arXiv subjects

Xu Ouyang

Publications and source records attributed to Xu Ouyang.

At least 19 recordsLinked to original sources

arXiv2026

Financial Numerical Prediction and Allocation as Token Generation

Financial prediction typically relies on task-specific regression, ranking, or policy heads, separating the language model from the numerical object ultimately evaluated. We investigate whether a causal language model can instead represent forecasts and decisions directly through constrained token generation. FinATOM introduces a unified, head-free interface for three-step stock-return forecasting and dynamic five-ETF allocation. The forecasting model autoregressively emits volatility-standardized return tokens and is trained with ordinal and ranking supervision followed by a one-epoch token-level policy stage. The allocation model generates normalized long-only weights; supervised fine-tuning imitates a causal mean--variance anchor, and DAPO-augmented GRPO optimizes realized 21-day Sharpe subject to anchor consistency. In 2023--2025 ETF tests, the allocation policy improves pooled gross Sharpe from 1.428 to 1.529 and net Sharpe under a 5-bp transaction-cost model from 1.394 to 1.494. The multimodal allocation input attains the highest three-period mean Sharpe of 1.540, with its clearest advantage in 2025. On FinTexTS, the SFT and policy strategies achieve 73.52\%/2.68 and 73.72\%/2.69 cumulative-return/Sharpe, respectively. These results support the feasibility of direct language-model token generation for financial numerical prediction and decision-making, while motivating broader tests across assets, regimes, and random seeds.

cs.CV↗

arXiv2026

LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws

Existing scaling laws for Large Language Models (LLMs), predominantly monotonic power laws, fail to explain emerging non-monotonic phenomena such as catastrophic overtraining and quantization-induced degradation, where performance deteriorates despite increased compute. We propose the Shannon Scaling Law, a unified theoretical framework that models LLM training as information transmission over a noisy channel, grounded in the Shannon-Hartley theorem. By mapping model parameters to channel bandwidth and training tokens to signal power, our formulation explicitly captures the interaction between learning signal and intrinsic noise. This perspective reveals a fundamental Shannon capacity for LLMs: scaling model size or data without preserving a sufficient signal-to-noise ratio (SNR) inevitably amplifies noise, inducing a transition from monotonic improvement to U-shaped performance degradation. We validate our theory through experiments on Pythia and OLMo2 under perturbations, including Gaussian noise, quantization and supervised fine-tuning on math, QA and code tasks. The Shannon Scaling Law consistently outperforms classical scaling laws and recent perturbation-aware laws, achieving strong $R^2$ scores and accurately capturing loss basins missed by prior approaches. It also extrapolates: fitted on $\leq$6.9B Pythia models with $\leq$180B tokens, it predicts the unseen 12B model up to 307B tokens at pooled $R^2{=}0.847$, while monotonic baselines collapse.

cs.LG↗

arXiv2025

ADMIRE-BayesOpt: Accelerated Data MIxture RE-weighting for Language Models with Bayesian Optimization

Determining the optimal data mixture for large language model training remains a challenging problem with an outsized impact on performance. In practice, language model developers continue to rely on heuristic exploration since no learning-based approach has emerged as a reliable solution. In this work, we propose to view the selection of training data mixtures as a black-box hyperparameter optimization problem, for which Bayesian Optimization is a well-established class of appropriate algorithms. Firstly, we cast data mixture learning as a sequential decision-making problem, in which we aim to find a suitable trade-off between the computational cost of training exploratory (proxy-) models and final mixture performance. Secondly, we systematically explore the properties of transferring mixtures learned at a small scale to larger-scale experiments, providing insights and highlighting opportunities for research at a modest scale. By proposing Multi-fidelity Bayesian Optimization as a suitable method in this common scenario, we introduce a natural framework to balance experiment cost with model fit, avoiding the risks of overfitting to smaller scales while minimizing the number of experiments at high cost. We present results for pre-training and instruction finetuning across models ranging from 1 million to 7 billion parameters, varying from simple architectures to state-of-the-art models and benchmarks spanning dozens of datasets. We demonstrate consistently strong results relative to a wide range of baselines, resulting inspeed-ups of over 500% in determining the best data mixture on our largest experiments. In addition, we broaden access to research by sharing ADMIRE IFT Runs, a dataset of 460 full training & evaluation runs worth over 13,000 GPU hours, greatly reducing the cost of conducting research in this area.

