arXiv subjects

Yuan Ni

Publications and source records attributed to Yuan Ni.

16 recordsLinked to original sources

arXiv2026

Real-time blind indexing by cross-frame consensus

Classical crystallography determines orientation and unit-cell geometry from a rotation series collected from a single specimen, whereas serial crystallography acquires one still exposure from each of many randomly oriented microcrystals and must reconstruct a complete dataset by pooling partial measurements across the ensemble. In serial experiments, each frame typically contains only a subset of reflections, and frames with few reliable peaks (the small-N regime) are especially difficult to index blindly, because multiple incorrect lattices or orientations can explain sparse observations. The approach implemented in GLINT addresses this small-N regime by treating the dataset, rather than the individual frame, as the unit of inference. Candidate solutions are generated for many frames, weak but recurrent lattice hypotheses are pooled across the ensemble to identify a shared unit cell, and each frame is then registered against that consensus cell through a known-cell orientation search with lower dimensionality than blind indexing. In benchmark tests, GLINT matched the strongest blind indexer in the comparison on indexing yield at roughly 40x lower per-frame blind-indexing latency against XGANDALF's fastest configuration, and batched known-cell registration ran entirely on one GPU, allowing cell discovery on the fly during serial data collection. On experimental serial data, frames indexed blind by GLINT merged to crystallographic quality (CC* = 0.90), while the method rejected non-crystal images rather than forcing unsupported indexing assignments. These results demonstrate that indexing performance can be evaluated not only by indexing yield and throughput, but also by the quality of the resulting merged crystallographic data.

physics.ins-det↗

arXiv2026

Observation geometry for uncertainty-aware Hamiltonian inference and experimental design in quantum magnets

Determining microscopic interactions from spectroscopic and scattering measurements is central to understanding quantum materials, yet it often remains unclear which interactions can be reliably revealed by the available experimental data and how additional experimental modalities should be designed to resolve the remaining ambiguities. Here we present an artificial intelligence-enabled framework for uncertainty-aware Hamiltonian inference and adaptive experimental design. By combining Hamiltonian-conditioned neural surrogates with Bayesian inference and observation geometry, the framework characterizes how measurements constrain Hamiltonian parameter space, quantifies the identifiability of microscopic interactions, and propagates posterior uncertainty directly in the physical Hamiltonian parameter space rather than an abstract learned representation. Using multimodal powder and single-crystal inelastic neutron scattering measurements of the quantum magnet NiPS$_{3}$, we demonstrate physically interpretable Hamiltonian inference, modality-aware uncertainty quantification, and adaptive experimental design. The framework provides a general strategy for uncertainty-aware microscopic characterization and multimodal experimental design across quantum materials.

cond-mat.str-el↗

arXiv2025

Forgetting-MarI: LLM Unlearning via Marginal Information Regularization

As AI models are trained on ever-expanding datasets, the ability to remove the influence of specific data from trained models has become essential for privacy protection and regulatory compliance. Unlearning addresses this challenge by selectively removing parametric knowledge from the trained models without retraining from scratch, which is critical for resource-intensive models such as Large Language Models (LLMs). Existing unlearning methods often degrade model performance by removing more information than necessary when attempting to ''forget'' specific data. We introduce Forgetting-MarI, an LLM unlearning framework that provably removes only the additional (marginal) information contributed by the data to be unlearned, while preserving the information supported by the data to be retained. By penalizing marginal information, our method yields an explicit upper bound on the unlearn dataset's residual influence in the trained models, providing provable undetectability. Extensive experiments confirm that our approach outperforms current state-of-the-art unlearning methods, delivering reliable forgetting and better preserved general model performance across diverse benchmarks. This advancement represents an important step toward making AI systems more controllable and compliant with privacy and copyright regulations without compromising their effectiveness.

cs.AI↗

arXiv2025

Multi-resolution Enhancement for Full Spectrum Neural Representations

Scientific data acquisition continues to outpace storage and analysis capabilities, making voxel-based representations increasingly intractable. Implicit neural representations (INRs) offer a promising solution by encoding signals through coordinate-based neural networks, serving as surrogates of data, with computational and storage requirements scaling with network complexity rather than data dimensionality. However, smaller INRs struggle to faithfully represent the multi-scale structures, high-frequency information, and fine textures that constitute a large proportion of scientific measurements. We propose WIEN-INR, a theoretically-guided hierarchical INR framework that distributes modeling across resolution scales and enables improved representation capacity through a novel enhancement network to recover subtle details. This multi-scale architecture allows smaller networks to retain the full spectrum of information while preserving training efficiency and lowering storage cost. Evaluated on distinct raw experimental measurements across scales and complexities, WIEN-INR represents a practical step toward broader adoption of neural representations in scientific workflows, delivering compact, robust, and high-fidelity representations.

