arXiv subjects

Aodong Li

Publications and source records attributed to Aodong Li.

13 recordsLinked to original sources

arXiv2026

AgentSM: Semantic Memory for Agentic Text-to-SQL

Recent advances in LLM-based Text-to-SQL have achieved remarkable gains on public benchmarks such as BIRD and Spider. Yet, these systems struggle to scale in realistic enterprise settings with large, complex schemas, diverse SQL dialects, and expensive multi-step reasoning. Emerging agentic approaches show potential for adaptive reasoning but often suffer from inefficiency and instability-repeating interactions with databases, producing inconsistent outputs, and occasionally failing to generate valid answers. To address these challenges, we introduce Agent Semantic Memory (AgentSM), an agentic framework for Text-to-SQL that builds and leverages interpretable semantic memory. Instead of relying on raw scratchpads or vector retrieval, AgentSM captures prior execution traces-or synthesizes curated ones-as structured programs that directly guide future reasoning. This design enables systematic reuse of reasoning paths, which allows agents to scale to larger schemas, more complex questions, and longer trajectories efficiently and reliably. Compared to state-of-the-art systems, AgentSM achieves higher efficiency by reducing average token usage and trajectory length by 25% and 35%, respectively, on the Spider 2.0 benchmark. It also improves execution accuracy, reaching a state-of-the-art accuracy of 44.8% on the Spider 2.0 Lite benchmark.

cs.AI↗

arXiv2025

Probabilistic Hash Embeddings for Online Learning of Categorical Features

We study streaming data with categorical features where the vocabulary of categorical feature values is changing and can even grow unboundedly over time. Feature hashing is commonly used as a pre-processing step to map these categorical values into a feature space of fixed size before learning their embeddings. While these methods have been developed and evaluated for offline or batch settings, in this paper we consider online settings. We show that deterministic embeddings are sensitive to the arrival order of categories and suffer from forgetting in online learning, leading to performance deterioration. To mitigate this issue, we propose a probabilistic hash embedding (PHE) model that treats hash embeddings as stochastic and applies Bayesian online learning to learn incrementally from data. Based on the structure of PHE, we derive a scalable inference algorithm to learn model parameters and infer/update the posteriors of hash embeddings and other latent variables. Our algorithm (i) can handle an evolving vocabulary of categorical items, (ii) is adaptive to new items without forgetting old items, (iii) is implementable with a bounded set of parameters that does not grow with the number of distinct observed values on the stream, and (iv) is invariant to the item arrival order. Experiments in classification, sequence modeling, and recommendation systems in online learning setups demonstrate the superior performance of PHE while maintaining high memory efficiency (consumes as low as 2~4 memory of a one-hot embedding table). Supplementary materials are at https://github.com/aodongli/probabilistic-hash-embeddings

cs.LG↗

arXiv2025

Tight-binding photonics

Photonics, dealing with the generation, manipulation, and detection of photons in various systems, lays the foundation of many advanced technologies. A key task of photonics is to know how photons propagate in complex media such as periodic and aperiodic photonic crystals. The conventional wisdom is to numerically solve the Maxwell equations either by dedicated numerical techniques or brute-force finite-element calculations. Recently, the strict analogy between photonic crystals and theoretical tight-binding models provides an unprecedentedly convenient wayof understanding the spectra and wavefunctions of photonic systems by mapping the complicated differential equationsinto matrixed Hamiltonians that can be easily solved through the band theory and exact diagonalization. in this paper, we present a timely review of tight-binding-like photonics in various platforms, covering fundamental theories, experimental realizations, unique physical efiects, and their potential applications. We also provide a brief outlook on the future trends of this active area. Our review offers an in-depth and comprehensive picture on this rapidly developing field and may shed light on the future design on advanced tight-binding-like photonic devices.

physics.optics↗

arXiv2024

Anomaly Detection of Tabular Data Using LLMs

Large language models (LLMs) have shown their potential in long-context understanding and mathematical reasoning. In this paper, we study the problem of using LLMs to detect tabular anomalies and show that pre-trained LLMs are zero-shot batch-level anomaly detectors. That is, without extra distribution-specific model fitting, they can discover hidden outliers in a batch of data, demonstrating their ability to identify low-density data regions. For LLMs that are not well aligned with anomaly detection and frequently output factual errors, we apply simple yet effective data-generating processes to simulate synthetic batch-level anomaly detection datasets and propose an end-to-end fine-tuning strategy to bring out the potential of LLMs in detecting real anomalies. Experiments on a large anomaly detection benchmark (ODDS) showcase i) GPT-4 has on-par performance with the state-of-the-art transductive learning-based anomaly detection methods and ii) the efficacy of our synthetic dataset and fine-tuning strategy in aligning LLMs to this task.