stat.ML↗

arXiv2025

Narrow beam and low-sidelobe two-dimensional beam steering on thin-film lithium niobate optical phased array

Optical beam steering has become indispensable in free-space optical communications, light detection and ranging (LiDAR), mapping, and projection. Optical phased array (OPA) leads this field, yet conventional versions still suffer from a narrow steering field of view (FOV), insufficient sidelobe suppression, and limited angular resolution. Thin-film lithium niobate (LN), with its strong Pockels electro-optic (EO) effect, offers a powerful integrated-photonics platform to overcome these limitations. Here we present a two-dimensional (2D) EO-steered OPA based on a non-uniformly spaced X-cut thin-film LN ridge-waveguide array. A superlattice ridge design suppresses optical crosstalk to -20 dB, enabling low-sidelobe far-field radiation. Using particle swarm optimization (PSO) method, we transform a uniformly spaced array into an optimized non-uniform design, largely improving angular resolution while maintaining sidelobe suppression. When combined with a single-radiating trapezoidal end-fire emitter incorporating an etched grating, the device produces a main-lobe beam width of 0.99 degree*0.63 degree from an aperture of only 140 um*250 um, achieving a wide 2D steering range of 47 degree*9.36 degree with a 20 dB sidelobe-suppression ratio. These results highlight thin-film LN OPA as a compelling route toward heterogeneous, compact, and high-performance EO beam-steering modules and ultra-miniaturized optical modulators.

physics.optics↗

arXiv2025

i-FlatCam: A 253 FPS, 91.49 $μ$J/Frame Ultra-Compact Intelligent Lensless Camera for Real-Time and Efficient Eye Tracking in VR/AR

We present a first-of-its-kind ultra-compact intelligent camera system, dubbed i-FlatCam, including a lensless camera with a computational (Comp.) chip. It highlights (1) a predict-then-focus eye tracking pipeline for boosted efficiency without compromising the accuracy, (2) a unified compression scheme for single-chip processing and improved frame rate per second (FPS), and (3) dedicated intra-channel reuse design for depth-wise convolutional layers (DW-CONV) to increase utilization. i-FlatCam demonstrates the first eye tracking pipeline with a lensless camera and achieves 3.16 degrees of accuracy, 253 FPS, 91.49 $μ$J/Frame, and 6.7mm x 8.9mm x 1.2mm camera form factor, paving the way for next-generation Augmented Reality (AR) and Virtual Reality (VR) devices.

cs.AR↗

arXiv2025

SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning

Neural architecture search (NAS) has demonstrated amazing success in searching for efficient deep neural networks (DNNs) from a given supernet. In parallel, the lottery ticket hypothesis has shown that DNNs contain small subnetworks that can be trained from scratch to achieve a comparable or higher accuracy than original DNNs. As such, it is currently a common practice to develop efficient DNNs via a pipeline of first search and then prune. Nevertheless, doing so often requires a search-train-prune-retrain process and thus prohibitive computational cost. In this paper, we discover for the first time that both efficient DNNs and their lottery subnetworks (i.e., lottery tickets) can be directly identified from a supernet, which we term as SuperTickets, via a two-in-one training scheme with jointly architecture searching and parameter pruning. Moreover, we develop a progressive and unified SuperTickets identification strategy that allows the connectivity of subnetworks to change during supernet training, achieving better accuracy and efficiency trade-offs than conventional sparse training. Finally, we evaluate whether such identified SuperTickets drawn from one task can transfer well to other tasks, validating their potential of handling multiple tasks simultaneously. Extensive experiments and ablation studies on three tasks and four benchmark datasets validate that our proposed SuperTickets achieve boosted accuracy and efficiency trade-offs than both typical NAS and pruning pipelines, regardless of having retraining or not. Codes and pretrained models are available at https://github.com/RICE-EIC/SuperTickets.

cs.CV↗

arXiv2025

SelectFormer: Private and Practical Data Selection for Transformers

Critical to a free data market is $\textit{private data selection}$, i.e. the model owner selects and then appraises training data from the data owner before both parties commit to a transaction. To keep the data and model private, this process shall evaluate the target model to be trained over Multi-Party Computation (MPC). While prior work suggests that evaluating Transformer-based models over MPC is prohibitively expensive, this paper makes it practical for the purpose of data selection. Our contributions are three: (1) a new pipeline for private data selection over MPC; (2) emulating high-dimensional nonlinear operators with low-dimension MLPs, which are trained on a small sample of the data of interest; (3) scheduling MPC in a parallel, multiphase fashion. We evaluate our method on diverse Transformer models and NLP/CV benchmarks. Compared to directly evaluating the target model over MPC, our method reduces the delay from thousands of hours to tens of hours, while only seeing around 0.20% accuracy degradation from training with the selected data.

