Large reasoning models that use long chainof-thought excel at problem-solving yet waste compute on redundant checks.Curbing this overthinking is hard: training-time length penalties can cripple ability, while inferencetime early-exit adds system overhead.To bridge this gap, we propose Step-GRPO, a novel post-training framework that internalizes dynamic early-exit capabilities directly into the model.Step-GRPO shifts the optimization objective from raw tokens to semantic steps by utilizing linguistic markers to structure reasoning.We introduce a Dynamic Truncated Rollout mechanism that exposes the model to concise high-confidence trajectories during exploration, synergized with a Step-Aware Relative Reward that dynamically penalizes redundancy based on group-level baselines.Extensive experiments across three model sizes on diverse benchmarks demonstrate that Step-GRPO achieves a superior accuracy-efficiency tradeoff.On Qwen3-8B, our method reduces token consumption by 32.0% compared to the vanilla model while avoiding the accuracy degradation observed in traditional length-penalty methods.

Split Learning (SL) offers a framework for collaborative model training that respects data privacy by allowing participants to share the same dataset while maintaining distinct feature sets. However, SL is susceptible to backdoor attacks, in which malicious clients subtly alter their embeddings to insert hidden triggers that compromise the final trained model. To address this vulnerability, we introduce SecureSplit, a defense mechanism tailored to SL. SecureSplit applies a dimensionality transformation strategy to accentuate subtle differences between benign and poisoned embeddings, facilitating their separation. With this enhanced distinction, we develop an adaptive filtering approach that uses a majority-based voting scheme to remove contaminated embeddings while preserving clean ones. Rigorous experiments across four datasets (CIFAR-10, MNIST, CINIC-10, and ImageNette), five backdoor attack scenarios, and seven alternative defenses confirm the effectiveness of SecureSplit under various challenging conditions.

In human-machine (autonomous vehicles and robots) interaction scenarios, pedestrians often appear in groups. Pedestrian groups provide richer information compared to individuals, which helps address occlusion problems in pedestrian-machine interactions. However, the randomness and spatiotemporal complexity of pedestrian activity make pedestrian group activity recognition (PGAR) a highly challenging task. This article provides a detailed description of the PGAR task. For the first time, a definition of pedestrian group and activity for autonomous vehicles and robots is provided. Existing datasets and methods are systematically summarized. Furthermore, the unique challenges and trends in PGAR for autonomous vehicles and robots are outlined. Although some related surveys have been published, there has not yet been a survey specifically focused on PGAR in autonomous driving and robotics scenarios. Therefore, the goal of this article is to narrow the gap in this topic and provide a comprehensive reference for researchers in this field.

The deployment of sensors enables data-driven urban management, but necessitates inductive spatio-temporal kriging to infer unmonitored areas. Existing methods impute these unknown observations by smoothing temporal features based on spatial dependencies, overlooking the decoupling ofinherent propertiesanddynamic correlationsin message passing. In particular, the inherent properties reveal non-transitive signals, and current coupled aggregation leads to inaccurate results. To this end, we proposeTempoRAl deCoupledKriging, named TRACK, to decouple two factors with the help of node-specific inherency. Specifically, we first construct a node-specific profile to represent its inherency including geographical and periodic features, which is subsequently transformed into decoupling prompts. Secondly, the coupled temporal features are separated through querying each prompt embedding, facilitating precise temporal aggregation for inherent properties and spatial aggregation for dynamic correlations. Finally, a multi-task training strategy is further adopted to mimic the inductive scenarios during testing. We evaluate TRACK on four real-world datasets spanning urban traffic and air quality prediction tasks. TRACK achieves state-of-the-art performance, with average improvements of 3.10% in MAE and 4.45% in RMSE over strong baselines. Moreover, we further demonstrated its robust generalization in a challenging cross-city inductive setting. Code is available athttps://github.com/JeremyChou28/TRACK.

