Federated multi-task learning (FMTL) faces significant challenges due to resource constraints and negative transfer among tasks. Existing methods, such as MAS, rely on task grouping and require multiple backbone models, resulting in increased complexity. To address this issue, we propose FedSTA, a novel FMTL framework that leverages affinity-based task partitions while maintaining a single shared backbone model. We design two task alternation strategies: spatial alternation, which assigns different task subsets to distinct clients within the same round, and temporal alternation, which cycles through task subsets across different rounds. Both strategies effectively exploit task synergies to mitigate negative transfer without the need to split the backbone. Additionally, we propose Global Proximal Min-max Optimization, a novel task weighting mechanism specifically designed for FMTL, capable of capturing global task difficulty distributions and adaptively modulating task optimization priorities to enhance training balance and robustness. Extensive experiments on multiple datasets demonstrate that FedSTA consistently outperforms existing multi-backbone approaches in overall performance while maintaining comparable computational and communication overhead using only a single backbone.

Federated learning is a decentralized machine learning approach that consists of servers and clients. It protects data privacy during model training by keeping the training data locally in each client. However, the requirement for the server and clients to frequently synchronize the parameters of the model brings a heavy burden to the communication links, especially when the model size has grown drastically in recent years. Several methods have been proposed to compress the model size by sparsification to reduce the communication overhead, albeit with significant accuracy degradation. In this work, we propose methods to better trade-off between model accuracy and training efficiency in federated learning. Our first proposed method is a novel sparse mask readjustment rule on the server and the second is a parameter-freezing method during training on the clients. Experimental results show that the model accuracy has significantly improved when combining our proposed methods. For example, compared with the previous state-of-the-art methods with the same total amount of communication cost and computation FLOPs, the accuracy increases on average by 4% and 6% in our methods for CIFAR-10 and CIFAR-100 datasets on ResNet-18, respectively. On the other hand, when targeting the same accuracy, the proposed method can reduce the communication cost by 4-8 times for different datasets with different sparsity levels.

The rapid growth of video platforms has transformed information dissemination and led to an explosion of multimedia content. However, this widespread reach also introduces risks, as some users exploit these platforms to spread hate speech, which is often concealed through complex rhetoric, making hateful video detection a critical challenge. Existing detection methods rely heavily on unimodal analysis or simple feature fusion, struggling to capture cross-modal interactions and reason through implicit hate in sarcasm and metaphor. To address these limitations, we propose HVGuard, the first reasoning-based hateful video detection framework with multimodal large language models (MLLMs). Our approach integrates Chain-of-Thought (CoT) reasoning to enhance multimodal interaction modeling and implicit hate interpretation. Additionally, we design a Mixture-of-Experts (MoE) network for efficient multimodal fusion and final decision-making. The framework is modular and extensible, allowing flexible integration of different MLLMs and encoders. Experimental results demonstrate that HVGuard outperforms all existing advanced detection tools, achieving an improvement of 6.88% to 13.13% in accuracy and 9.21% to 34.37% in M-F1 on two public datasets covering both English and Chinese.

Deep neural networks have achieved exceptional performance across a wide range of applications but remain susceptible to adversarial attacks. While most prior research has focused on single-task scenarios, increasing attention is being directed toward adversarial attacks targeting multiple tasks simultaneously. However, existing methods often fail to balance attack performance across tasks in a multi-task model. These approaches typically aim to maximize the model’s overall loss, neglecting task-specific attack difficulties, which results in imbalanced attack performance among tasks. To address this challenge, we propose a novel multi-task adversarial attack method that ensures robust and balanced attack performance across multiple tasks. Our approach dynamically updates task-specific weighting factors through a min-max optimization during the attack, optimizing the worst-case attack performance across all tasks. Experimental results demonstrate that our method significantly enhances the worst-case attack performance across diverse datasets and attack strategies compared to existing approaches. By dynamically adjusting the attack intensity on the least vulnerable tasks, the min-max optimization significantly improves overall attack effectiveness as well as the worst-case performance by balancing the task weights.