cs.LG↗

arXiv2025

Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks

Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks, i.e., an imperceptible perturbation to the input can mislead DNNs trained on clean images into making erroneous predictions. To tackle this, adversarial training is currently the most effective defense method, by augmenting the training set with adversarial samples generated on the fly. Interestingly, we discover for the first time that there exist subnetworks with inborn robustness, matching or surpassing the robust accuracy of the adversarially trained networks with comparable model sizes, within randomly initialized networks without any model training, indicating that adversarial training on model weights is not indispensable towards adversarial robustness. We name such subnetworks Robust Scratch Tickets (RSTs), which are also by nature efficient. Distinct from the popular lottery ticket hypothesis, neither the original dense networks nor the identified RSTs need to be trained. To validate and understand this fascinating finding, we further conduct extensive experiments to study the existence and properties of RSTs under different models, datasets, sparsity patterns, and attacks, drawing insights regarding the relationship between DNNs' robustness and their initialization/overparameterization. Furthermore, we identify the poor adversarial transferability between RSTs of different sparsity ratios drawn from the same randomly initialized dense network, and propose a Random RST Switch (R2S) technique, which randomly switches between different RSTs, as a novel defense method built on top of RSTs. We believe our findings about RSTs have opened up a new perspective to study model robustness and extend the lottery ticket hypothesis.

cs.LG↗

arXiv2024

Fine-grained Text to Image Synthesis

Fine-grained text to image synthesis involves generating images from texts that belong to different categories. In contrast to general text to image synthesis, in fine-grained synthesis there is high similarity between images of different subclasses, and there may be linguistic discrepancy among texts describing the same image. Recent Generative Adversarial Networks (GAN), such as the Recurrent Affine Transformation (RAT) GAN model, are able to synthesize clear and realistic images from texts. However, GAN models ignore fine-grained level information. In this paper we propose an approach that incorporates an auxiliary classifier in the discriminator and a contrastive learning method to improve the accuracy of fine-grained details in images synthesized by RAT GAN. The auxiliary classifier helps the discriminator classify the class of images, and helps the generator synthesize more accurate fine-grained images. The contrastive learning method minimizes the similarity between images from different subclasses and maximizes the similarity between images from the same subclass. We evaluate on several state-of-the-art methods on the commonly used CUB-200-2011 bird dataset and Oxford-102 flower dataset, and demonstrated superior performance.

cs.CV↗

arXiv2024

Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens

We reveal that low-bit quantization favors undertrained large language models (LLMs) by observing that models with larger sizes or fewer training tokens experience less quantization-induced degradation (QiD) when applying low-bit quantization, whereas smaller models with extensive training tokens suffer significant QiD. To gain deeper insights into this trend, we study over 1500 quantized LLM checkpoints of various sizes and at different training levels (undertrained or fully trained) in a controlled setting, deriving scaling laws for understanding the relationship between QiD and factors such as the number of training tokens, model size and bit width. With the derived scaling laws, we propose a novel perspective that we can use QiD to measure an LLM's training levels and determine the number of training tokens required for fully training LLMs of various sizes. Moreover, we use the scaling laws to predict the quantization performance of different-sized LLMs trained with 100 trillion tokens. Our projection shows that the low-bit quantization performance of future models, which are expected to be trained with over 100 trillion tokens, may NOT be desirable. This poses a potential challenge for low-bit quantization in the future and highlights the need for awareness of a model's training level when evaluating low-bit quantization research. To facilitate future research on this problem, we release all the 1500+ quantized checkpoints used in this work at https://huggingface.co/Xu-Ouyang.

