Zhenyu Zhao

Chengzhen Meng, Xiuzhuang Chen, Bingcai Sui et al.

The rapid advancement of AI workloads and domain-specific architectures has led to increasingly diverse processor microarchitectures, whose design exploration requires fast and accurate performance validation. However, traditional workflows defer validation process until RTL design and SoC integration are complete, significantly prolonging development and iteration cycle. In this work, we present FASE framework, FPGA-Assisted Syscall Emulation, the first work for adapt syscall emulation on FPGA platforms, enabling complex multi-thread benchmarks to directly run on the processor design without integrating SoC or target OS for early-stage performance validation. FASE introduces three key innovations to address three critical challenges for adapting FPGA-based syscall emulation: (1) only a minimal CPU interface is exposed, with other hardware components untouched, addressing the lack of a unified hardware interface in FPGA systems; (2) a Host-Target Protocol (HTP) is proposed to minimize cross-device data traffic, mitigating the low-bandwidth and high-latency communication between FPGA and host; and (3) a host-side runtime is proposed to remotely handle Linux-style system calls, addressing the challenge of cross-device syscall delegation. Experiments ware conducted on Xilinx FPGA with open-sourced RISC-V SMP processor Rocket. With single-thread CoreMark, FASE introduces less than 1% performance error and achieves over 2000x higher efficiency compared to Proxy Kernel due to FPGA acceleration. With complex OpenMP benchmarks, FASE demonstrates over 96% performance validation accuracy for most single-thread workloads and over 91.5% for most multi-thread workloads compared to full SoC validation, significantly reducing development complexity and time-to-feedback. All components of FASE framework are released as open-source.

Songlin Wei, Hongyi Jing, Boqian Li et al.

We introduce $Ψ_0$ (Psi-Zero), an open foundation model to address challenging humanoid loco-manipulation tasks. While existing approaches often attempt to address this fundamental problem by co-training on large and diverse human and humanoid data, we argue that this strategy is suboptimal due to the fundamental kinematic and motion disparities between humans and humanoid robots. Therefore, data efficiency and model performance remain unsatisfactory despite the considerable data volume. To address this challenge, \ours\;decouples the learning process to maximize the utility of heterogeneous data sources. Specifically, we propose a staged training paradigm with different learning objectives: First, we autoregressively pre-train a VLM backbone on large-scale egocentric human videos to acquire generalizable visual-action representations. Then, we post-train a flow-based action expert on high-quality humanoid robot data to learn precise robot joint control. Our research further identifies a critical yet often overlooked data recipe: in contrast to approaches that scale with noisy Internet clips or heterogeneous cross-embodiment robot datasets, we demonstrate that pre-training on high-quality egocentric human manipulation data followed by post-training on domain-specific real-world humanoid trajectories yields superior performance. Extensive real-world experiments demonstrate that \ours\ achieves the best performance using only about 800 hours of human video data and 30 hours of real-world robot data, outperforming baselines pre-trained on more than 10$\times$ as much data by over 40\% in overall success rate across multiple tasks. We will open-source the entire ecosystem to the community, including a data processing and training pipeline, a humanoid foundation model, and a real-time action inference engine.

Shen Zhang, Zhaowei Chen, Zhenyu Zhao et al.

Diffusion models have become a mainstream approach for high-resolution image synthesis. However, directly generating higher-resolution images from pretrained diffusion models will encounter unreasonable object duplication and exponentially increase the generation time. In this paper, we discover that object duplication arises from feature duplication in the deep blocks of the U-Net. Concurrently, We pinpoint the extended generation times to self-attention redundancy in U-Net's top blocks. To address these issues, we propose a tuning-free higher-resolution framework named HiDiffusion. Specifically, HiDiffusion contains Resolution-Aware U-Net (RAU-Net) that dynamically adjusts the feature map size to resolve object duplication and engages Modified Shifted Window Multi-head Self-Attention (MSW-MSA) that utilizes optimized window attention to reduce computations. we can integrate HiDiffusion into various pretrained diffusion models to scale image generation resolutions even to 4096x4096 at 1.5-6x the inference speed of previous methods. Extensive experiments demonstrate that our approach can address object duplication and heavy computation issues, achieving state-of-the-art performance on higher-resolution image synthesis tasks.

Liangrui Pan, Jiadi Luo, Yuxuan Xiao et al.