cs.LG↗

arXiv2025

Physics-Guided Dual Implicit Neural Representations for Source Separation

Significant challenges exist in efficient data analysis of most advanced experimental and observational techniques because the collected signals often include unwanted contributions--such as background and signal distortions--that can obscure the physically relevant information of interest. To address this, we have developed a self-supervised machine-learning approach for source separation using a dual implicit neural representation framework that jointly trains two neural networks: one for approximating distortions of the physical signal of interest and the other for learning the effective background contribution. Our method learns directly from the raw data by minimizing a reconstruction-based loss function without requiring labeled data or pre-defined dictionaries. We demonstrate the effectiveness of our framework by considering a challenging case study involving large-scale simulated as well as experimental momentum-energy-dependent inelastic neutron scattering data in a four-dimensional parameter space, characterized by heterogeneous background contributions and unknown distortions to the target signal. The method is found to successfully separate physically meaningful signals from a complex or structured background even when the signal characteristics vary across all four dimensions of the parameter space. An analytical approach that informs the choice of the regularization parameter is presented. Our method offers a versatile framework for addressing source separation problems across diverse domains, ranging from superimposed signals in astronomical measurements to structural features in biomedical image reconstructions.

cs.CV↗

arXiv2024

ZALM3: Zero-Shot Enhancement of Vision-Language Alignment via In-Context Information in Multi-Turn Multimodal Medical Dialogue

The rocketing prosperity of large language models (LLMs) in recent years has boosted the prevalence of vision-language models (VLMs) in the medical sector. In our online medical consultation scenario, a doctor responds to the texts and images provided by a patient in multiple rounds to diagnose her/his health condition, forming a multi-turn multimodal medical dialogue format. Unlike high-quality images captured by professional equipment in traditional medical visual question answering (Med-VQA), the images in our case are taken by patients' mobile phones. These images have poor quality control, with issues such as excessive background elements and the lesion area being significantly off-center, leading to degradation of vision-language alignment in the model training phase. In this paper, we propose ZALM3, a Zero-shot strategy to improve vision-language ALignment in Multi-turn Multimodal Medical dialogue. Since we observe that the preceding text conversations before an image can infer the regions of interest (RoIs) in the image, ZALM3 employs an LLM to summarize the keywords from the preceding context and a visual grounding model to extract the RoIs. The updated images eliminate unnecessary background noise and provide more effective vision-language alignment. To better evaluate our proposed method, we design a new subjective assessment metric for multi-turn unimodal/multimodal medical dialogue to provide a fine-grained performance comparison. Our experiments across three different clinical departments remarkably demonstrate the efficacy of ZALM3 with statistical significance.

cs.CL↗

arXiv2024

IAPT: Instruction-Aware Prompt Tuning for Large Language Models

Soft prompt tuning is a widely studied parameter-efficient fine-tuning method. However, it has a clear drawback: many soft tokens must be inserted into the input sequences to guarantee downstream performance. As a result, soft prompt tuning is less considered than Low-rank adaptation (LoRA) in the large language modeling (LLM) era. In this work, we propose a novel prompt tuning method, Instruction-Aware Prompt Tuning (IAPT), that requires only four soft tokens. First, we install a parameter-efficient soft prompt generator at each Transformer layer to generate idiosyncratic soft prompts for each input instruction. The generated soft prompts can be seen as a semantic summary of the input instructions and can effectively guide the output generation. Second, the soft prompt generators are modules with a bottleneck architecture consisting of a self-attention pooling operation, two linear projections, and an activation function. Pilot experiments show that prompt generators at different Transformer layers require different activation functions. Thus, we propose to learn the idiosyncratic activation functions for prompt generators automatically with the help of rational functions. We have conducted experiments on various tasks, and the experimental results demonstrate that (a) our IAPT method can outperform the recent baselines with comparable tunable parameters. (b) Our IAPT method is more efficient than LoRA under the single-backbone multi-tenant setting.

cs.CL↗

arXiv2024

Auto-Calibration and Biconvex Compressive Sensing with Applications to Parallel MRI

