arXiv subjects

Dong Yin

Publications and source records attributed to Dong Yin.

At least 19 recordsLinked to original sources

arXiv2026

Implementation Risk in Portfolio Backtesting: A Previously Unquantified Source of Error

Portfolio backtesting is the primary tool for evaluating investment strategies before deployment, yet practitioners implicitly assume that different engines produce identical results for the same strategy. we formalise implementation risk, the systematic divergence in backtested portfolio metrics arising solely from differences in how engines implement the same logical strategy, and propose four metrics grounded in metrology to quantify it: engine sensitivity, implementation uncertainty interval, divergence amplification factor, and conclusion stability index. we execute 15 benchmark strategies through five independent open-source engines on 30 non-overlapping stratified asset buckets comprising 180 s&p 500 stocks under four transaction-cost regimes. at zero cost, all five engines agree exactly (maximum divergence 0.000%), isolating transaction-cost implementation as the sole source of disagreement. under nonzero costs, divergence is structured and predictable (spearman rho = 0.93 with cost intensity), remaining below 0.75 percentage points for most strategies but reaching 3.71% for high-turnover rotation strategies. source-code forensics uncovered seven previously undocumented defects across three engines, abstracted into a five-category failure-mode taxonomy. all engines agree on the sign of every performance metric (conclusion stability index = 1), so implementation risk does not alter investment decisions for the strategies studied but introduces measurable ambiguity in performance attribution. code and benchmark data are publicly available.

q-fin.PM↗

arXiv2025

RLAX: Large-Scale, Distributed Reinforcement Learning for Large Language Models on TPUs

Reinforcement learning (RL) has emerged as the de-facto paradigm for improving the reasoning capabilities of large language models (LLMs). We have developed RLAX, a scalable RL framework on TPUs. RLAX employs a parameter-server architecture. A master trainer periodically pushes updated model weights to the parameter server while a fleet of inference workers pull the latest weights and generates new rollouts. We introduce a suite of system techniques to enable scalable and preemptible RL for a diverse set of state-of-art RL algorithms. To accelerate convergence and improve model quality, we have devised new dataset curation and alignment techniques. Large-scale evaluations show that RLAX improves QwQ-32B's pass@8 accuracy by 12.8% in just 12 hours 48 minutes on 1024 v5p TPUs, while remaining robust to preemptions during training.

cs.LG↗

arXiv2025

Bridging the genotype-phenotype gap with generative artificial intelligence

The genotype-phenotype gap is a persistent barrier to complex trait genetic dissection, worsened by the explosive growth of genomic data (1.5 billion variants identified in the UK Biobank WGS study) alongside persistently scarce and subjective human-defined phenotypes. Digital phenotyping offers a potential solution, yet existing tools fail to balance scalable non-manual phenotype generation and biological interpretability of these quantitative traits. Here we report AIPheno, the first generative AI-driven "phenotype sequencer" that bridges this gap. It enables high-throughput, unsupervised extraction of digital phenotypes from imaging data and unlocks their biological meaning via generative network analysis. AIPheno transforms imaging modalities into a rich source of quantitative traits, dramatically enhancing cross-species genetic discovery, including novel loci such as CCBE1 (humans), KITLG-TMTC3 (domestic pigeons), and SOD2-IGF2R (swine). Critically, its generative module decodes AI-derived phenotypes by synthesizing variant-specific images to yield actionable biological insights. For example, it clarifies how the OCA2-HERC2 locus pleiotropically links pigmentation to retinal vascular traits via vascular visibility modulation. Integrating scalable non-manual phenotyping, enhanced genetic discovery power, and generative mechanistic decoding, AIPheno establishes a transformative closed-loop paradigm. This work addresses the longstanding genotype-phenotype imbalance, redefines digital phenotype utility, and accelerates translation of genetic associations into actionable understanding with profound implications for human health and agriculture.

q-bio.QM↗

arXiv2025

IL3D: A Large-Scale Indoor Layout Dataset for LLM-Driven 3D Scene Generation

In this study, we present IL3D, a large-scale dataset meticulously designed for large language model (LLM)-driven 3D scene generation, addressing the pressing demand for diverse, high-quality training data in indoor layout design. Comprising 27,816 indoor layouts across 18 prevalent room types and a library of 29,215 high-fidelity 3D object assets, IL3D is enriched with instance-level natural language annotations to support robust multimodal learning for vision-language tasks. We establish rigorous benchmarks to evaluate LLM-driven scene generation. Experimental results show that supervised fine-tuning (SFT) of LLMs on IL3D significantly improves generalization and surpasses the performance of SFT on other datasets. IL3D offers flexible multimodal data export capabilities, including point clouds, 3D bounding boxes, multiview images, depth maps, normal maps, and semantic masks, enabling seamless adaptation to various visual tasks. As a versatile and robust resource, IL3D significantly advances research in 3D scene generation and embodied intelligence, by providing high-fidelity scene data to support environment perception tasks of embodied agents.

