arXiv subjects

Yi Ren

Publications and source records attributed to Yi Ren.

At least 55 records · Page 3Linked to original sources

arXiv2025

ASGO: Adaptive Structured Gradient Optimization

Training deep neural networks is a structured optimization problem, because the parameters are naturally represented by matrices and tensors rather than by vectors. Under this structural representation, it has been widely observed that gradients are low-rank and Hessians are approximately block diagonal. These structured properties are crucial for designing efficient optimization algorithms, but are not utilized by many current popular optimizers like Adam. In this paper, we present a novel optimization algorithm ASGO that capitalizes on these properties by employing a preconditioner that is adaptively updated using structured gradients. By a fine-grained theoretical analysis, ASGO is proven to achieve superior convergence rates compared to existing structured gradient methods. Based on this convergence theory, we further demonstrate that ASGO can benefit from low-rank gradients and block diagonal Hessians. We also discuss practical modifications of ASGO and empirically verify ASGO's effectiveness on language model tasks. Code is available at https://github.com/infinity-stars/ASGO.

cs.LG↗

arXiv2025

Falcon: A Remote Sensing Vision-Language Foundation Model (Technical Report)

This paper introduces a holistic vision-language foundation model tailored for remote sensing, named Falcon. Falcon offers a unified, prompt-based paradigm that effectively executes comprehensive and complex remote sensing tasks. Falcon demonstrates powerful understanding and reasoning abilities at the image, region, and pixel levels. Specifically, given simple natural language instructions and remote sensing images, Falcon can produce impressive results in text form across 14 distinct tasks, i.e., image classification, object detection, segmentation, image captioning, and etc. To facilitate Falcon's training and empower its representation capacity to encode rich spatial and semantic information, we developed Falcon_SFT, a large-scale, multi-task, instruction-tuning dataset in the field of remote sensing. The Falcon_SFT dataset consists of approximately 78 million high-quality data samples, covering 5.6 million multi-spatial resolution and multi-view remote sensing images with diverse instructions. It features hierarchical annotations and undergoes manual sampling verification to ensure high data quality and reliability. Extensive comparative experiments are conducted, which verify that Falcon achieves remarkable performance over 67 datasets and 14 tasks, despite having only 0.7B parameters. We release the complete dataset, code, and model weights at https://github.com/TianHuiLab/Falcon, hoping to help further develop the open-source community.

cs.CV↗

arXiv2025

Measuring Star Formation Histories from Asymptotic Giant Branch Stars I: A Demonstration in M31

We demonstrate how near-infrared (NIR) imaging of resolved luminous asymptotic giant branch (AGB) stars can be used to measure well-constrained star formation histories (SFHs) across cosmic time. Using UKIRT $J$ and $K$-band imaging of M31, we first show excellent agreement over the past $\sim8$ Gyr between the PHAT SFH of M31's outer disk derived from a deep optical color-magnitude diagram (CMD; $\sim3.3\times10^{7}$ stars with $M_{\rm F814W} \lesssim +2$), and our spatially-matched SFH based only on modeling AGB stars on a NIR CMD ($\sim7.7\times10^{3}$ stars with $M_{\rm J} \lesssim -6$). We find that only $\sim1000$ AGB stars are needed for reliable SFH recovery, owing to their excellent age sensitivity in the NIR. We then measure the spatially-resolved SFH of M31's inner stellar halo ($D_{\rm M31, projected} \sim20-30$ kpc) using $\sim10^4$ AGB stars. We find: (i) a dominant burst of star formation across M31's stellar halo $3-5$ Gyr ago and lower level, spatially distributed star formation $\sim1-3$ Gyr ago; (ii) $M_{\star}\approx3_{-1}^{+5}\times10^9 M_{\odot}$ formed over the past $\sim8$ Gyr. We discuss some caveats and the enormous potential of resolved AGB stars in the NIR for measuring SFHs back to ancient epochs ($\sim14$ Gyr ago) in galaxies to large distances ($D\gtrsim20$ Mpc) with JWST, Roman, and Euclid.

astro-ph.GA↗

arXiv2025

LightSAE: Parameter-Efficient and Heterogeneity-Aware Embedding for IoT Multivariate Time Series Forecasting