cs.LG↗

arXiv2024

Multi-state Chiral Switching Through Adiabaticity Control in Encircling Exceptional Points

Dynamic encircling of exceptional points has attracted significant interest in recent years, as it can facilitate chiral transmission selectivity due to a nontrivial eigenstate evolution. Recently, multi-state systems have been explored, associated with more complex topologies supporting a larger number of exceptional points, but chiral switching among multiple eigenstates has remained elusive in experiments. Here, we overcome this challenge by dividing the eigenstate space into multiple subspaces by controlling the adiabaticity. The eigenstates in different subspaces can evolve without crosstalk, and chiral switching occurs as the eigenstates within each subspace are subject to a non-adiabatic transition while they encircle exceptional points. We experimentally demonstrate this phenomenon by reporting chiral switching for two groups of optical modes at telecom wavelengths in a four-state optical system, and theoretically demonstrate that our approach can be extended to higher-order systems. Our findings pave new avenues for studying chiral dynamics based on exceptional-point physics in multi-state systems, and offer opportunities to develop multiplexed photonic devices.

physics.optics↗

arXiv2024

Successive Phase Transition in Higher-order Topological Anderson Insulators

Disorder, traditionally believed to hinder the propagation of waves. has recently been shown to prompt the occurrence of topological phase transitions. For example, when disorder strength continuously increases and surpasses certain critical value, a phase transition from topologically trivial to nontrivial insulating phases occurs. However, in the parameter domain of the nontrivial phase, whether there exists a finer phase diagram that can be further classified by different disorder strengths is still unclear. Here we present a successive topological phase transition driven by the disorder strength in a higher-order topological insulator with long-range couplings. As the strength of the disorder gradually increases, the real-space topological invariant of the system undergoes a consecutive change from 0 to 4, accompanied by the stepped increase in the number of boundary-localized corner states. Our work opens an avenue for utilizing disorder to induce phase transitions among different higher-order topological insulators.

cond-mat.mes-hall↗

arXiv2023

Zero-Shot Anomaly Detection via Batch Normalization

Anomaly detection (AD) plays a crucial role in many safety-critical application domains. The challenge of adapting an anomaly detector to drift in the normal data distribution, especially when no training data is available for the "new normal," has led to the development of zero-shot AD techniques. In this paper, we propose a simple yet effective method called Adaptive Centered Representations (ACR) for zero-shot batch-level AD. Our approach trains off-the-shelf deep anomaly detectors (such as deep SVDD) to adapt to a set of inter-related training data distributions in combination with batch normalization, enabling automatic zero-shot generalization for unseen AD tasks. This simple recipe, batch normalization plus meta-training, is a highly effective and versatile tool. Our theoretical results guarantee the zero-shot generalization for unseen AD tasks; our empirical results demonstrate the first zero-shot AD results for tabular data and outperform existing methods in zero-shot anomaly detection and segmentation on image data from specialized domains. Code is at https://github.com/aodongli/zero-shot-ad-via-batch-norm

cs.LG↗

arXiv2023

Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data

Anomaly detection is the task of identifying abnormal samples in large unlabeled datasets. While the advent of foundation models has produced powerful zero-shot anomaly detection methods, their deployment in practice is often hindered by the absence of labeled validation data -- without it, their detection performance cannot be evaluated reliably. In this work, we propose SWSA (Selection With Synthetic Anomalies): a general-purpose framework to select image-based anomaly detectors without labeled validation data. Instead of collecting labeled validation data, we generate synthetic anomalies without any training or fine-tuning, using only a small support set of normal images. Our synthetic anomalies are used to create detection tasks that compose a validation framework for model selection. In an empirical study, we evaluate SWSA with three types of synthetic anomalies and on two selection tasks: model selection of image-based anomaly detectors and prompt selection for CLIP-based anomaly detection. SWSA often selects models and prompts that match selections made with a ground-truth validation set, outperforming baseline selection strategies.