We study an auto-calibration problem in which a transform-sparse signal is acquired via compressive sensing by multiple sensors in parallel, but with unknown calibration parameters of the sensors. This inverse problem has an important application in pMRI reconstruction, where the calibration parameters of the receiver coils are often difficult and costly to obtain explicitly, but nonetheless are a fundamental requirement for high-precision reconstructions. Most auto-calibration strategies for this problem involve solving a challenging biconvex optimization problem, which lacks reconstruction guarantees. In this work, we transform the auto-calibrated parallel compressive sensing problem to a convex optimization problem using the idea of `lifting'. By exploiting sparsity structures in the signal and the redundancy introduced by multiple sensors, we solve a mixed-norm minimization problem to recover the underlying signal and the sensing parameters simultaneously. Our method provides robust and stable recovery guarantees that take into account the presence of noise and sparsity deficiencies in the signals. As such, it offers a theoretically guaranteed approach to auto-calibrated parallel imaging in MRI under appropriate assumptions. Applications in compressive sensing pMRI are discussed, and numerical experiments using real and simulated MRI data are presented to support our theoretical results.

math.OC↗

arXiv2024

Text2MDT: Extracting Medical Decision Trees from Medical Texts

Knowledge of the medical decision process, which can be modeled as medical decision trees (MDTs), is critical to build clinical decision support systems. However, the current MDT construction methods rely heavily on time-consuming and laborious manual annotation. In this work, we propose a novel task, Text2MDT, to explore the automatic extraction of MDTs from medical texts such as medical guidelines and textbooks. We normalize the form of the MDT and create an annotated Text-to-MDT dataset in Chinese with the participation of medical experts. We investigate two different methods for the Text2MDT tasks: (a) an end-to-end framework which only relies on a GPT style large language models (LLM) instruction tuning to generate all the node information and tree structures. (b) The pipeline framework which decomposes the Text2MDT task to three subtasks. Experiments on our Text2MDT dataset demonstrate that: (a) the end-to-end method basd on LLMs (7B parameters or larger) show promising results, and successfully outperform the pipeline methods. (b) The chain-of-thought (COT) prompting method \cite{Wei2022ChainOT} can improve the performance of the fine-tuned LLMs on the Text2MDT test set. (c) the lightweight pipelined method based on encoder-based pretrained models can perform comparably with LLMs with model complexity two magnititudes smaller. Our Text2MDT dataset is open-sourced at \url{https://tianchi.aliyun.com/dataset/95414}, and the source codes are open-sourced at \url{https://github.com/michael-wzhu/text2dt}.

cs.CL↗

arXiv2023

UltraFeedback: Boosting Language Models with Scaled AI Feedback

Learning from human feedback has become a pivot technique in aligning large language models (LLMs) with human preferences. However, acquiring vast and premium human feedback is bottlenecked by time, labor, and human capability, resulting in small sizes or limited topics of current datasets. This further hinders feedback learning as well as alignment research within the open-source community. To address this issue, we explore how to go beyond human feedback and collect high-quality \textit{AI feedback} automatically for a scalable alternative. Specifically, we identify \textbf{scale and diversity} as the key factors for feedback data to take effect. Accordingly, we first broaden instructions and responses in both amount and breadth to encompass a wider range of user-assistant interactions. Then, we meticulously apply a series of techniques to mitigate annotation biases for more reliable AI feedback. We finally present \textsc{UltraFeedback}, a large-scale, high-quality, and diversified AI feedback dataset, which contains over 1 million GPT-4 feedback for 250k user-assistant conversations from various aspects. Built upon \textsc{UltraFeedback}, we align a LLaMA-based model by best-of-$n$ sampling and reinforcement learning, demonstrating its exceptional performance on chat benchmarks. Our work validates the effectiveness of scaled AI feedback data in constructing strong open-source chat language models, serving as a solid foundation for future feedback learning research. Our data and models are available at https://github.com/thunlp/UltraFeedback.

cs.CL↗

arXiv2023

Unified Demonstration Retriever for In-Context Learning

In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction. It has been shown highly dependent on the provided demonstrations and thus promotes the research of demonstration retrieval: given a test input, relevant examples are retrieved from the training set to serve as informative demonstrations for in-context learning. While previous works focus on training task-specific retrievers for several tasks separately, these methods are often hard to transfer and scale on various tasks, and separately trained retrievers incur a lot of parameter storage and deployment cost. In this paper, we propose Unified Demonstration Retriever (\textbf{UDR}), a single model to retrieve demonstrations for a wide range of tasks. To train UDR, we cast various tasks' training signals into a unified list-wise ranking formulation by language model's feedback. Then we propose a multi-task list-wise ranking training framework, with an iterative mining strategy to find high-quality candidates, which can help UDR fully incorporate various tasks' signals. Experiments on 30+ tasks across 13 task families and multiple data domains show that UDR significantly outperforms baselines. Further analyses show the effectiveness of each proposed component and UDR's strong ability in various scenarios including different LMs (1.3B - 175B), unseen datasets, varying demonstration quantities, etc.