Large language models have demonstrated impressive performance on challenging mathematical reasoning tasks, which has triggered the discussion of whether the performance is achieved by true reasoning capability or memorization. To investigate this question, prior work has constructed mathematical benchmarks when questions undergo simple perturbations – modifications that still preserve the underlying reasoning patterns of the solutions. However, no work has explored hard perturbations, which fundamentally change the nature of the problem so that the original solution steps do not apply. To bridge the gap, we construct MATH-P-Simple and MATH-P-Hard via simple perturbation and hard perturbation, respectively. Each consists of 279 perturbed math problems derived from level-5 (hardest) problems in the MATH dataset (Hendrycks et al., 2021). We observe significant performance drops on MATH-P-Hard across various models, including o1-mini (-16.49%) and gemini-2.0-flash-thinking (-12.9%). We also raise concerns about a novel form of memorization where models blindly apply learned problem-solving skills without assessing their applicability to modified contexts. This issue is amplified when using original problems for in-context learning. We call for research efforts to address this challenge, which is critical for developing more robust and reliable reasoning models. The project is available at https://math-perturb.github.io/.

Current LiDAR-based Vehicle-to-Everything (V2X) multi-agent perception systems have shown the significant success on 3D object detection. While these models perform well in the trained clean weather, they struggle in unseen adverse weather conditions with the domain gap. In this paper, we propose a Domain Generalization based approach, named V2X-DGW, for LiDAR-based 3D object detection on multi-agent perception system under adverse weather conditions. Our research aims to not only maintain favorable multi-agent performance in the clean weather but also promote the performance in the unseen adverse weather conditions by learning only on the clean weather data. To realize the Domain Generalization, we first introduce the Adaptive Weather Augmentation (AWA) to mimic the unseen adverse weather conditions, and then propose two alignments for generalizable representation learning: Trust-region Weatherinvariant Alignment (TWA) and Agent-aware Contrastive Alignment (ACA). To evaluate this research, we add Fog, Rain, Snow conditions on two publicized multi-agent datasets based on physics-based models, resulting in two new datasets: OPV2V-w and V2XSet-w. Extensive experiments demonstrate that our V2X-DGW achieved significant improvements in the unseen adverse weathers. The code is available at https://github.com/Baolu1998/V2X-DGW.

LiDAR-Radar fusion has been widely regarded as an effective strategy for enhancing sensor-level robustness in 3D perception under adverse weather. However, it remains fundamentally insufficient to address feature-level domain shifts induced by diverse weather conditions - a critical yet often overlooked bottleneck in multimodal 3D object detection. In this work, we advocate a new perspective: all-weather 3D detection should be formulated as a lightweight capacity allocation problem, rather than simply enlarging or duplicating models for each weather domain. To this end, we propose DA3D, a Domain-Aware Dynamic Adaptation framework that leverages LoRA as a domain-adaptive capacity controller for efficient and scalable feature modulation. In addition, we introduce a domain-aware rank adaptation strategy that dynamically reallocates LoRA capacity based on domain difficulty, allowing the model to focus its representational power where it matters most. Extensive experiments on the K-Radar benchmark show that DA3D consistently improves 3D detection across both radar-only and LiDAR-Radar fusion backbones, achieving +4.9% AP3D on RTNH, +3.8% on 3D-LRF, and +8.1% on L4DR at IoU=0.5. Notably, DA3D outperforms existing multi-weather modeling methods under the same parameter budget, offering a practical and scalable solution for robust all-weather 3D perception. The code is available at https://github.com/Dawns14/DA3D.