Vision-language models (VLMs) have shown remarkable advancements in multimodal reasoning tasks. However, they still often generate inaccurate or irrelevant responses due to issues like hallucinated image understandings or unrefined reasoning paths. To address these challenges, we introduce Critic-V, a novel framework inspired by the Actor-Critic paradigm to boost the reasoning capability of VLMs. This framework decouples the reasoning process and critic process by integrating two independent components: the Reasoner, which generates reasoning paths based on visual and textual inputs, and the Critic, which provides constructive critique to refine these paths. In this approach, the Reasoner generates reasoning responses according to text prompts, which can evolve iteratively as a policy based on feedback from the Critic. This interaction process was theoretically driven by a reinforcement learning framework where the Critic offers natural language critiques instead of scalar rewards, enabling more nuanced feedback to boost the Reasoner’s capability on complex reasoning tasks. The Critic model is trained using Direct Preference Optimization (DPO), leveraging a preference dataset of critiques ranked by Rule-based Reward (RBR) to enhance its critic capabilities. Evaluation results show that the Critic-V framework significantly outperforms existing methods, including GPT-4V, on 5 out of 8 benchmarks, especially regarding reasoning accuracy and efficiency. Combining a dynamic text-based policy for the Reasoner and constructive feedback from the preference-optimized Critic enables a more reliable and context-sensitive multimodal reasoning process. Our approach provides a promising solution to enhance the reliability of VLMs, improving their performance in real-world reasoning-heavy multimodal applications such as autonomous driving and embodied intelligence. Our data and code are released at https://github.com/kyrieLei/Critic-V.

The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant computational burden, with the computational complexity scaling quadratically with the number of tokens. In this work, we propose a novel transformer attention operator whose computational complexity scales linearly with the number of tokens. We derive our network architecture by extending prior work which has shown that a transformer style architecture naturally arises by "white-box" architecture design, where each layer of the network is designed to implement an incremental optimization step of a maximal coding rate reduction objective (MCR$^2$). Specifically, we derive a novel variational form of the MCR$^2$ objective and show that the architecture that results from unrolled gradient descent of this variational objective leads to a new attention module called Token Statistics Self-Attention ($\texttt{TSSA}$). $\texttt{TSSA}$ has $\textit{linear computational and memory complexity}$ and radically departs from the typical attention architecture that computes pairwise similarities between tokens. Experiments on vision, language, and long sequence tasks show that simply swapping $\texttt{TSSA}$ for standard self-attention, which we refer to as the Token Statistics Transformer ($\texttt{ToST}$), achieves competitive performance with conventional transformers while being significantly more computationally efficient and interpretable. Our results also somewhat call into question the conventional wisdom that pairwise similarity style attention mechanisms are critical to the success of transformer architectures.

Multimodal large language models (MLLMs) have achieved significant progress in image and language tasks due to the strong reasoning capability of large language models (LLMs). Nevertheless, most MLLMs suffer from limited spatial reasoning ability to interpret and infer spatial arrangements in three-dimensional space. In this work, we propose a novel vision encoder based on hierarchical fusion of geometry and semantics features, generating spatial-aware visual embedding and boosting the spatial grounding capability of MLLMs. Specifically, we first unveil that the spatial ambiguity shortcoming stems from the lossy embedding of the vision encoder utilized in most existing MLLMs (e.g., CLIP), restricted to instance-level semantic features. This motivates us to complement CLIP with the geometry features from vision-only self-supervised learning via a hierarchical adapter, enhancing the spatial awareness in the proposed SpatialGeo. The network is efficiently trained using pretrained LLaVA model and optimized with random feature dropping to avoid trivial solutions relying solely on the CLIP encoder. Experimental results show that SpatialGeo improves the accuracy in spatial reasoning tasks, enhancing state-of-the-art models by at least 8.0% in SpatialRGPT-Bench with ∼50% less memory cost during inference. The source code is available via https://ricky-plus.github.io/SpatialGeoPages/.