Accurate intraoperative and postoperative diagnosis of spread through air spaces (STAS) is essential for guiding surgical decisions and postoperative management in lung cancer. However, histopathological assessment is labor-intensive and is prone to missed or incorrect diagnoses. We propose a Diffusion Attention Expert Model (DAEM) to detect STAS in frozen sections (FSs) and paraffin sections (PSs). Its diffusion attention expert module leverages full attention aggregation to learn multi-scale features from histopathological images, while a dual-branch architecture strengthens multi-scale feature representation. On an internal dataset, DAEM achieves AUCs of 0.8946 for FSs and 0.9112 for PSs. Validation on external multi-center datasets from eight institutions demonstrates strong generalizability and interpretability. Using tumor microenvironment (TME) features in PSs, we further enable semi-automatic measurement of STAS location and its distance from the primary tumor. Several quantitative TME metrics are identified as potential biomarkers for STAS, including micropapillary-type STAS. Overall, DAEM offers a clinically actionable framework for STAS assessment by enabling accurate and interpretable detection on FSs and PSs, supporting postoperative risk stratification through quantitative TME-based analysis.

Zhenyu Zhao, Yanfei Wang

We propose a patchwise local Fourier extension method for approximating smooth functions on general two dimensional domains with curved boundaries. The domain is embedded into a Cartesian background grid and decomposed into rectangular interior patches and one-side curved trapezoidal boundary patches. After local data transfer, all patches are converted into fixed-size tensor-product arrays and approximated by a truncated-SVD stabilized local Fourier extension procedure. Unlike global Fourier frame approximations, the proposed method localizes both the geometry and the ill-conditioned extension process. For fixed local parameters, the local algebraic operations are performed on fixed-size systems, and the reference Fourier extension matrices and their singular value decompositions are reused across patches. Boundary patches require additional one-dimensional transfer or completion steps, but their costs remain uniformly bounded by the local resolution. Consequently, the online complexity is \(O(N)\), where \(N\) denotes the total number of retained output points for fixed local resolution. Numerical experiments on smooth curved domains and on a mildly rough boundary domain demonstrate that the method achieves high accuracy with a fixed set of local parameters. The smooth-cover correction reduces the boundary-induced error by several orders of magnitude in the full-domain rough-boundary test, without changing the underlying scan-based partition.

Zhenyu Zhao, Yumin Zhang, Totte Harinen et al.

Uplift modeling is a causal learning technique that estimates subgroup-level treatment effects. It is commonly used in industry and elsewhere for tasks such as targeting ads. In a typical setting, uplift models can take thousands of features as inputs, which is costly and results in problems such as overfitting and poor model interpretability. Consequently, there is a need to select a subset of the most important features for modeling. However, traditional methods for doing feature selection are not fit for the task because they are designed for standard machine learning models whose target is importantly different from uplift models. To address this, we introduce a set of feature selection methods explicitly designed for uplift modeling, drawing inspiration from statistics and information theory. We conduct empirical evaluations on the proposed methods on publicly available datasets, demonstrating the advantages of the proposed methods compared to traditional feature selection. We make the proposed methods publicly available as a part of the CausalML open-source package.

Benxue Gong, Zhenyu Zhao, Chenyang Wang

We propose a local Legendre frame (LLF) method for function approximation from equispaced data on a finite interval. Motivated by the difficulty of stable high-order polynomial approximation at equispaced points, especially in the presence of the Runge phenomenon, the method partitions the interval into subintervals, maps each subinterval to a common reference interval, and computes local coefficients by a truncated singular value decomposition (TSVD) regularization. Since all subintervals share the same local sampling matrix, the method admits a natural offline--online implementation. We establish a quasi-optimal estimate for the regularized reconstruction and discuss practical parameter selection. Numerical results show that LLF attains high accuracy for relatively smooth and moderately oscillatory functions, while it remains applicable to highly oscillatory functions, although comparable accuracy generally requires more sampling points. For continuous piecewise smooth functions with derivative singularities, the method also provides an effective detect--localize--correct strategy based on one-sided coefficient-energy indicators. These results indicate that LLF provides a stable and flexible local approximation framework for equispaced data.