cs.LG↗

arXiv2023

Efficient NLP Model Finetuning via Multistage Data Filtering

As model finetuning is central to the modern NLP, we set to maximize its efficiency. Motivated by redundancy in training examples and the sheer sizes of pretrained models, we exploit a key opportunity: training only on important data. To this end, we set to filter training examples in a streaming fashion, in tandem with training the target model. Our key techniques are two: (1) automatically determine a training loss threshold for skipping backward training passes; (2) run a meta predictor for further skipping forward training passes. We integrate the above techniques in a holistic, three-stage training process. On a diverse set of benchmarks, our method reduces the required training examples by up to 5.3$\times$ and training time by up to 6.8$\times$, while only seeing minor accuracy degradation. Our method is effective even when training one epoch, where each training example is encountered only once. It is simple to implement and is compatible with the existing finetuning techniques. Code is available at: https://github.com/xo28/efficient- NLP-multistage-training

cs.CL↗

arXiv2022

e-G2C: A 0.14-to-8.31 $μ$J/Inference NN-based Processor with Continuous On-chip Adaptation for Anomaly Detection and ECG Conversion from EGM

This work presents the first silicon-validated dedicated EGM-to-ECG (G2C) processor, dubbed e-G2C, featuring continuous lightweight anomaly detection, event-driven coarse/precise conversion, and on-chip adaptation. e-G2C utilizes neural network (NN) based G2C conversion and integrates 1) an architecture supporting anomaly detection and coarse/precise conversion via time multiplexing to balance the effectiveness and power, 2) an algorithm-hardware co-designed vector-wise sparsity resulting in a 1.6-1.7$\times$ speedup, 3) hybrid dataflows for enhancing near 100% utilization for normal/depth-wise(DW)/point-wise(PW) convolutions (Convs), and 4) an on-chip detection threshold adaptation engine for continuous effectiveness. The achieved 0.14-8.31 $μ$J/inference energy efficiency outperforms prior arts under similar complexity, promising real-time detection/conversion and possibly life-critical interventions

eess.SP↗

arXiv2021

Generating tightly focused perfect optical vortex for ultra-secure optical encryption

Light's orbital angular momentum (OAM) with inherent mode orthogonality has been suggested as a new way to the optical encryption. However, the dependence of annular intensity profiles on the topological charge complicates nanoscale light-matter interactions and hampers the ultra-secure encryption application. In this paper, we demonstrate ultra-secure image encryption by tightly focusing perfect optical vortex (POV) beams with controllable annular intensity profiles and OAM states. A simple scheme composed of single spatial light modulator is proposed to generate radius-controllable POV in tightly focused beams. Such focused POV beams with identical intensity profiles but varied OAM states are applied to disorder-coupled gold nanorod aggregates to selectively excite electromagnetic hot spots for encoding information through photothermal deformation. As such, ultra-secure image encryption in OAM states of POV beams in combination with different polarizations can be achieved. Our results lay the ground for diverse nanophotonic applications harnessing the OAM division of POV beams.

physics.optics↗

arXiv2021

Semi-supervised Domain Adaptation for Semantic Segmentation

Deep learning approaches for semantic segmentation rely primarily on supervised learning approaches and require substantial efforts in producing pixel-level annotations. Further, such approaches may perform poorly when applied to unseen image domains. To cope with these limitations, both unsupervised domain adaptation (UDA) with full source supervision but without target supervision and semi-supervised learning (SSL) with partial supervision have been proposed. While such methods are effective at aligning different feature distributions, there is still a need to efficiently exploit unlabeled data to address the performance gap with respect to fully-supervised methods. In this paper we address semi-supervised domain adaptation (SSDA) for semantic segmentation, where a large amount of labeled source data as well as a small amount of labeled target data are available. We propose a novel and effective two-step semi-supervised dual-domain adaptation (SSDDA) approach to address both cross- and intra-domain gaps in semantic segmentation. The proposed framework is comprised of two mixing modules. First, we conduct a cross-domain adaptation via an image-level mixing strategy, which learns to align the distribution shift of features between the source data and target data. Second, intra-domain adaptation is achieved using a separate student-teacher network which is built to generate category-level data augmentation by mixing unlabeled target data in a way that respects predicted object boundaries. We demonstrate that the proposed approach outperforms state-of-the-art methods on two common synthetic-to-real semantic segmentation benchmarks. An extensive ablation study is provided to further validate the effectiveness of our approach.

cs.CV↗

arXiv2021

Cylindrical vector beams reveal radiationless anapole condition in a resonant state