Precise prediction of upcoming gait signals, especially over an extended time scale like the entire gait cycle, is crucial. During this period, devices or gait retraining programs can respond to dynamic changes while considering multiple factors in the neurological and musculoskeletal systems. This enables effective adjustments, ultimately optimising outcomes based on the unique rehabilitation goals. However, current state-of-the-art models, whether driven by physical modelling or data modelling approaches, are constrained by short prediction time scales, limited accuracy, and high computational costs, which hinder their use on edge devices. We developed TFNet, a dual-stream neural network model that integrates temporal and frequency domain analyses to accurately predict biomechanical signals across the entire gait cycle. TFNet predicted lower limb joint angles and ground reaction forces with high precision, within 5 degrees and 0.1 body weight, respectively. The model demonstrated the feasibility for deployment on edge devices and adaptability to patients with gait impairments. Explainability analysis highlighted key biomechanical features throughout the gait cycle, improving interpretability and clinical relevance. These comprehensive validations demonstrate the potential of TFNet as a reliable and cost-effective solution for clinical applications aimed at restoring and enhancing gait function.

Multi-source transfer learning is an effective solution to data scarcity by utilizing multiple source tasks for the learning of the target task. However, access to source data and model details is limited in the era of commercial models, giving rise to the setting of multi-source-free (MSF) transfer learning that aims to leverage source domain knowledge without such access. As a newly defined problem paradigm, MSF transfer learning remains largely underexplored and not clearly formulated. In this work, we adopt an information theoretic perspective on it and propose a framework named H-ensemble, which dynamically learns the optimal linear combination, or ensemble, of source models for the target task, using a generalization of maximal correlation regression. The ensemble weights are optimized by maximizing an information theoretic metric for transferability. Compared to previous works, H-ensemble is characterized by: 1) its adaptability to a novel and realistic MSF setting for few-shot target tasks, 2) theoretical reliability, 3) a lightweight structure easy to interpret and adapt. Our method is empirically validated by ablation studies, along with extensive comparative analysis with other task ensemble and transfer learning methods. We show that the H-ensemble can successfully learn the optimal task ensemble, as well as outperform prior arts.

In this paper, we abstract the process of people hearing speech, extracting meaningful cues, and creating vari-ous dynamically audio-consistent talking faces, termed Lis-tening and Imagining, into the task of high-fidelity diverse talking faces generation from a single audio. Specifically, it involves two critical challenges: one is to effectively de-couple identity, content, and emotion from entangled au-dio, and the other is to maintain intra-video diversity and inter- video consistency. To tackle the issues, we first dig out the intricate relationships among facial factors and sim-plify the decoupling process, tailoring a Progressive Audio Disentanglement for accurate facial geometry and seman-tics learning, where each stage incorporates a customized training module responsible for a specific factor. Secondly, to achieve visually diverse and audio-synchronized animation solely from input audio within a single model, we intro-duce the Controllable Coherent Frame generation, which involves the flexible integration of three trainable adapters with frozen Latent Diffusion Models (LDMs) to focus on maintaining facial geometry and semantics, as well as texsture and temporal coherence between frames. In this way, we inherit high-quality diverse generation from LDMs while significantly improving their controllability at a low training cost. Extensive experiments demonstrate the flexibility and effectiveness of our method in handling this paradigm. The codes will be released at FaceChain.

Dependency structures between modalities have been utilized explicitly and implicitly in multimodal learning to enhance classification performance, particularly when the training samples are insufficient. Recent efforts have con-centrated on developing mathematical frameworks utilizing conditional dependency structures, but the non-asymptotic relations between the training sample size and various structures are not sufficiently addressed. To address this issue, we propose a mathematical framework that can be utilized to characterize conditional dependency structures in analytic ways. It provides an explicit description of the sample size in learning various structures in a non-asymptotic regime. Additionally, it demonstrates how task complexity and a fitness evaluation of conditional dependence structures affect the results. Furthermore, we develop an autonomously updated coefficient algorithm auto-CODES based on the theoretical framework and conduct experiments on multimodal emotion recognition tasks using the MELD dataset. The experimental results validate our theory and show the effectiveness of the proposed algorithm.