Xinran Liu, Zhenyu Zhao, Benxue Gong

We propose a high-precision numerical quadrature framework based on local Fourier extension (LFE) approximations. The method constructs, on each subinterval, a truncated-SVD stabilized local Fourier continuation of the integrand on an extended periodic domain, and then evaluates the integral \emph{analytically} from the resulting Fourier coefficients. Under uniform sampling, the discrete LFE matrix and its TSVD factors are precomputed once and reused across all windows, yielding an efficient offline/online implementation that remains compatible with classical composite rules. We provide an error bound that reduces the quadrature error to the LFE approximation error and derive algebraic convergence rates for Sobolev-regular integrands. Numerical experiments demonstrate that, on smooth functions, the proposed quadrature reaches near machine precision with substantially fewer nodes than the composite Simpson rule. The advantage persists for oscillatory and variable-frequency integrands and becomes more pronounced for nonuniform phase structures. For continuous piecewise smooth integrands, we develop a correction strategy driven by coefficient-energy outliers to identify singularity-containing windows, followed by a localized procedure that brackets the singular point within one grid cell and corrects only the affected window contribution. The corrected quadrature restores near-spectral accuracy in the reported tests, including cases where the singularity is not aligned with the window endpoints.

Zhenyu Zhao, Yexi Jiang

Effective feature selection is essential for optimizing contextual multi-armed bandits (CMABs) in large-scale online systems, where suboptimal features can degrade rewards, interpretability, and efficiency. Traditional feature selection often prioritizes outcome correlation, neglecting the crucial role of heterogeneous treatment effects (HTE) across arms in CMAB decision-making. This paper introduces two novel, model-free filter methods, Heterogeneous Incremental Effect (HIE) and Heterogeneous Distribution Divergence (HDD), specifically designed to identify features driving HTE. HIE quantifies a feature's value based on its ability to induce changes in the optimal arm, while HDD measures its impact on reward distribution divergence across arms. These methods are computationally efficient, robust to model mis-specification, and adaptable to various feature types, making them suitable for rapid screening in dynamic environments where retraining complex models is infeasible. We validate HIE and HDD on synthetic data with known ground truth and in a large-scale commercial recommender system, demonstrating their consistent ability to identify influential HTE features and thereby enhance CMAB performance.

Team Cohere, Aakanksha, Arash Ahmadian et al. · mila

In this report we describe the development of Command A, a powerful large language model purpose-built to excel at real-world enterprise use cases. Command A is an agent-optimised and multilingual-capable model, with support for 23 languages of global business, and a novel hybrid architecture balancing efficiency with top of the range performance. It offers best-in-class Retrieval Augmented Generation (RAG) capabilities with grounding and tool use to automate sophisticated business processes. These abilities are achieved through a decentralised training approach, including self-refinement algorithms and model merging techniques. We also include results for Command R7B which shares capability and architectural similarities to Command A. Weights for both models have been released for research purposes. This technical report details our original training pipeline and presents an extensive evaluation of our models across a suite of enterprise-relevant tasks and public benchmarks, demonstrating excellent performance and efficiency.

Zhenyu Zhao, Sander Land, Dan Bikel et al.

Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We observe that reasoning tokens split into two functional types: low-entropy \textit{structural} tokens (recurring phrases that scaffold the reasoning process) and higher-entropy \textit{organic} tokens (problem-specific content that drives toward a solution). This asymmetry motivates a simple, model-agnostic compression pipeline: apply cross-word BPE merges on a model's own reasoning traces to derive \textit{supertokens} that capture frequent structural patterns, then teach the model to adopt them via supervised fine-tuning. Across three model families and five mathematical reasoning benchmarks, our approach shortens reasoning traces by 8.1\% on average with no statistically significant accuracy loss on any model--benchmark pair. Beyond compression, supertokens act as interpretable reasoning-move annotations (backtracking, verification, strategy shifts), exposing the model's high-level strategy at a glance. Analyzing transitions between structural categories reveals systematic differences between correct and incorrect traces: correct traces show productive recovery (backtracking followed by strategy shifts and verification), while incorrect traces are dominated by confusion cycles (repeated hedging and unresolved contradictions). These diagnostic signals suggest applications in reward shaping and early stopping for RL-based reasoning training.

Shuhong Liu, Chenyu Bao, Ziteng Cui et al.

This paper presents a comprehensive review of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge, detailing the proposed methods and results. The challenge seeks to identify robust reconstruction pipelines that are robust under real-world adverse conditions, specifically extreme low-light and smoke-degraded environments, as captured by our RealX3D benchmark. A total of 279 participants registered for the competition, of whom 33 teams submitted valid results. We thoroughly evaluate the submitted approaches against state-of-the-art baselines, revealing significant progress in 3D reconstruction under adverse conditions. Our analysis highlights shared design principles among top-performing methods and provides insights into effective strategies for handling 3D scene degradation.