cs.CV↗

arXiv2025

Apple Intelligence Foundation Language Models: Tech Report 2025

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations such as KV-cache sharing and 2-bit quantization-aware training; and ii a scalable server model built on a novel Parallel-Track Mixture-of-Experts PT-MoE transformer that combines track parallelism, mixture-of-experts sparse computation, and interleaved global-local attention to deliver high quality with competitive cost on Apple's Private Cloud Compute platform. Both models are trained on large-scale multilingual and multimodal datasets sourced via responsible web crawling, licensed corpora, and high-quality synthetic data, then further refined with supervised fine-tuning and reinforcement learning on a new asynchronous platform. The resulting models support several additional languages while understanding images and executing tool calls. In public benchmarks and human evaluations, both the server model and the on-device model match or surpass comparably sized open baselines. A new Swift-centric Foundation Models framework exposes guided generation, constrained tool calling, and LoRA adapter fine-tuning, allowing developers to integrate these capabilities with a few lines of code. The latest advancements in Apple Intelligence models are grounded in our Responsible AI approach with safeguards like content filtering and locale-specific evaluation, as well as our commitment to protecting our users' privacy with innovations like Private Cloud Compute.

cs.LG↗

arXiv2024

SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF

In Large Language Model (LLM) development, Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning models with human values and preferences. RLHF traditionally relies on the Kullback-Leibler (KL) divergence between the current policy and a frozen initial policy as a reference, which is added as a penalty in policy optimization algorithms like Proximal Policy Optimization (PPO). While this constraint prevents models from deviating too far from the initial checkpoint, it limits exploration of the reward landscape, reducing the model's ability to discover higher-quality solutions. As a result, policy optimization is often trapped in a narrow region of the parameter space, leading to suboptimal alignment and performance. This paper presents SALSA (Soup-based Alignment Learning for Stronger Adaptation), a novel approach designed to overcome these limitations by creating a more flexible and better located reference model through weight-space averaging of two independent supervised fine-tuned (SFT) models. This model soup allows for larger deviation in KL divergence and exploring a promising region of the solution space without sacrificing stability. By leveraging this more robust reference model, SALSA fosters better exploration, achieving higher rewards and improving model robustness, out-of-distribution generalization, and performance. We validate the effectiveness of SALSA through extensive experiments on popular open models (Llama2-7B, Mistral-7B, and Gemma-2B) across various benchmarks (MT-Bench, Arena-Hard, UltraFeedback), where it consistently surpasses PPO by fostering deeper exploration and achieving superior alignment in LLMs.

cs.LG↗

arXiv2024

Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo

Augmenting the multi-step reasoning abilities of Large Language Models (LLMs) has been a persistent challenge. Recently, verification has shown promise in improving solution consistency by evaluating generated outputs. However, current verification approaches suffer from sampling inefficiencies, requiring a large number of samples to achieve satisfactory performance. Additionally, training an effective verifier often depends on extensive process supervision, which is costly to acquire. In this paper, we address these limitations by introducing a novel verification method based on Twisted Sequential Monte Carlo (TSMC). TSMC sequentially refines its sampling effort to focus exploration on promising candidates, resulting in more efficient generation of high-quality solutions. We apply TSMC to LLMs by estimating the expected future rewards at partial solutions. This approach results in a more straightforward training target that eliminates the need for step-wise human annotations. We empirically demonstrate the advantages of our method across multiple math benchmarks, and also validate our theoretical analysis of both our approach and existing verification methods.

cs.LG↗

arXiv2024

Apple Intelligence Foundation Language Models

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute. These models are designed to perform a wide range of tasks efficiently, accurately, and responsibly. This report describes the model architecture, the data used to train the model, the training process, how the models are optimized for inference, and the evaluation results. We highlight our focus on Responsible AI and how the principles are applied throughout the model development.

cs.AI↗

arXiv2024

MindSet: Vision. A toolbox for testing DNNs on key psychological experiments

Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision. In almost all cases these benchmarks are observational in the sense they are composed of behavioural and brain responses to naturalistic images that have not been manipulated to test hypotheses regarding how DNNs or humans perceive and identify objects. Here we introduce the toolbox \textit{MindSet: Vision}, consisting of a collection of image datasets and related scripts designed to test DNNs on 30 psychological findings. In all experimental conditions, the stimuli are systematically manipulated to test specific hypotheses regarding human visual perception and object recognition. In addition to providing pre-generated datasets of images, we provide code to regenerate these datasets, offering many configurable parameters which greatly extend the dataset versatility for different research contexts, and code to facilitate the testing of DNNs on these image datasets using three different methods (similarity judgments, out-of-distribution classification, and decoder method), accessible via https://github.com/MindSetVision/MindSetVision. To illustrate the challenges these datasets pose for developing better DNN models of human vision, we test several models on range of datasets included in the toolbox.