Modern Internet of Things (IoT) systems generate massive, heterogeneous multivariate time series data. Accurate Multivariate Time Series Forecasting (MTSF) of such data is critical for numerous applications. However, existing methods almost universally employ a shared embedding layer that processes all channels identically, creating a representational bottleneck that obscures valuable channel-specific information. To address this challenge, we introduce a Shared-Auxiliary Embedding (SAE) framework that decomposes the embedding into a shared base component capturing common patterns and channel-specific auxiliary components modeling unique deviations. Within this decomposition, we \rev{empirically observe} that the auxiliary components tend to exhibit low-rank and clustering characteristics, a structural pattern that is significantly less apparent when using purely independent embeddings. Consequently, we design LightSAE, a parameter-efficient embedding module that operationalizes these observed characteristics through low-rank factorization and a shared, gated component pool. Extensive experiments across 9 IoT-related datasets and 4 backbone architectures demonstrate LightSAE's effectiveness, achieving MSE improvements of up to 22.8\% with only 4.0\% parameter increase.

cs.LG↗

arXiv2025

UnifiedRL: A Reinforcement Learning Algorithm Tailored for Multi-Task Fusion in Large-Scale Recommender Systems

As the last pivotal stage of Recommender System (RS), Multi-Task Fusion (MTF) is responsible for combining multiple scores outputted by Multi-Task Learning (MTL) model into a final score to maximize user satisfaction. Recently, to optimize long-term user satisfaction, Reinforcement Learning (RL) is used for MTF in RSs. However, the existing offline RL algorithms used for MTF have the following severe problems: a) To avoid Out-of-Distribution (OOD), their constraints are overly strict, which seriously damage performance; b) They are unaware of the exploration policy used to collect training data, only suboptimal policy can be learned; c) Their exploration policies are inefficient and hurt user experience. To solve the above problems, we propose an innovative method called UnifiedRL tailored for MTF in large-scale RSs. UnifiedRL seamlessly integrates offline RL model with its custom exploration policy to relax overly strict constraints, which is different from existing RL-MTF methods and significantly improves performance. In addition, compared to existing exploration policies, UnifiedRL's custom exploration policy is highly efficient, enabling frequent online exploration and offline training iterations, which further improves performance. Extensive offline and online experiments are conducted in a large-scale RS. The results demonstrate that UnifiedRL outperforms other existing MTF methods remarkably, achieving a +4.64% increase in user valid consumption and a +1.74% increase in user duration time. To the best of our knowledge, UnifiedRL is the first RL algorithm tailored for MTF in RSs and has been successfully deployed in multiple large-scale RSs since June 2023, yielding significant benefits.

cs.IR↗

arXiv2025

Dynamic User Interest Augmentation via Stream Clustering and Memory Networks in Large-Scale Recommender Systems

Recommender System (RS) provides personalized recommendation service based on user interest. However, lots of users' interests are sparse due to lacking consumption behaviors, making it challenging to provide accurate recommendations for them, which is widespread in large-scale RSs. In particular, efficiently solving this problem in the ranking stage of RS is an even greater challenge, which requires an end-to-end and real-time approach. To solve this problem, we propose an innovative method called Dynamic User Interest Augmentation (DUIA). DUIA enhances user interest including user profile and user history behavior sequences by generating enhancement vectors and personalized enhancement vectors through dynamic stream clustering of similar users and relevant items from multiple perspectives. To realize stream clustering, we specially design an algorithm called Gradient-based Hierarchical Clustering Algorithm (GHCA) for DUIA, which performs clustering via gradient descent and stores the cluster centers in memory networks. Extensive offline and online experiments demonstrate that DUIA not only significantly improves model performance for users with sparse interests but also delivers notable gains for other users. As an end-to-end method, DUIA can be easily integrated with existing models. Furthermore, DUIA is also used for long-tail items and cold-start problem, which also yields excellent improvements. Since 2022, DUIA has been successfully deployed in multiple industrial RSs in Tencent and was made public in May 2024. Moreover, the thoughts behind DUIA, dynamic stream clustering and similarity-based enhancement, have inspired relevant works and have also been applied in other stages of RS.

cs.IR↗

arXiv2025

Learning Dynamics of Deep Learning -- Force Analysis of Deep Neural Networks

This thesis explores how deep learning models learn over time, using ideas inspired by force analysis. Specifically, we zoom in on the model's training procedure to see how one training example affects another during learning, like analyzing how forces move objects. We break this influence into two parts: how similar the two examples are, and how strong the updating force is. This framework helps us understand a wide range of the model's behaviors in different real systems. For example, it explains why certain examples have non-trivial learning paths, why (and why not) some LLM finetuning methods work, and why simpler, more structured patterns tend to be learned more easily. We apply this approach to various learning tasks and uncover new strategies for improving model training. While the method is still developing, it offers a new way to interpret models' behaviors systematically.