Zhenyu Zhao, Aparna Balagopalan, Adi Agrawal et al.

Given the increased use of LLMs in financial systems today, it becomes important to evaluate the safety and robustness of such systems. One failure mode that LLMs frequently display in general domain settings is that of sycophancy. That is, models prioritize agreement with expressed user beliefs over correctness, leading to decreased accuracy and trust. In this work, we focus on evaluating sycophancy that LLMs display in agentic financial tasks. Our findings are three-fold: first, we find the models show only low to modest drops in performance in the face of user rebuttals or contradictions to the reference answer, which distinguishes sycophancy that models display in financial agentic settings from findings in prior work. Second, we introduce a suite of tasks to test for sycophancy by user preference information that contradicts the reference answer and find that most models fail in the presence of such inputs. Lastly, we benchmark different modes of recovery such as input filtering with a pretrained LLM.

Liangrui Pan, Zhenyu Zhao, Ying Lu et al.

Influenced by ChatGPT, artificial intelligence (AI) large models have witnessed a global upsurge in large model research and development. As people enjoy the convenience by this AI large model, more and more large models in subdivided fields are gradually being proposed, especially large models in radiology imaging field. This article first introduces the development history of large models, technical details, workflow, working principles of multimodal large models and working principles of video generation large models. Secondly, we summarize the latest research progress of AI large models in radiology education, radiology report generation, applications of unimodal and multimodal radiology. Finally, this paper also summarizes some of the challenges of large AI models in radiology, with the aim of better promoting the rapid revolution in the field of radiography.

Liangrui Pan, Qingchun Liang, Wenwu Zeng et al.

Spread through air spaces (STAS) is a distinct invasion pattern in lung cancer, crucial for prognosis assessment and guiding surgical decisions. Histopathology is the gold standard for STAS detection, yet traditional methods are subjective, time-consuming, and prone to misdiagnosis, limiting large-scale applications. We present VERN, an image analysis model utilizing a feature-interactive Siamese graph encoder to predict STAS from lung cancer histopathological images. VERN captures spatial topological features with feature sharing and skip connections to enhance model training. Using 1,546 histopathology slides, we built a large single-cohort STAS lung cancer dataset. VERN achieved an AUC of 0.9215 in internal validation and AUCs of 0.8275 and 0.8829 in frozen and paraffin-embedded test sections, respectively, demonstrating clinical-grade performance. Validated on a single-cohort and three external datasets, VERN showed robust predictive performance and generalizability, providing an open platform (http://plr.20210706.xyz:5000/) to enhance STAS diagnosis efficiency and accuracy.

Zhenyu Zhao, Hongyi Jing, Xiawei Liu et al.

From loco-motion to dextrous manipulation, humanoid robots have made remarkable strides in demonstrating complex full-body capabilities. However, the majority of current robot learning datasets and benchmarks mainly focus on stationary robot arms, and the few existing humanoid datasets are either confined to fixed environments or limited in task diversity, often lacking human-humanoid interaction and lower-body locomotion. Moreover, there are a few standardized evaluation platforms for benchmarking learning-based policies on humanoid data. In this work, we present Humanoid Everyday, a large-scale and diverse humanoid manipulation dataset characterized by extensive task variety involving dextrous object manipulation, human-humanoid interaction, locomotion-integrated actions, and more. Leveraging a highly efficient human-supervised teleoperation pipeline, Humanoid Everyday aggregates high-quality multimodal sensory data, including RGB, depth, LiDAR, and tactile inputs, together with natural language annotations, comprising 10.3k trajectories and over 3 million frames of data across 260 tasks across 7 broad categories. In addition, we conduct an analysis of representative policy learning methods on our dataset, providing insights into their strengths and limitations across different task categories. For standardized evaluation, we introduce a cloud-based evaluation platform that allows researchers to seamlessly deploy their policies in our controlled setting and receive performance feedback. By releasing Humanoid Everyday along with our policy learning analysis and a standardized cloud-based evaluation platform, we intend to advance research in general-purpose humanoid manipulation and lay the groundwork for more capable and embodied robotic agents in real-world scenarios. Our dataset, data collection code, and cloud evaluation website are made publicly available on our project website.