Federated Multi-Task Learning (FMTL) enables collaborative training of multiple tasks across decentralized clients, but faces two key challenges in practice: negative transfer among tasks and scalability under resource constraints. Task differences can cause gradient conflicts that degrade overall performance, while limited computation and storage on edge devices make it difficult to maintain accuracy with low overhead. Existing methods address these issues either by adopting multi-backbone architectures, which split tasks to reduce interference but incur substantial parameter and computation costs, or by performing naive global averaging, which ignores inter-task differences and fails to effectively mitigate negative transfer. To overcome these limitations, we propose Task-Aware Federated Multi-Task Learning (TA-FMTL), a single-backbone framework that balances accuracy and efficiency. TA-FMTL integrates two lightweight components: a min–max task-difficulty weighting strategy that dynamically allocates more updates to harder tasks for balanced optimization, and a variance-aware reputation aggregation that down-weights clients with high overall loss or unstable cross-task performance. This design enables robust coordination across heterogeneous tasks without task splitting. Experiments on the Taskonomy benchmark show that TA-FMTL consistently achieves better or comparable accuracy to state-of-the-art MAS variants while reducing parameters by up to 77.2% and FLOPs by 37.3% in challenging 5-task and 9-task settings, demonstrating its scalability and practicality for real-world FMTL under heterogeneous and resource-limited conditions.

This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case. Motivated by real-world settings such as loading in game playing, we propose an enhanced feedback model called ``multiple observations in hindsight'', where after each episode of interaction with the POMDP, the learner may collect multiple additional observations emitted from the encountered latent states, but may not observe the latent states themselves. We show that sample-efficient learning under this feedback model is possible for two new subclasses of POMDPs: \emph{multi-observation revealing POMDPs} and \emph{distinguishable POMDPs}. Both subclasses generalize and substantially relax \emph{revealing POMDPs}---a widely studied subclass for which sample-efficient learning is possible under standard trajectory feedback. Notably, distinguishable POMDPs only require the emission distributions from different latent states to be \emph{different} instead of \emph{linearly independent} as required in revealing POMDPs.

In our study, we present bifurcated attention, a method developed for language model inference in single-context batch sampling contexts. This approach aims to reduce redundant memory IO costs, a significant factor in latency for high batch sizes and long context lengths. Bifurcated attention achieves this by dividing the attention mechanism during incremental decoding into two distinct GEMM operations, focusing on the KV cache from prefill and the decoding process. This method ensures precise computation and maintains the usual computational load (FLOPs) of standard attention mechanisms, but with reduced memory IO. Bifurcated attention is also compatible with multi-query attention mechanism known for reduced memory IO for KV cache, further enabling higher batch size and context length. The resulting efficiency leads to lower latency, improving suitability for real-time applications, e.g., enabling massively-parallel answer generation without substantially increasing latency, enhancing performance when integrated with post-processing techniques such as reranking.

Policy optimization from batch data, i.e., offline reinforcement learning (RL) is important when collecting data from a current policy is not possible. This setting incurs distribution mismatch between batch training data and trajectories from the current policy. Pessimistic offsets estimate mismatch using concentration bounds, which possess strong theoretical guarantees and simplicity of implementation. Mismatch may be conservative in sparse data regions and less so otherwise, which can result in under-performing their no-penalty variants in practice. We derive a new pessimistic penalty as the distance between the data and the true distribution using an evaluable one-sample test known as Stein Discrepancy that requires minimal smoothness conditions, and noticeably, allows a mixture family representation of distribution over next states. This entity forms a quantifier of information in offline data, which justifies calling this approach *information-directed pessimism* (IDP) for offline RL. We further establish that this new penalty based on discrete Stein discrepancy yields practical gains in performance while generalizing the regret of prior art to multimodal distributions.

Multi-task learning is a subfield of machine learning in which the data is trained with a shared model to solve different tasks simultaneously. Instead of training multiple models corresponding to different tasks, we only need to train a single model with shared parameters by using multi-task learning. Multi-task learning highly reduces the number of parameters in the machine learning models and thus reduces the computational and storage requirements. When we apply multi-task learning on deep neural networks (DNNs), we need to further compress the model since the model size of a single DNN is still a critical challenge to many computation systems, especially for edge platforms. However, when model compression is applied to multi-task learning, it is challenging to maintain the performance of all the different tasks. To deal with this challenge, we propose a min-max optimization framework for the training of highly compressed multi-task DNN models. Our proposed framework can automatically adjust the learnable weighting factors corresponding to different tasks to guarantee that the task with worst-case performance across all the different tasks will be optimized.