In heavy-duty series hybrid electric vehicles (SHEVs), engine-generator set (EGS) functions as the main power source for propulsion. However, limitation of engine power per liter and delayed computation of control algorithm result in the hysteretic response of EGS to high demand power. It leads to deteriorating operation of powertrain. Thus, challenging technical issue lies in achieving stable powertrain operation which is difficult to describe precisely by real-time control. In this work, an efficient power control scheme for heavy-duty HEV with online optimized variable universe fuzzy system is proposed. First, a splitting sequential clustering quadratic programming (SSCQP) algorithm is designed to solve power distribution and achieve real-time control. The original subproblem is split into two subproblems with smaller scale to obtain iterative points. And clustering algorithm is introduced to gather up the points to improve the termination criterion. It turns to skip unnecessary short step in the iteration which fails to obtain sufficient descent. Then, the online optimized variable universe fuzzy system is established to achieve rapid response of EGS by adjusting power distribution. In this system, online optimization of membership function distribution parameters is considered. The optimization is constructed on real-time membership overlap degree and central value of fuzzy system rather than the traditional off-line optimization using posterior information of vehicle. Finally, effectiveness of proposed scheme is validated both in simulation test and hardware-in-loop test. The results reveal that stable power output is maintained and calculation time is decreased by 40.9%, 46.0% under two driving cycles.

Vehicle trajectory prediction plays a crucial role in ensuring the driving safety of autonomous vehicles in complex traffic scenes. To accurately predict the trajectory of autonomous vehicles, in this article, we propose a distributed decouple long short-term memory (LSTM) self-trajectory prediction method for autonomous driving. The proposed new recurrent network includes a decouple-LSTM unit and corresponding distributed network architecture. To characterize the closed-loop dynamics of autonomous vehicles, a decouple gate and a control gate are proposed to build the decouple-LSTM unit. The data are processed in different ways according to whether the data participates in the recurrent. The decouple gate filters the data participating in the recurrent, while the control gate handles the data outside the recurrent. By leveraging the decouple-LSTM unit, a distributed network architecture is established, which corresponds with the general vehicle motion control architecture, which effectively models the vehicle motion processes. The proposed method is trained using an actual vehicle dataset and validated through vehicle experiments. The prediction horizon ranges from 0.5 to 3 s. When the prediction horizon is set to 3 s, compared with the LSTM method, the mean square error of the proposed method decreases by 98.0%. Results show that the proposed method significantly improves vehicle trajectory prediction accuracy.

Automotive electrification is a major trend for environmentally friendly transportation. Hybrid electric vehicles are also gaining popularity as a key transitional technology. Coordination control is crucial in improving the operation efficiency for series hybrid electric powertrains (S-HEPs), which involves determining the output power of multiple units such as the engine-generator set (EGS), battery, and motor. However, due to nonlinearity and the electromechanical dynamic difference between each unit, the powertrain state, such as engine speed and direct current link voltage, is prone to fluctuation. So, a high-performance coordinated control strategy is urgently needed. To address this problem, this article proposes a self-triggered model predictive control (MPC) method with adaptive prediction horizon for S-HEPs. Unlike traditional unit-independent feedback control schemes, this article proposes a system-integrated control scheme by establishing a multi-input and multioutput control model that integrates the EGS, battery, and motor. The model is then translated into a linear optimization control problem with input constraints applied into MPC. To reduce the computing burdens of MPC, a mechanism of self-triggered with adaptive prediction horizon is designed by considering the state dispersion and future state deviation. Finally, a hardware-in-the-loop experiment and a simulation experiment are conducted to validate the efficiency of the proposed self-triggered MPC. The results show that the proposed control method achieves a more desirable powertrain state compared to the conventional stability-voltage strategy, and the proposed self-triggered MPC reduces about 60% computing burdens while maintaining similar tracking performance to normal MPC.