Nonscattering optical anapole condition is corresponding to the excitation of radiationless field distributions in open resonators, which offers new degrees of freedom for tailoring light-matter interaction. Conventional mechanisms for achieving such a condition relies on sophisticated manipulation of electromagnetic multipolar moments of all orders to guarantee superpositions of vanished moment strengths at the same wavelength. In contrast, here we report on the excitation of optical radiationless anapole hidden in a resonant state of a Si nanoparticle utilizing tightly focused radially polarized (RP) beam. The coexistence of magnetic resonant state and anapole condition at the same wavelength further enables the triggering of resonant state by tightly focused azimuthally polarized (AP) beam whose corresponding electric multipole coefficient could be zero. As a result, high contrast inter-transition between radiationless anapole condition and ideal magnetic resonant scattering can be achieved experimentally in visible spectrum. The proposed mechanism is general which can be realized in different types of nanostructures. Our results showcase that the unique combination of structured light and structured Mie resonances could provide new degrees of freedom for tailoring light-matter interaction, which might shed new light on functional meta-optics.

physics.optics↗

arXiv2021

"BNN - BN = ?": Training Binary Neural Networks without Batch Normalization

Batch normalization (BN) is a key facilitator and considered essential for state-of-the-art binary neural networks (BNN). However, the BN layer is costly to calculate and is typically implemented with non-binary parameters, leaving a hurdle for the efficient implementation of BNN training. It also introduces undesirable dependence between samples within each batch. Inspired by the latest advance on Batch Normalization Free (BN-Free) training, we extend their framework to training BNNs, and for the first time demonstrate that BNs can be completed removed from BNN training and inference regimes. By plugging in and customizing techniques including adaptive gradient clipping, scale weight standardization, and specialized bottleneck block, a BN-free BNN is capable of maintaining competitive accuracy compared to its BN-based counterpart. Extensive experiments validate the effectiveness of our proposal across diverse BNN backbones and datasets. For example, after removing BNs from the state-of-the-art ReActNets, it can still be trained with our proposed methodology to achieve 92.08%, 68.34%, and 68.0% accuracy on CIFAR-10, CIFAR-100, and ImageNet respectively, with marginal performance drop (0.23%~0.44% on CIFAR and 1.40% on ImageNet). Codes and pre-trained models are available at: https://github.com/VITA-Group/BNN_NoBN.

cs.LG↗

arXiv2021

Near-perfect fidelity polarization-encoded multilayer optical data storage based on aligned gold nanorods

Encoding information in light polarization is of great importance in facilitating optical data storage (ODS) for information security and data storage capacity escalation. However, despite recent advances in nanophotonic techniques vastly enhancing the feasibility of applying polarization channels, the data fidelity in reconstructed bits has been constrained by severe crosstalks occurring between varied polarization angles during data recording and reading process, which gravely hindered the utilization of this technique in practice. In this paper, we demonstrate an ultra-low crosstalk polarization-encoding multilayer optical data storage technique for high-fidelity data recording and retrieving by utilizing a nanofibre-based nanocomposite film involving highly aligned gold nanorods (GNRs). With parallelizing the gold nanorods in the recording medium, the information carrier configuration minimizes miswriting and misreading possibilities for information input and output, respectively, compared with its randomly self-assembled counterparts. The enhanced data accuracy has significantly improved the bit recall fidelity that is quantified by a correlation coefficient higher than 0.99. It is anticipated that the demonstrated technique can facilitate the development of multiplexing ODS for a greener future.

physics.optics↗

arXiv2021

Mask-based Data Augmentation for Semi-supervised Semantic Segmentation

Semantic segmentation using convolutional neural networks (CNN) is a crucial component in image analysis. Training a CNN to perform semantic segmentation requires a large amount of labeled data, where the production of such labeled data is both costly and labor intensive. Semi-supervised learning algorithms address this issue by utilizing unlabeled data and so reduce the amount of labeled data needed for training. In particular, data augmentation techniques such as CutMix and ClassMix generate additional training data from existing labeled data. In this paper we propose a new approach for data augmentation, termed ComplexMix, which incorporates aspects of CutMix and ClassMix with improved performance. The proposed approach has the ability to control the complexity of the augmented data while attempting to be semantically-correct and address the tradeoff between complexity and correctness. The proposed ComplexMix approach is evaluated on a standard dataset for semantic segmentation and compared to other state-of-the-art techniques. Experimental results show that our method yields improvement over state-of-the-art methods on standard datasets for semantic image segmentation.

cs.CV↗