cs.CV↗

arXiv2024

Provably Robust Multi-bit Watermarking for AI-generated Text

Large Language Models (LLMs) have demonstrated remarkable capabilities of generating texts resembling human language. However, they can be misused by criminals to create deceptive content, such as fake news and phishing emails, which raises ethical concerns. Watermarking is a key technique to address these concerns, which embeds a message (e.g., a bit string) into a text generated by an LLM. By embedding the user ID (represented as a bit string) into generated texts, we can trace generated texts to the user, known as content source tracing. The major limitation of existing watermarking techniques is that they achieve sub-optimal performance for content source tracing in real-world scenarios. The reason is that they cannot accurately or efficiently extract a long message from a generated text. We aim to address the limitations. In this work, we introduce a new watermarking method for LLM-generated text grounded in pseudo-random segment assignment. We also propose multiple techniques to further enhance the robustness of our watermarking algorithm. We conduct extensive experiments to evaluate our method. Our experimental results show that our method substantially outperforms existing baselines in both accuracy and robustness on benchmark datasets. For instance, when embedding a message of length 20 into a 200-token generated text, our method achieves a match rate of $97.6\%$, while the state-of-the-art work Yoo et al. only achieves $49.2\%$. Additionally, we prove that our watermark can tolerate edits within an edit distance of 17 on average for each paragraph under the same setting.

cs.CR↗

arXiv2023

Sample Efficient Deep Reinforcement Learning via Local Planning

The focus of this work is sample-efficient deep reinforcement learning (RL) with a simulator. One useful property of simulators is that it is typically easy to reset the environment to a previously observed state. We propose an algorithmic framework, named uncertainty-first local planning (UFLP), that takes advantage of this property. Concretely, in each data collection iteration, with some probability, our meta-algorithm resets the environment to an observed state which has high uncertainty, instead of sampling according to the initial-state distribution. The agent-environment interaction then proceeds as in the standard online RL setting. We demonstrate that this simple procedure can dramatically improve the sample cost of several baseline RL algorithms on difficult exploration tasks. Notably, with our framework, we can achieve super-human performance on the notoriously hard Atari game, Montezuma's Revenge, with a simple (distributional) double DQN. Our work can be seen as an efficient approximate implementation of an existing algorithm with theoretical guarantees, which offers an interpretation of the positive empirical results.

cs.LG↗

arXiv2023

Convolutional Neural Networks Trained to Identify Words Provide a Surprisingly Good Account of Visual Form Priming Effects

A wide variety of orthographic coding schemes and models of visual word identification have been developed to account for masked priming data that provide a measure of orthographic similarity between letter strings. These models tend to include hand-coded orthographic representations with single unit coding for specific forms of knowledge (e.g., units coding for a letter in a given position). Here we assess how well a range of these coding schemes and models account for the pattern of form priming effects taken from the Form Priming Project and compare these findings to results observed with 11 standard deep neural network models (DNNs) developed in computer science. We find that deep convolutional networks (CNNs) perform as well or better than the coding schemes and word recognition models, whereas transformer networks did less well. The success of CNNs is remarkable as their architectures were not developed to support word recognition (they were designed to perform well on object recognition), they classify pixel images of words (rather than artificial encodings of letter strings), and their training was highly simplified (not respecting many key aspects of human experience). In addition to these form priming effects, we find that the DNNs can account for visual similarity effects on priming that are beyond all current psychological models of priming. The findings add to the recent work of (Hannagan et al., 2021) and suggest that CNNs should be given more attention in psychology as models of human visual word recognition.

cs.CV↗

arXiv2022

Wide Neural Networks Forget Less Catastrophically

A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the distribution shifts. While the recent progress in continual learning literature is encouraging, our understanding of what properties of neural networks contribute to catastrophic forgetting is still limited. To address this, instead of focusing on continual learning algorithms, in this work, we focus on the model itself and study the impact of "width" of the neural network architecture on catastrophic forgetting, and show that width has a surprisingly significant effect on forgetting. To explain this effect, we study the learning dynamics of the network from various perspectives such as gradient orthogonality, sparsity, and lazy training regime. We provide potential explanations that are consistent with the empirical results across different architectures and continual learning benchmarks.