This study proposes a sequential clustering quadratic programming (SCQP) method for the energy management strategies of plug-in hybrid electric vehicles (PHEVs). In this method, the clustering algorithm is introduced to gather up the points with a smaller iteration step size in the iteration process. The clustering results are utilized to design the termination criterion based on the distance between the cluster centers of various iteration domains. In the case that the distance varies within the preset range, it indicates that the current iteration point is sufficiently close to the optimal point. So that the criterion turns to terminate the computation to reduce unnecessary iteration steps. To analyze the convergence of the method with the designed criterion, the mathematical illustrations are proposed. In the mathematical illustrations, the monotonicity of the clustering objective function is firstly given. Then, the theorem of feasibility for the solution obtained by the designed criterion is proved. On the basis of aforementioned conclusions, the convergence of the SCQP method is obtained. Finally, the performance of the proposed method is validated both in simulation test and hardware-in-loop (HIL) test. The simulation results reveal that the PHEV achieves 8.81% and 7.74% less fuel consumption under two driving cycles. And the average iteration number of the proposed method is obviously reduced compared with the conventional SQP. The HIL results reveal that the proposed strategy exhibits similar performance in both real controller and simulation. The energy saving and real-time performance can be verified.

Vehicle chassis coordinated control always has been an appealing topic in academia and industry because of the increasing number of chassis electronic actuators with the rapid development of automated vehicles. The optimization of multiple performance targets with multiactuators is intractable, which involves trajectory tracking and handling stability. Additionally, the optimization of tire friction usage remains a knotty problem. Therefore, this article develops a global chassis multiactuator integrated control framework, named by the chassis domain controller (CDC), to realize chassis global dynamics optimization for automated vehicles. Aiming at realizing more efficient, reliable, and flexible mobility, this framework defines each individual wheel to be fully adjustable and controllable to overcome the individual actuation limitation of traditional chassis structures. Global chassis dynamic modeling is formulated based on the analysis of distributed and controllable tire modules and vehicle dynamics motions. A game-theoretical control scheme is proposed to formulate chassis multiactuator integrated control, and the chassis global dynamics can be optimized by guaranteeing a Nash equilibrium for this game. Various experimental results demonstrate the feasibility and effectiveness of the proposed control method, and it suggests the CDC merits further studies to enhance the dynamics performance of automated vehicles in full situations.

Deep Joint Source-Channel Coding (JSCC) has gained increased attention, asserting its significance in the communication field. However, existing Deep JSCC techniques struggle to mitigate time-varying noise due to the deep neural networks being trained beforehand and fixed. To address this issue, we propose a robust deep JSCC scheme. Firstly, a multi-network parallel structure, as well as error-correcting codes, is introduced to effectively exploit label information. Secondly, a closed-form linear encoder and decoder pair is employed at the input and output ends of the channel to deal with the varying noise, which releases the neural network from dealing with a large range of varying noise levels. Thirdly, a transfer learning algorithm is utilized for estimating real-time noise statistics, which outperforms conventional estimation methods when noise statistics are time-dependent. These three components are effectively integrated as a comprehensive transmission system. Experimental results demonstrate that our optimized scheme outperforms existing approaches in the literature.

For automated driving vehicles, trajectory planning is responsible for obtaining feasible trajectories with velocity profiles according to driving environments. From the perspective of trajectory planning, multiple uncertainties of environments and tracking deviations are two significant factors affecting driving safety. The former disturbs the judgment of trajectory planning on the environments, and the latter reduces the tracking accuracy of planned trajectories. To solve these problems, an improved model predictive control (MPC) trajectory planning method is proposed in this paper. Firstly, a Kalman filter fusion method is carried out to predict obstacle trajectory and their uncertainty, which combines model-based and data-based prediction methods. Based on the prediction results, a tube-based MPC trajectory planning method is applied to plan a reference trajectory with a small tracking deviation. The tube-based MPC is composed of two parts. One is the MPC with tightened constraints that is used to plan a feasible trajectory according to a nominal vehicle system and driving environment. The other is a state feedback control that is proposed to adjust the above planned trajectory to reduce the tracking deviations. To our knowledge, this paper proposes Kalman filter fusion and tube-based MPC planning method for the first time to consider the uncertainties of trajectory prediction and tracking control meanwhile in the planning. The planning method is verified by simulations and experiments in multiple scenes. Results show that the method is suitable for both static and dynamic scenes. Compared with applying the basic prediction method, the lateral deviation of the proposed method from the ideal trajectory is decreased by 46.5%. Compared with the nominal MPC method, the lateral tracking deviations of the proposed method are decreased by 77.42%.