Shen Zhang, Siyuan Liang, Yaning Tan et al.

Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings(PE), such as RoPE, need extrapolating to unseen positions which degrades performance when the inference resolution differs from training. In this paper, We propose a Length-Extrapolatable Diffusion Transformer~(LEDiT) to overcome this limitation. LEDiT needs no explicit PEs, thereby avoiding PE extrapolation. The key innovation of LEDiT lies in the use of causal attention. We demonstrate that causal attention can implicitly encode global positional information and show that such information facilitates extrapolation. We further introduce a locality enhancement module, which captures fine-grained local information to complement the global coarse-grained position information encoded by causal attention. Experimental results on both conditional and text-to-image generation tasks demonstrate that LEDiT supports up to 4x resolution scaling (e.g., from 256x256 to 512x512), achieving better image quality compared to the state-of-the-art length extrapolation methods. We believe that LEDiT marks a departure from the standard RoPE-based methods and offers a promising insight into length extrapolation. Project page: https://shenzhang2145.github.io/ledit/

Hongtao Zhu, Sizhe Zhang, Yang Su et al.

In the domain of causal inference research, the prevalent potential outcomes framework, notably the Rubin Causal Model (RCM), often overlooks individual interference and assumes independent treatment effects. This assumption, however, is frequently misaligned with the intricate realities of real-world scenarios, where interference is not merely a possibility but a common occurrence. Our research endeavors to address this discrepancy by focusing on the estimation of direct and spillover treatment effects under two assumptions: (1) network-based interference, where treatments on neighbors within connected networks affect one's outcomes, and (2) non-random treatment assignments influenced by confounders. To improve the efficiency of estimating potentially complex effects functions, we introduce an novel active learning approach: Active Learning in Causal Inference with Interference (ACI). This approach uses Gaussian process to flexibly model the direct and spillover treatment effects as a function of a continuous measure of neighbors' treatment assignment. The ACI framework sequentially identifies the experimental settings that demand further data. It further optimizes the treatment assignments under the network interference structure using genetic algorithms to achieve efficient learning outcome. By applying our method to simulation data and a Tencent game dataset, we demonstrate its feasibility in achieving accurate effects estimations with reduced data requirements. This ACI approach marks a significant advancement in the realm of data efficiency for causal inference, offering a robust and efficient alternative to traditional methodologies, particularly in scenarios characterized by complex interference patterns.

Zhenyu Zhao, David Zhang, Ellie Zhao et al.

Cold-start exploration is a core challenge in large-scale recommender systems: new or data-sparse items must receive traffic to estimate value, but over-exploration harms users and wastes impressions. In practice, Thompson Sampling (TS) is often initialized with a uniform Beta(1,1) prior, implicitly assuming a 50% success rate for unseen items. When true base rates are far lower, this optimistic prior systematically over-allocates to weak items. The impact is amplified by batched policy updates and pipeline latency: for hours, newly launched items can remain effectively "no data," so the prior dominates allocation before feedback is incorporated. We propose Dynamic Prior Thompson Sampling, a prior design that directly controls the probability that a new arm outcompetes the incumbent winner. Our key contribution is a closed-form quadratic solution for the prior mean that enforces P(X_j > Y_k) = epsilon at introduction time, making exploration intensity predictable and tunable while preserving TS Bayesian updates. Across Monte Carlo validation, offline batched simulations, and a large-scale online experiment on a thumbnail personalization system serving millions of users, dynamic priors deliver precise exploration control and improved efficiency versus a uniform-prior baseline.

Gongli Xi, Ye Tian, Mengyu Yang et al.

The structure of topology underpins much of the research on performance and robustness, yet available topology data are typically scarce, necessitating the generation of synthetic graphs with desired properties for testing or release. Prior diffusion-based approaches either embed conditions into the diffusion model, requiring retraining for each attribute and hindering real-time applicability, or use classifier-based guidance post-training, which does not account for topology scale and practical constraints. In this paper, we show from a discrete perspective that gradients from a pre-trained graph-level classifier can be incorporated into the discrete reverse diffusion posterior to steer generation toward specified structural properties. Based on this insight, we propose Classifier-guided Conditional Topology Generation with Persistent Homology (CoPHo), which builds a persistent homology filtration over intermediate graphs and interprets features as guidance signals that steer generation toward the desired properties at each denoising step. Experiments on four generic/network datasets demonstrate that CoPHo outperforms existing methods at matching target metrics, and we further validate its transferability on the QM9 molecular dataset.