cs.CL↗

arXiv2022

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark

Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually changing medical practice. With the development of biomedical language understanding benchmarks, AI applications are widely used in the medical field. However, most benchmarks are limited to English, which makes it challenging to replicate many of the successes in English for other languages. To facilitate research in this direction, we collect real-world biomedical data and present the first Chinese Biomedical Language Understanding Evaluation (CBLUE) benchmark: a collection of natural language understanding tasks including named entity recognition, information extraction, clinical diagnosis normalization, single-sentence/sentence-pair classification, and an associated online platform for model evaluation, comparison, and analysis. To establish evaluation on these tasks, we report empirical results with the current 11 pre-trained Chinese models, and experimental results show that state-of-the-art neural models perform by far worse than the human ceiling. Our benchmark is released at \url{https://tianchi.aliyun.com/dataset/dataDetail?dataId=95414&lang=en-us}.

cs.CL↗

arXiv2022

A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation

Early exiting allows instances to exit at different layers according to the estimation of difficulty. Previous works usually adopt heuristic metrics such as the entropy of internal outputs to measure instance difficulty, which suffers from generalization and threshold-tuning. In contrast, learning to exit, or learning to predict instance difficulty is a more appealing way. Though some effort has been devoted to employing such "learn-to-exit" modules, it is still unknown whether and how well the instance difficulty can be learned. As a response, we first conduct experiments on the learnability of instance difficulty, which demonstrates that modern neural models perform poorly on predicting instance difficulty. Based on this observation, we propose a simple-yet-effective Hash-based Early Exiting approach (HashEE) that replaces the learn-to-exit modules with hash functions to assign each token to a fixed exiting layer. Different from previous methods, HashEE requires no internal classifiers nor extra parameters, and therefore is more efficient. Experimental results on classification, regression, and generation tasks demonstrate that HashEE can achieve higher performance with fewer FLOPs and inference time compared with previous state-of-the-art early exiting methods.

cs.CL↗

arXiv2021

AutoTrans: Automating Transformer Design via Reinforced Architecture Search

Though the transformer architectures have shown dominance in many natural language understanding tasks, there are still unsolved issues for the training of transformer models, especially the need for a principled way of warm-up which has shown importance for stable training of a transformer, as well as whether the task at hand prefer to scale the attention product or not. In this paper, we empirically explore automating the design choices in the transformer model, i.e., how to set layer-norm, whether to scale, number of layers, number of heads, activation function, etc, so that one can obtain a transformer architecture that better suits the tasks at hand. RL is employed to navigate along search space, and special parameter sharing strategies are designed to accelerate the search. It is shown that sampling a proportion of training data per epoch during search help to improve the search quality. Experiments on the CoNLL03, Multi-30k, IWSLT14 and WMT-14 shows that the searched transformer model can outperform the standard transformers. In particular, we show that our learned model can be trained more robustly with large learning rates without warm-up.

cs.CL↗

arXiv2020

AutoRC: Improving BERT Based Relation Classification Models via Architecture Search

Although BERT based relation classification (RC) models have achieved significant improvements over the traditional deep learning models, it seems that no consensus can be reached on what is the optimal architecture. Firstly, there are multiple alternatives for entity span identification. Second, there are a collection of pooling operations to aggregate the representations of entities and contexts into fixed length vectors. Third, it is difficult to manually decide which feature vectors, including their interactions, are beneficial for classifying the relation types. In this work, we design a comprehensive search space for BERT based RC models and employ neural architecture search (NAS) method to automatically discover the design choices mentioned above. Experiments on seven benchmark RC tasks show that our method is efficient and effective in finding better architectures than the baseline BERT based RC model. Ablation study demonstrates the necessity of our search space design and the effectiveness of our search method.

cs.CL↗

arXiv2014

Plasmonic lasing of nanocavity embedding in metallic nanoantenna array

Plasmonic nanolasers have ultrahigh lasing thresholds, especially those devices for which all three dimensions are truly subwavelength. Because of a momentum mismatch between the propagating light and localized optical field of the subwavelength nanocavity, poor optical pumping efficiency is another important reason for the ultrahigh threshold but is normally always ignored. Based on a cavity-embedded nanoantenna array design, we demonstrate a room-temperature low-threshold plasmonic nanolaser that is robust, reproducible, and easy-to-fabricate using chemical-template lithography. The mode volume of the device is~0.22(λ/2n)3 (here,λ is resonant wavelength and n is the refractive index), and the experimental lasing threshold produced is ~2.70MW/mm2. The lasing polarization and the function of nanoantenna array are investigated in detail. Our work provides a new strategy to achieve room-temperature low-threshold plasmonic nanolasers of interest in applications to biological sensoring and information technology.

physics.optics↗