cs.LG↗

arXiv2023

Deep Anomaly Detection under Labeling Budget Constraints

Selecting informative data points for expert feedback can significantly improve the performance of anomaly detection (AD) in various contexts, such as medical diagnostics or fraud detection. In this paper, we determine a set of theoretical conditions under which anomaly scores generalize from labeled queries to unlabeled data. Motivated by these results, we propose a data labeling strategy with optimal data coverage under labeling budget constraints. In addition, we propose a new learning framework for semi-supervised AD. Extensive experiments on image, tabular, and video data sets show that our approach results in state-of-the-art semi-supervised AD performance under labeling budget constraints.

cs.LG↗

arXiv2022

Latent Outlier Exposure for Anomaly Detection with Contaminated Data

Anomaly detection aims at identifying data points that show systematic deviations from the majority of data in an unlabeled dataset. A common assumption is that clean training data (free of anomalies) is available, which is often violated in practice. We propose a strategy for training an anomaly detector in the presence of unlabeled anomalies that is compatible with a broad class of models. The idea is to jointly infer binary labels to each datum (normal vs. anomalous) while updating the model parameters. Inspired by outlier exposure (Hendrycks et al., 2018) that considers synthetically created, labeled anomalies, we thereby use a combination of two losses that share parameters: one for the normal and one for the anomalous data. We then iteratively proceed with block coordinate updates on the parameters and the most likely (latent) labels. Our experiments with several backbone models on three image datasets, 30 tabular data sets, and a video anomaly detection benchmark showed consistent and significant improvements over the baselines.

cs.LG↗

arXiv2021

Encircling exceptional points in a Riemann sphere for efficient asymmetric polarization-locked devices

Dynamically encircling exceptional points (EPs) in two-dimensional Hamiltonian parameter space has enabled intriguing chiral dynamics in which the final state of the system depends on the encircling direction. Here, we show that full Hamiltonian parameter space can be described in a Riemann sphere, and those points on the parameter space boundary with the eigenstates of the system Hamiltonian being convergent, converge to the north vertex. We present that encircling one EP on the Riemann sphere leads to chiral response, and a continuous encircling trajectory passing through the north vertex can realize near-unity asymmetrical transmission. An asymmetric polarization-locked devices are designed by mapping the encircling path onto the L-shaped silicon waveguides. We experimentally demonstrate near 100% asymmetrical polarization conversion efficiency between TE and TM modes with the mode crosstalk below -20 dB at 1550 nm. Our results bring the study of EP-associated dynamics into the realm of highly-efficient asymmetrical polarization conversion and power up new application opportunities for EP physics.

physics.optics↗

arXiv2021

Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning

We consider the problem of online learning in the presence of distribution shifts that occur at an unknown rate and of unknown intensity. We derive a new Bayesian online inference approach to simultaneously infer these distribution shifts and adapt the model to the detected changes by integrating ideas from change point detection, switching dynamical systems, and Bayesian online learning. Using a binary 'change variable,' we construct an informative prior such that--if a change is detected--the model partially erases the information of past model updates by tempering to facilitate adaptation to the new data distribution. Furthermore, the approach uses beam search to track multiple change-point hypotheses and selects the most probable one in hindsight. Our proposed method is model-agnostic, applicable in both supervised and unsupervised learning settings, suitable for an environment of concept drifts or covariate drifts, and yields improvements over state-of-the-art Bayesian online learning approaches.

stat.ML↗

arXiv2017

Enhanced Neural Machine Translation by Learning from Draft

Neural machine translation (NMT) has recently achieved impressive results. A potential problem of the existing NMT algorithm, however, is that the decoding is conducted from left to right, without considering the right context. This paper proposes an two-stage approach to solve the problem. In the first stage, a conventional attention-based NMT system is used to produce a draft translation, and in the second stage, a novel double-attention NMT system is used to refine the translation, by looking at the original input as well as the draft translation. This drafting-and-refinement can obtain the right-context information from the draft, hence producing more consistent translations. We evaluated this approach using two Chinese-English translation tasks, one with 44k pairs and 1M pairs respectively. The experiments showed that our approach achieved positive improvements over the conventional NMT system: the improvements are 2.4 and 0.9 BLEU points on the small-scale and large-scale tasks, respectively.

cs.CL↗