Chaoyu Li, Tianzhi Li, Fei Tao et al.

Vision-language models (VLMs) have advanced video understanding, but their performance is limited by the number of input frames they can process. Existing frame sampling strategies, such as uniform or fixed-budget selection, often fail to adapt to variations in information density or task complexity, resulting in inefficiency and information loss. To address this, we present FrameOracle, a lightweight and plug-and-play module that predicts both (1) which frames are most relevant to a given query and (2) how many frames are needed. FrameOracle is trained using a four-stage curriculum, with the first three stages relying on weak proxy signals such as cross-modal similarity. In the final stage, it leverages stronger supervision from a new dataset we introduce, FrameOracle-41K, the first large-scale VideoQA collection to provide keyframe annotations specifying the minimal set of frames required to answer each question. Extensive experiments across five VLMs and six benchmarks demonstrate that FrameOracle reduces 16-frame inputs to an average of 10.4 frames without any loss in accuracy. When starting from 64-frame candidates, it reduces the input to an average of 13.9 frames while improving accuracy by 1.4%, achieving state-of-the-art efficiency-accuracy trade-offs for scalable video understanding.

Chen Zheng, Zhenyu Zhao

Online experiments (A/B tests) are widely regarded as the gold standard for evaluating recommender system variants and guiding launch decisions. However, a variety of biases can distort the results of the experiment and mislead decision-making. An underexplored but critical bias is algorithm adaptation effect. This bias arises from the flywheel dynamics among production models, user data, and training pipelines: new models are evaluated on user data whose distributions are shaped by the incumbent system or tested only in a small treatment group. As a result, the measured effect of a new product change in modeling and user experience in this constrained experimental setting can diverge substantially from its true impact in full deployment. In practice, the experiment results often favor the production variant with large traffic while underestimating the performance of the test variant with small traffic, which leads to missing opportunities to launch a true winning arm or underestimating the impact. This paper aims to raise awareness of algorithm adaptation bias, situate it within the broader landscape of RecSys evaluation biases, and motivate discussion of solutions that span experiment design, measurement, and adjustment. We detail the mechanisms of this bias, present empirical evidence from real-world experiments, and discuss potential methods for a more robust online evaluation.

Ziyi Liu, Priyanka Dey, Jen-tse Huang et al.

Cultural Intelligence (CQ) refers to the ability to understand unfamiliar cultural contexts, a crucial skill for large language models (LLMs) to effectively engage with globally diverse users. Existing studies often focus on explicitly stated cultural norms, but fail to capture the subtle, implicit values that are common in daily conversation. To address this gap, we introduce CQBench, a benchmark specifically designed to assess LLMs' capability to infer implicit cultural values from natural conversational contexts. CQBench consists of multi character conversation based stories using values from the World Value Survey and the GlobalOpinions, with topics including ethical, religious, social, etc. Our automatic dataset construction pipeline integrates rigorous validation procedures (incorporation, consistency, and implicitness checks), achieving a 94.5% human model agreement in the final validation. To leverage CQBench data, we design three tasks of increasing complexity: attitude detection, value selection, and value extraction. These tasks evaluate whether models can detect attitude and recognize values embedded within natural dialogues rather than relying on explicit cultural knowledge. We find that while frontier models like o1 reach human level performance in value selection (0.809 F1), they still fall short in nuanced attitude detection (0.622 F1). Notably, finetuning a smaller LLaMA-3.2-3B on only 500 culturally rich examples improves performance by over 10%, even outperforming o3-mini in some cases. Using CQ-Bench, we provide insights into the current challenges in LLMs' CQ research and suggest practical pathways for enhancing LLMs' cross-cultural reasoning abilities.

Zhenyu Zhao, Yan He, Miao Chen

Online controlled experimentation is widely adopted for evaluating new features in the rapid development cycle for web products and mobile applications. Measurement of the overall experiment sample is a common practice to quantify the overall treatment effect. In order to understand why the treatment effect occurs in a certain way, segmentation becomes a valuable approach to a finer analysis of experiment results. This paper introduces a framework for creating and utilizing user behavioral segments in online experimentation. By using the data of user engagement with individual product components as input, this method defines segments that are closely related to the features being evaluated in the product development cycle. With a real-world example, we demonstrate that the analysis with such behavioral segments offered deep, actionable insights that successfully informed product decision-making.