Accurate trajectory prediction is essential for safe and efficient autonomous driving in complex traffic environments. While artificial intelligence has shown great promise in improving prediction accuracy, its inherent uncertainty and lack of explainability may lead to unpredictable failures, creating challenges for safety-critical decision-making. This study aims to address these challenges by exploring the impact of traffic environment on prediction algorithms. The study proposes a trajectory prediction framework with epistemic uncertainty estimation ability to output high uncertainty when facing unforeseeable or unknown scenarios. The framework analyzes the environmental effect on the trajectory prediction by considering scenario features and shifts. Features are divided into kinematic features of a target agent, features of surrounding traffic participants, and other scenario features. Feature correlation and importance analyses are performed to study their influence on prediction error and epistemic uncertainty. The impact of unavoidable distributional shifts in the real world on trajectory predictions is investigated using multiple intersection datasets. The results indicate that deep ensemble-based methods have advantages in improving robustness while estimating epistemic uncertainty. Consistent conclusions were obtained from the correlation and importance analyses, indicating that kinematic features of the target agent have relatively strong effects on both prediction error and epistemic uncertainty. Finally, the study analyzes the accuracy deterioration caused by distributional shifts and the potential of the deep ensemble-based method. Through deep ensemble, the errors of the prediction methods based on GRIP++ and Trajectron++ have been improved by 6.4% and 10.8% in the same-dataset test, and 6.3% and 10.8% in the cross-dataset test.

Multimodal learning is an increasingly important research topic. Exploiting conditional dependency across multiple modalities has been shown useful for estimating of the multimodal joint distribution, especially when the number of training samples is insufficient. However, it is difficult to theoretically characterize such conditional dependency structure. To address this issue, we establish a mathematical framework and formulate the estimation problem based on the minimax principle. Then, we propose an estimator which is close to the analytical solution of the problem under a mild assumption on the sample size. Moreover, the proposed estimator is a linear combination of the learning results from the true dependency structure and the conditional one. The combining coefficient is related to three aspects: the number of training samples, the fitness of the conditional dependency structure, and the cardinality of each modality. Finally, numerical simulations are provided to verify our theoretical results that the proposed estimator is close to the optimal solution of the formulated problem.

Due to inevitable parameter uncertainties and disturbances, four-wheel independent drive automated vehicles (4WIDAVs) will produce tracking deviation during the path following process, which have a negative impact on driving safety. Meanwhile, the over-actuated feature of 4WIDAVs will also increase the deviation if not properly handled. To solve this problem, a specific adaptive model predictive control strategy for path following of 4WIDAVs is proposed. Firstly, to obtain a real-time and accurate vehicle dynamics model, the recursive least square method is used to estimate the time-varying uncertainty of tire cornering stiffness. Secondly, based on the real-time updating system model, the modified tube-based model predictive control method is applied to realize path following under the influence of the disturbance. Meanwhile, the compensating yaw moment for controlling vehicle is generated by the designed torque distribution algorithm, which makes full use of the over-actuated feature of 4WIDAVs. Finally, different maneuvers are performed both in simulation and experiment. Results show that the proposed strategy can achieve more accurate path following than the traditional model predictive control and linear quadratic regulator. Compared with the existing controller, the path following accuracy is improved by 41.6% and 60% in simulation and experiment, respectively. Therefore, the proposed strategy is proved to be effective, which provides a theoretical reference for vehicle control in reality.