cs.LG↗

arXiv2025

AC-Refiner: Efficient Arithmetic Circuit Optimization Using Conditional Diffusion Models

Arithmetic circuits, such as adders and multipliers, are fundamental components of digital systems, directly impacting the performance, power efficiency, and area footprint. However, optimizing these circuits remains challenging due to the vast design space and complex physical constraints. While recent deep learning-based approaches have shown promise, they struggle to consistently explore high-potential design variants, limiting their optimization efficiency. To address this challenge, we propose AC-Refiner, a novel arithmetic circuit optimization framework leveraging conditional diffusion models. Our key insight is to reframe arithmetic circuit synthesis as a conditional image generation task. By carefully conditioning the denoising diffusion process on target quality-of-results (QoRs), AC-Refiner consistently produces high-quality circuit designs. Furthermore, the explored designs are used to fine-tune the diffusion model, which focuses the exploration near the Pareto frontier. Experimental results demonstrate that AC-Refiner generates designs with superior Pareto optimality, outperforming state-of-the-art baselines. The performance gain is further validated by integrating AC-Refiner into practical applications.

cs.AR↗

arXiv2025

Orthrus: Dual-Loop Automated Framework for System-Technology Co-Optimization

With the diminishing return from Moore's Law, system-technology co-optimization (STCO) has emerged as a promising approach to sustain the scaling trends in the VLSI industry. By bridging the gap between system requirements and technology innovations, STCO enables customized optimizations for application-driven system architectures. However, existing research lacks sufficient discussion on efficient STCO methodologies, particularly in addressing the information gap across design hierarchies and navigating the expansive cross-layer design space. To address these challenges, this paper presents Orthrus, a dual-loop automated framework that synergizes system-level and technology-level optimizations. At the system level, Orthrus employs a novel mechanism to prioritize the optimization of critical standard cells using system-level statistics. It also guides technology-level optimization via the normal directions of the Pareto frontier efficiently explored by Bayesian optimization. At the technology level, Orthrus leverages system-aware insights to optimize standard cell libraries. It employs a neural network-assisted enhanced differential evolution algorithm to efficiently optimize technology parameters. Experimental results on 7nm technology demonstrate that Orthrus achieves 12.5% delay reduction at iso-power and 61.4% power savings at iso-delay over the baseline approaches, establishing new Pareto frontiers in STCO.

cs.AR↗

arXiv2025

Shape control of simulated multi-segment continuum robots via Koopman operators with per-segment projection

Soft continuum robots can allow for biocompatible yet compliant motions, such as the ability of octopus arms to swim, crawl, and manipulate objects. However, current state-of-the-art continuum robots can only achieve real-time task-space control (i.e., tip control) but not whole-shape control, mainly due to the high computational cost from its infinite degrees of freedom. In this paper, we present a data-driven Koopman operator-based approach for the shape control of simulated multi-segment tendon-driven soft continuum robots with the Kirchhoff rod model. Using data collected from these simulated soft robots, we conduct a per-segment projection scheme on the state of the robots allowing for the identification of control-affine Koopman models that are an order of magnitude more accurate than without the projection scheme. Using these learned Koopman models, we use a linear model predictive control (MPC) to control the robots to a collection of target shapes of varying complexity. Our method realizes computationally efficient closed-loop control, and demonstrates the feasibility of real-time shape control for soft robots. We envision this work can pave the way for practical shape control of soft continuum robots.

cs.RO↗

arXiv2025

Physics-informed Split Koopman Operators for Data-efficient Soft Robotic Simulation

Koopman operator theory provides a powerful data-driven technique for modeling nonlinear dynamical systems in a linear framework, in comparison to computationally expensive and highly nonlinear physics-based simulations. However, Koopman operator-based models for soft robots are very high dimensional and require considerable amounts of data to properly resolve. Inspired by physics-informed techniques from machine learning, we present a novel physics-informed Koopman operator identification method that improves simulation accuracy for small dataset sizes. Through Strang splitting, the method takes advantage of both continuous and discrete Koopman operator approximation to obtain information both from trajectory and phase space data. The method is validated on a tendon-driven soft robotic arm, showing orders of magnitude improvement over standard methods in terms of the shape error. We envision this method can significantly reduce the data requirement of Koopman operators for systems with partially known physical models, and thus reduce the cost of obtaining data.

cs.RO↗

arXiv2025

FAMES: Fast Approximate Multiplier Substitution for Mixed-Precision Quantized DNNs--Down to 2 Bits!

