zhengtao Yao, Runhao Li, Xupeng Chen +12
Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretr…
Less Data, Better Alignment: Data-Centric Multi-Evaluator Agreement for Preference Optimization
Zhengtao Yao, Runhao Li, Xupeng Chen +12
Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence set of on-policy responses can…
MindAdapter: Few-Shot Parameter-Efficient Residual Calibration of Cross-Subject Brain-to-Visual Decoding Models
Jiaxiang Liu, Jiawei Du, Xupeng Chen +4
Cross-subject brain-to-visual decoding remains a core challenge in brain-computer interfaces due to severe inter-individual variability that induces systematic subject-specific fun…
Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering
Xupeng Chen, Binbin Shi, Chenqian Le +5
Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich visual content (tables, figures, str…
Comparison of sEMG Encoding Accuracy Across Speech Modes Using Articulatory and Phoneme Features
Chenqian Le, Ruisi Li, Beatrice Fumagalli +6
We test whether Speech Articulatory Coding (SPARC) features can linearly predict surface electromyography (sEMG) envelopes across aloud, mimed, and subvocal speech in twenty-four s…
Why Does Grounding Hurt Medical VQA? Benchmarking, Diagnosis, and Fine-Tuning of Vision-Language Models
Xupeng Chen, Binbin Shi, Chenqian Le +5
Vision-language models (VLMs) are increasingly applied to medical visual question answering (Med-VQA), yet whether they can \emph{localize} the evidence behind their answers---a pr…
Artificial Intelligence and Systemic Risk: A Unified Model of Performative Prediction, Algorithmic Herding, and Cognitive Dependency in Financial Markets
Shuchen Meng, Xupeng Chen
We develop a unified model in which AI adoption in financial markets generates systemic risk through three mutually reinforcing channels: performative prediction, algorithmic herdi…
Multimodal Fusion of Skeleton Dynamics and Clinical Gait Features for Video-Based Cerebral Palsy Severity Assessment
Kaiyuan Yang, Xupeng Chen, Jiangpeng He
Video-based gait analysis has become a promising approach for assessing motor impairment in children with cerebral palsy (CP). However, existing methods usually rely on either pose…
Abundant Intelligence and Deficient Demand: A Macro-Financial Stress Test of Rapid AI Adoption
Xupeng Chen
We formalize a macro-financial stress test for rapid AI adoption. Rather than a productivity bust or existential risk, we identify a distribution-and-contract mismatch: AI-generate…
When AI Levels the Playing Field: Skill Homogenization, Asset Concentration, and Two Regimes of Inequality
Xupeng Chen, Shuchen Meng
Generative AI compresses within-task skill differences while shifting economic value toward concentrated complementary assets, creating an apparent paradox: the technology that equ…
VoxelFormer: Parameter-Efficient Multi-Subject Visual Decoding from fMRI
Chenqian Le, Yilin Zhao, Nikasadat Emami +4
Recent advances in fMRI-based visual decoding have enabled compelling reconstructions of perceived images. However, most approaches rely on subject-specific training, limiting scal…
Machine Learning-Based Prediction of Speech Arrest During Direct Cortical Stimulation Mapping
Nikasadat Emami, Amirhossein Khalilian-Gourtani, Jianghao Qian +4
Identifying cortical regions critical for speech is essential for safe brain surgery in or near language areas. While Electrical Stimulation Mapping (ESM) remains the clinical gold…
Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs
Chenqian Le, Ziheng Gong, Chihang Wang +3
Large language models (LLMs) have shown great potential in medical question answering (MedQA), yet adapting them to biomedical reasoning remains challenging due to domain-specific…
When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs
Xiaomin Li, Zhou Yu, Zhiwei Zhang +5
Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on man…
ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models
Xiaomin Li, Xupeng Chen, Jingxuan Fan +2
The safety alignment of large language models (LLMs) often relies on reinforcement learning from human feedback (RLHF), which requires human annotations to construct preference dat…
Enhancing Exchange Rate Forecasting with Explainable Deep Learning Models
Shuchen Meng, Andi Chen, Chihang Wang +5
Accurate exchange rate prediction is fundamental to financial stability and international trade, positioning it as a critical focus in economic and financial research. Traditional…