This paper designs a fault-tolerant controller for the path-following of independently actuated (IA) electric autonomous vehicles (AVs) with steer-by-wire (SBW) systems. Such a controller can handle the effect of steering motor fault and the bounded disturbances of the vehicle dynamic system. Firstly, we formulate the dynamic models of the vehicle, the tire, the SBW system, and the steering motor. Secondly, with the models, we identify the effectiveness coefficient of the steering motor and calculate the steering resistance torque. Both the two parameters are used to determine the potential maximum front-wheel angle. The effectiveness coefficient can determine when the control system switches to the fault-tolerant control (FTC) mode. For the FTC mode, we then introduce a tube-based model predictive control (MPC) framework to guarantee vehicle stability in steering processes and maintain the tracking performance. The disturbances of the vehicle dynamic system affect both the control input and the state. On one hand, the disturbances are formulated to be a tightened state constraint. On the other hand, together with the potential maximum front-wheel angle, the disturbances are formulated to be a tightened input constraint. Finally, we show the effectiveness of the designed fault-tolerant controller via Carsim-Simulink joint simulation and real-vehicle experiment.

The CCCTC-binding factor (CTCF) mediates transcriptional regulation and implicates epigenetic modifications in cancers. However, the systematically unveiling inverse regulatory relationship between CTCF and epigenetic modifications still remains unclear, especially the mechanism by which histone modification mediates CTCF binding. Here, we developed a systematic approach to investigate how epigenetic changes affect CTCF binding. Through integration analysis of CTCF binding in 30 cell lines, we concluded that CTCF generally binds with higher intensity in normal cell lines than that in cancers, and higher intensity in genome regions closed to transcription start sites. To facilitate the better understanding of their associations, we constructed linear mixed-effect models to analyze the effects of the epigenetic modifications on CTCF binding in four cancer cell lines and six normal cell lines, and identified seven epigenetic modifications as potential epigenetic patterns that influence CTCF binding intensity in promoter regions and six epigenetic modifications in enhancer regions. Further analysis of the effects in different locations revealed that the epigenetic regulation of CTCF binding was location-specific and cancer cell line-specific. Moreover, H3K4me2 and H3K9ac showed the potential association with immune regulation of disease. Taken together, our method can contribute to improve the understanding of the epigenetic regulation of CTCF binding and provide potential therapeutic targets for treating tumors associated with CTCF.

While it is commonly believed that estimating the small singular modes for a nearly low-rank matrix requires more samples, the sample size needed is generally unclear. In this paper, we investigate this sample complexity by considering the difference between the estimation errors of estimating a matrix with or without estimating these small singular modes. Specifically, we develop a mathematical framework based on the matrix perturbation analysis to characterize the noise level of estimating small singular modes by n samples. In particular, we show that under mild assumptions on the sample noise, it requires at least n = O(η-2) samples to well estimate the singular modes with the singular value in the order of some small η. More importantly, our results are applied to the channel state estimation and Hirschfeld-Gebelein-Rényi (HGR) maximal correlation problems, from which we characterize that for how many samples, utilizing the low-rank approximation in these problems are beneficial. Finally, numerical simulations are provided to verify our results.

Despite recent progress in prediction and prevention, heart disease remains a leading cause of death. One preliminary step in heart disease prediction and prevention is risk factor identification. Many studies have been proposed to identify risk factors associated with heart disease; however, none have attempted to identify all risk factors. In 2014, the National Center of Informatics for Integrating Biology and Beside (i2b2) issued a clinical natural language processing (NLP) challenge that involved a track (track 2) for identifying heart disease risk factors in clinical texts over time. This track aimed to identify medically relevant information related to heart disease risk and track the progression over sets of longitudinal patient medical records. Identification of tags and attributes associated with disease presence and progression, risk factors, and medications in patient medical history were required. Our participation led to development of a hybrid pipeline system based on both machine learning-based and rule-based approaches. Evaluation using the challenge corpus revealed that our system achieved an F1-score of 92.68%, making it the top-ranked system (without additional annotations) of the 2014 i2b2 clinical NLP challenge.