A widely-used technique in designing energy-efficient deep neural network (DNN) accelerators is quantization. Recent progress in this direction has reduced the bitwidths used in DNN down to 2. Meanwhile, many prior works apply approximate multipliers (AppMuls) in designing DNN accelerators to lower their energy consumption. Unfortunately, these works still assume a bitwidth much larger than 2, which falls far behind the state-of-the-art in quantization area and even challenges the meaningfulness of applying AppMuls in DNN accelerators, since a high-bitwidth AppMul consumes much more energy than a low-bitwidth exact multiplier! Thus, an important problem to study is: Can approximate multipliers be effectively applied to quantized DNN models with very low bitwidths? In this work, we give an affirmative answer to this question and present a systematic solution that achieves the answer: FAMES, a fast approximate multiplier substitution method for mixed-precision DNNs. Our experiments demonstrate an average 28.67% energy reduction on state-of-the-art mixed-precision quantized models with bitwidths as low as 2 bits and accuracy losses kept under 1%. Additionally, our approach is up to 300x faster than previous genetic algorithm-based methods.

cs.LG↗

arXiv2025

InfinityHuman: Towards Long-Term Audio-Driven Human

Audio-driven human animation has attracted wide attention thanks to its practical applications. However, critical challenges remain in generating high-resolution, long-duration videos with consistent appearance and natural hand motions. Existing methods extend videos using overlapping motion frames but suffer from error accumulation, leading to identity drift, color shifts, and scene instability. Additionally, hand movements are poorly modeled, resulting in noticeable distortions and misalignment with the audio. In this work, we propose InfinityHuman, a coarse-to-fine framework that first generates audio-synchronized representations, then progressively refines them into high-resolution, long-duration videos using a pose-guided refiner. Since pose sequences are decoupled from appearance and resist temporal degradation, our pose-guided refiner employs stable poses and the initial frame as a visual anchor to reduce drift and improve lip synchronization. Moreover, to enhance semantic accuracy and gesture realism, we introduce a hand-specific reward mechanism trained with high-quality hand motion data. Experiments on the EMTD and HDTF datasets show that InfinityHuman achieves state-of-the-art performance in video quality, identity preservation, hand accuracy, and lip-sync. Ablation studies further confirm the effectiveness of each module. Code will be made public.

cs.CV↗

arXiv2025

Towards Enhancing Data Equity in Public Health Data Science

Data-driven decisions shape public health policies and practice, yet persistent disparities in data representation skew insights and undermine interventions. To address this, we advance a structured roadmap that integrates public health data science with computer science and is grounded in reflexivity. We adopt data equity as a guiding concept: ensuring the fair and inclusive representation, collection, and use of data to prevent the introduction or exacerbation of systemic biases that could lead to invalid downstream inference and decisions. To underscore urgency, we present three public health cases where non-representative datasets and skewed knowledge impede decisions across diverse subgroups. These challenges echo themes in two literatures: public health highlights gaps in high-quality data for specific populations, while computer science and statistics contribute criteria and metrics for diagnosing bias in data and models. Building on these foundations, we propose a working definition of public health data equity and a structured self-audit framework. Our framework integrates core computational principles (fairness, accountability, transparency, ethics, privacy, confidentiality) with key public health considerations (selection bias, representativeness, generalizability, causality, information bias) to guide equitable practice across the data life cycle, from study design and data collection to measurement, analysis, interpretation, and translation. Embedding data equity in routine practice offers a practical path for ensuring that data-driven policies, artificial intelligence, and emerging technologies improve health outcomes for all. Finally, we emphasize the critical understanding that, although data equity is an essential first step, it does not inherently guarantee information, learning, or decision equity.

stat.AP↗

arXiv2025

Neural Contrast Expansion for Explainable Structure-Property Prediction and Random Microstructure Design

