16 papers
Adaptive Transfer of Representational Signatures for LLM Reliability Detection
Yongtong Li, Yixuan Florence Wu, Jiawei Zhang +1
Large language models (LLMs) are reported to be susceptible to reliability issues including hallucinations and reasoning errors. Existing quality detectors can predict unreliable o…
Delay-Guided Attention for Quality Prediction in Multistage Manufacturing
Jiarui Zhang, Zhaoyang Guan, Zhixuan Xia +1
Quality prediction in multistage manufacturing is challenging when inter-stage lags vary over time, as measurements taken at the same timestamp may reflect different process states…
Two Vectors Replace In-Context Demos: Structured Task Adaptation via Embeddings
Xi Ding, Naichen Shi, Jiawei Zhang
In-context learning (ICL) adapts frozen large multimodal models (LMMs) to new tasks from a few demonstrations (demos), but re-encodes them at every query, where each demo image add…
Retrieval-Based In-Context Learning: A Domain Adaptation Framework
Yilun Zhu, Naihao Deng, Yingcong Li +2
In-context retrieval (ICR) is a retrieval-based form of in-context learning (ICL) in which demonstrations are retrieved from a source database based on similarity to the query, rat…
Interpolating Neural Operator (INO): A Data-Free and Efficient Approach for Learning PDE Solution Operators
Jiachen Guo, Ye Lu, Naichen Shi +2
Neural operators have become a popular approach to approximate the solution operators of parametric partial differential equations (PDEs). However, existing neural operators either…
Multimodal Alignment Through Joint Kernel Entropic Gromov--Wasserstein Optimal Transport
Yixuan Florence Wu, Yilun Zhu, Naichen Shi
We study the problem of aligning data from multiple modalities into a shared representation space, focusing on settings where strong pretrained unimodal encoders are available but…
It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO
Naihao Deng, Yilun Zhu, Naichen Shi +2
Warning: This paper contains several toxic and offensive statements. Modern large language models (LLMs) are typically aligned through large-scale post-training to ensure fair and…
Generative Bayesian Filtering for State Estimation
Lei Cao, Sihang Feng, Jixin Yan +2
The state of a dynamic system evolves over time, switching among several latent modes that govern its observable behavior. Filtering methods infer the latent state from observation…
LMT: A Bayesian Framework for Causal Discovery from Textual Alarm Records in Manufacturing Systems
Xiaofeng Xiao, Jianhong Chen, Qiuzhuang Sun +2
Textual event records, such as alarm logs, have become an increasingly common data source in engineering and manufacturing systems. Beyond identifying correlations or recurring pat…
SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate
Lifu Wei, Yinuo Ren, Naichen Shi +1
Data assimilation (DA) addresses the problem of sequentially estimating the state of a dynamical system from noisy and incomplete observations. In this work, we employ a diffusion…
DiffATS: Diffusion in Aligned Tensor Space
Jinhua Lyu, Tianmin Yu, Brian Kim +3
Direct diffusion modeling of high-resolution spatiotemporal fields is computationally challenging. Parameter-efficient primitives address this by representing high-dimensional data…
Scalable Mean-Field Variational Inference via Preconditioned Primal-Dual Optimization
Jinhua Lyu, Tianmin Yu, Ying Ma +1
In this work, we investigate the large-scale mean-field variational inference (MFVI) problem from a mini-batch primal-dual perspective. By reformulating MFVI as a constrained finit…
Causal Discovery from Heteroscedastic Stochastic Dynamical Systems under Imperfect Physical Models
Jianhong Chen, Naichen Shi, Xubo Yue
Causal discovery is a data-driven paradigm for analyzing complex systems, while physics-based models, such as ordinary differential equations (ODEs), provide mechanistic structure…
Coupled Flow Matching
Wenxi Cai, Yuheng Wang, Naichen Shi
We introduce Coupled Flow Matching (CPFM), a framework that integrates controllable dimensionality reduction and high-fidelity reconstruction. CPFM learns coupled continuous flows…
Calibrated Principal Component Regression
Yixuan Florence Wu, Yilun Zhu, Lei Cao +1
We propose a new method for statistical inference in generalized linear models. In the overparameterized regime, Principal Component Regression (PCR) reduces variance by projecting…
Domain Generalization Under Posterior Drift
Yilun Zhu, Naihao Deng, Naichen Shi +2
Domain generalization (DG) is the problem of generalizing from several distributions (or domains), for which labeled training data are available, to a new test domain for which no…