Chenxu Jiang, Chenglong Fu, Zhenyu Zhao et al.

Smart home IoT systems and devices are susceptible to attacks and malfunctions. As a result, users' concerns about their security and safety issues arise along with the prevalence of smart home deployments. In a smart home, various anomalies (such as fire or flooding) could happen, due to cyber attacks, device malfunctions, or human mistakes. These concerns motivate researchers to propose various anomaly detection approaches. Existing works on smart home anomaly detection focus on checking the sequence of IoT devices' events but leave out the temporal information of events. This limitation prevents them to detect anomalies that cause delay rather than missing/injecting events. To fill this gap, in this paper, we propose a novel anomaly detection method that takes the inter-event intervals into consideration. We propose an innovative metric to quantify the temporal similarity between two event sequences. We design a mechanism to learn the temporal patterns of event sequences of common daily activities. Delay-caused anomalies are detected by comparing the sequence with the learned patterns. We collect device events from a real-world testbed for training and testing. The experiment results show that our proposed method achieves accuracies of 93%, 88%, 89% for three daily activities.

Huigang Chen, Totte Harinen, Jeong-Yoon Lee et al.

CausalML is a Python implementation of algorithms related to causal inference and machine learning. Algorithms combining causal inference and machine learning have been a trending topic in recent years. This package tries to bridge the gap between theoretical work on methodology and practical applications by making a collection of methods in this field available in Python. This paper introduces the key concepts, scope, and use cases of this package.

Zhenyu Zhao, Radhika Anand, Mallory Wang

In machine learning applications for online product offerings and marketing strategies, there are often hundreds or thousands of features available to build such models. Feature selection is one essential method in such applications for multiple objectives: improving the prediction accuracy by eliminating irrelevant features, accelerating the model training and prediction speed, reducing the monitoring and maintenance workload for feature data pipeline, and providing better model interpretation and diagnosis capability. However, selecting an optimal feature subset from a large feature space is considered as an NP-complete problem. The mRMR (Minimum Redundancy and Maximum Relevance) feature selection framework solves this problem by selecting the relevant features while controlling for the redundancy within the selected features. This paper describes the approach to extend, evaluate, and implement the mRMR feature selection methods for classification problem in a marketing machine learning platform at Uber that automates creation and deployment of targeting and personalization models at scale. This study first extends the existing mRMR methods by introducing a non-linear feature redundancy measure and a model-based feature relevance measure. Then an extensive empirical evaluation is performed for eight different feature selection methods, using one synthetic dataset and three real-world marketing datasets at Uber to cover different use cases. Based on the empirical results, the selected mRMR method is implemented in production for the marketing machine learning platform. A description of the production implementation is provided and an online experiment deployed through the platform is discussed.

Zhenyu Zhao, Totte Harinen

Uplift modeling is an emerging machine learning approach for estimating the treatment effect at an individual or subgroup level. It can be used for optimizing the performance of interventions such as marketing campaigns and product designs. Uplift modeling can be used to estimate which users are likely to benefit from a treatment and then prioritize delivering or promoting the preferred experience to those users. An important but so far neglected use case for uplift modeling is an experiment with multiple treatment groups that have different costs, such as for example when different communication channels and promotion types are tested simultaneously. In this paper, we extend standard uplift models to support multiple treatment groups with different costs. We evaluate the performance of the proposed models using both synthetic and real data. We also describe a production implementation of the approach.

Chen Xu, Zhouchen Lin, Zhenyu Zhao et al.

We propose a new majorization-minimization (MM) method for non-smooth and non-convex programs, which is general enough to include the existing MM methods. Besides the local majorization condition, we only require that the difference between the directional derivatives of the objective function and its surrogate function vanishes when the number of iterations approaches infinity, which is a very weak condition. So our method can use a surrogate function that directly approximates the non-smooth objective function. In comparison, all the existing MM methods construct the surrogate function by approximating the smooth component of the objective function. We apply our relaxed MM methods to the robust matrix factorization (RMF) problem with different regularizations, where our locally majorant algorithm shows advantages over the state-of-the-art approaches for RMF. This is the first algorithm for RMF ensuring, without extra assumptions, that any limit point of the iterates is a stationary point.