Effective properties of composite materials are defined as the ensemble average of property-specific PDE solutions over the underlying microstructure distributions. Traditionally, predicting such properties can be done by solving PDEs derived from microstructure samples or building data-driven models that directly map microstructure samples to properties. The former has a higher running cost, but provides explainable sensitivity information that may guide material design; the latter could be more cost-effective if the data overhead is amortized, but its learned sensitivities are often less explainable. With a focus on properties governed by linear self-adjoint PDEs (e.g., Laplace, Helmholtz, and Maxwell curl-curl) defined on bi-phase microstructures, we propose a structure-property model that is both cost-effective and explainable. Our method is built on top of the strong contrast expansion (SCE) formalism, which analytically maps $N$-point correlations of an unbounded random field to its effective properties. Since real-world material samples have finite sizes and analytical PDE kernels are not always available, we propose Neural Contrast Expansion (NCE), an SCE-inspired architecture to learn surrogate PDE kernels from structure-property data. For static conduction and electromagnetic wave propagation cases, we show that NCE models reveal accurate and insightful sensitivity information useful for material design. Compared with other PDE kernel learning methods, our method does not require measurements about the PDE solution fields, but rather only requires macroscopic property measurements that are more accessible in material development contexts.

cs.LG↗

arXiv2025

UniTalker: Conversational Speech-Visual Synthesis

Conversational Speech Synthesis (CSS) is a key task in the user-agent interaction area, aiming to generate more expressive and empathetic speech for users. However, it is well-known that "listening" and "eye contact" play crucial roles in conveying emotions during real-world interpersonal communication. Existing CSS research is limited to perceiving only text and speech within the dialogue context, which restricts its effectiveness. Moreover, speech-only responses further constrain the interactive experience. To address these limitations, we introduce a Conversational Speech-Visual Synthesis (CSVS) task as an extension of traditional CSS. By leveraging multimodal dialogue context, it provides users with coherent audiovisual responses. To this end, we develop a CSVS system named UniTalker, which is a unified model that seamlessly integrates multimodal perception and multimodal rendering capabilities. Specifically, it leverages a large-scale language model to comprehensively understand multimodal cues in the dialogue context, including speaker, text, speech, and the talking-face animations. After that, it employs multi-task sequence prediction to first infer the target utterance's emotion and then generate empathetic speech and natural talking-face animations. To ensure that the generated speech-visual content remains consistent in terms of emotion, content, and duration, we introduce three key optimizations: 1) Designing a specialized neural landmark codec to tokenize and reconstruct facial expression sequences. 2) Proposing a bimodal speech-visual hard alignment decoding strategy. 3) Applying emotion-guided rendering during the generation stage. Comprehensive objective and subjective experiments demonstrate that our model synthesizes more empathetic speech and provides users with more natural and emotionally consistent talking-face animations.

eess.AS↗

arXiv2025

HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation

Human motion video generation has advanced significantly, while existing methods still struggle with accurately rendering detailed body parts like hands and faces, especially in long sequences and intricate motions. Current approaches also rely on fixed resolution and struggle to maintain visual consistency. To address these limitations, we propose HumanDiT, a pose-guided Diffusion Transformer (DiT)-based framework trained on a large and wild dataset containing 14,000 hours of high-quality video to produce high-fidelity videos with fine-grained body rendering. Specifically, (i) HumanDiT, built on DiT, supports numerous video resolutions and variable sequence lengths, facilitating learning for long-sequence video generation; (ii) we introduce a prefix-latent reference strategy to maintain personalized characteristics across extended sequences. Furthermore, during inference, HumanDiT leverages Keypoint-DiT to generate subsequent pose sequences, facilitating video continuation from static images or existing videos. It also utilizes a Pose Adapter to enable pose transfer with given sequences. Extensive experiments demonstrate its superior performance in generating long-form, pose-accurate videos across diverse scenarios.

cs.CV↗

arXiv2025

Successor Features for Transfer in Alternating Markov Games

This paper explores successor features for knowledge transfer in zero-sum, complete-information, and turn-based games. Prior research in single-agent systems has shown that successor features can provide a ``jump start" for agents when facing new tasks with varying reward structures. However, knowledge transfer in games typically relies on value and equilibrium transfers, which heavily depends on the similarity between tasks. This reliance can lead to failures when the tasks differ significantly. To address this issue, this paper presents an application of successor features to games and presents a novel algorithm called Game Generalized Policy Improvement (GGPI), designed to address Markov games in multi-agent reinforcement learning. The proposed algorithm enables the transfer of learning values and policies across games. An upper bound of the errors for transfer is derived as a function the similarity of the task. Through experiments with a turn-based pursuer-evader game, we demonstrate that the GGPI algorithm can generate high-reward interactions and one-shot policy transfer. When further tested in a wider set of initial conditions, the GGPI algorithm achieves higher success rates with improved path efficiency compared to those of the baseline algorithms.

cs.MA↗