cs.LG↗

arXiv2022

Morse-STF: Improved Protocols for Privacy-Preserving Machine Learning

Secure multi-party computation enables multiple mutually distrusting parties to perform computations on data without revealing the data itself, and has become one of the core technologies behind privacy-preserving machine learning. In this work, we present several improved privacy-preserving protocols for both linear and non-linear layers in machine learning. For linear layers, we present an extended beaver triple protocol for bilinear maps that significantly reduces communication of convolution layer. For non-linear layers, we introduce novel protocols for computing the sigmoid and softmax function. Both functions are essential building blocks for machine learning training of classification tasks. Our protocols are both more scalable and robust than prior constructions, and improves runtime performance by 3-17x. Finally, we introduce Morse-STF, an end-to-end privacy-preserving system for machine learning training that leverages all these improved protocols. Our system achieves a 1.8x speedup on logistic regression and 3.9-4.9x speedup on convolutional neural networks compared to prior state-of-the-art systems.

cs.CR↗

arXiv2022

Revisiting the Loss Weight Adjustment in Object Detection

Object detection is a typical multi-task learning application, which optimizes classification and regression simultaneously. However, classification loss always dominates the multi-task loss in anchor-based methods, hampering the consistent and balanced optimization of the tasks. In this paper, we find that shifting the bounding boxes can change the division of positive and negative samples in classification, meaning classification depends on regression. Moreover, we summarize three important conclusions about fine-tuning loss weights, considering different datasets, optimizers and regression loss functions. Based on the above conclusions, we propose Adaptive Loss Weight Adjustment(ALWA) to solve the imbalance in optimizing anchor-based methods according to statistical characteristics of losses. By incorporating ALWA into previous state-of-the-art detectors, we achieve a significant performance gain on PASCAL VOC and MS COCO, even with L1, SmoothL1 and CIoU loss. The code is available at https://github.com/ywx-hub/ALWA.

cs.CV↗

arXiv2022

Efficient Local Planning with Linear Function Approximation

We study query and computationally efficient planning algorithms with linear function approximation and a simulator. We assume that the agent only has local access to the simulator, meaning that the agent can only query the simulator at states that have been visited before. This setting is more practical than many prior works on reinforcement learning with a generative model. We propose two algorithms, named confident Monte Carlo least square policy iteration (Confident MC-LSPI) and confident Monte Carlo Politex (Confident MC-Politex) for this setting. Under the assumption that the Q-functions of all policies are linear in known features of the state-action pairs, we show that our algorithms have polynomial query and computational costs in the dimension of the features, the effective planning horizon, and the targeted sub-optimality, while these costs are independent of the size of the state space. One technical contribution of our work is the introduction of a novel proof technique that makes use of a virtual policy iteration algorithm. We use this method to leverage existing results on $\ell_\infty$-bounded approximate policy iteration to show that our algorithm can learn the optimal policy for the given initial state even only with local access to the simulator. We believe that this technique can be extended to broader settings beyond this work.

cs.LG↗

arXiv2022

Architecture Matters in Continual Learning

A large body of research in continual learning is devoted to overcoming the catastrophic forgetting of neural networks by designing new algorithms that are robust to the distribution shifts. However, the majority of these works are strictly focused on the "algorithmic" part of continual learning for a "fixed neural network architecture", and the implications of using different architectures are mostly neglected. Even the few existing continual learning methods that modify the model assume a fixed architecture and aim to develop an algorithm that efficiently uses the model throughout the learning experience. However, in this work, we show that the choice of architecture can significantly impact the continual learning performance, and different architectures lead to different trade-offs between the ability to remember previous tasks and learning new ones. Moreover, we study the impact of various architectural decisions, and our findings entail best practices and recommendations that can improve the continual learning performance.

cs.LG↗

arXiv2021

An Instance-Dependent Simulation Framework for Learning with Label Noise

We propose a simulation framework for generating instance-dependent noisy labels via a pseudo-labeling paradigm. We show that the distribution of the synthetic noisy labels generated with our framework is closer to human labels compared to independent and class-conditional random flipping. Equipped with controllable label noise, we study the negative impact of noisy labels across a few practical settings to understand when label noise is more problematic. We also benchmark several existing algorithms for learning with noisy labels and compare their behavior on our synthetic datasets and on the datasets with independent random label noise. Additionally, with the availability of annotator information from our simulation framework, we propose a new technique, Label Quality Model (LQM), that leverages annotator features to predict and correct against noisy labels. We show that by adding LQM as a label correction step before applying existing noisy label techniques, we can further improve the models' performance.

cs.LG↗