Vehicle detection in Unmanned Aerial Vehicle (UAV) captured images has wide applications in aerial photography and remote sensing. There are many public benchmark datasets proposed for the vehicle detection and tracking in UAV images. Recent studies show that adding an adversarial patch on objects can fool the well-trained deep neural networks based object detectors, posing security concerns to the downstream tasks. However, the current public UAV datasets might ignore the diverse altitudes, vehicle attributes, fine-grained instance-level annotation in mostly side view with blurred vehicle roof, so none of them is good to study the adversarial patch based vehicle detection attack problem. In this paper, we propose a new dataset named EVD4UAV as an altitude-sensitive benchmark to evade vehicle detection in UAV with 6,284 images and 90,886 fine-grained annotated vehicles. The EVD4UAV dataset has diverse altitudes (50m, 70m, 90m), vehicle attributes (color, type), fine-grained annotation (horizontal and rotated bounding boxes, instance-level mask) in top view with clear vehicle roof. One white-box and two black-box patch based attack methods are implemented to attack three classic deep neural networks based object detectors on EVD4UAV. The experimental results show that these representative attack methods could not achieve the robust altitude-insensitive attack performance.

Unsupervised learning is a challenging task due to the lack of labels. Multiple Object Tracking (MOT), which inevitably suffers from mutual object interference, occlusion, etc., is even more difficult without label supervision. In this paper, we explore the latent consistency of sample features across video frames and propose an Unsupervised Contrastive Similarity Learning method, named UCSL, including three contrast modules: self-contrast, cross-contrast, and ambiguity contrast. Specifically, i) self-contrast uses intra-frame direct and inter-frame indirect contrast to obtain discriminative representations by maximizing self-similarity. ii) Cross-contrast aligns cross- and continuous-frame matching results, mitigating the persistent negative effect caused by object occlusion. And iii) ambiguity contrast matches ambiguous objects with each other to further increase the certainty of subsequent object association through an implicit manner. On existing benchmarks, our method outperforms the existing unsupervised methods using only limited help from ReID head, and even provides higher accuracy than lots of fully supervised methods.

In this paper, we study representation learning in partially observable Markov Decision Processes (POMDPs), where the agent learns a decoder function that maps a series of high-dimensional raw observations to a compact representation and uses it for more efficient exploration and planning. We focus our attention on the sub-classes of *$\gamma$-observable* and *decodable POMDPs*, for which it has been shown that statistically tractable learning is possible, but there has not been any computationally efficient algorithm. We first present an algorithm for decodable PMMDPs that combines maximum likelihood estimation (MLE) and optimism in the face of uncertainty (OFU) to perform representation learning and achieve efficient sample complexity, while only calling supervised learning computational oracles. We then show how to adapt this algorithm to also work in the broader class of $\gamma$-observable POMDPs.

Narrowband weak connection network environment is often associated with imperfect network infrastructure. It has the characteristics of low bandwidth, high BER, and unstable connection which can cause high packet loss at the application layer. Narrowband network environment ranges from tens of Kbps to hundreds of Kbps, and the packet loss rate can be more than 50%. Most of the throughput is devoted to retransmit packet so that there is a low effective throughput rate in traditional reliable transmission methods in this environment. In this paper, a reliable effective transmission mechanism is proposed. On the one hand, this mechanism uses multiple heterogeneous networks to transmit data simultaneously to enhance the available bandwidth. On the other hand, redundant encoded packets are generated in each network by RLNC encoder to avoid the increase in transmission delay caused by packet retransmission. It can ensure the reliability of data transmission and maintain a high effective throughput rate in narrowband weak connection environment. Compared with TCP and RUDP, the proposed method can exceed at packet loss rates higher than 20%.

Click-through rate (CTR) prediction is crucial for online sponsored search advertising. Several successful CTR models have been adopted in the industry, including the regularized logistic regression (LR). Nonetheless, the learning process suffers from two limitations: 1) Feature crosses for high-order information may generate trillions of features, which are sparse for online learning examples; 2) Rapid changing of data distribution brings challenges to the accurate learning since the model has to perform a fast adaptation on the new data. Moreover, existing adaptive optimizers are ineffective in handling the sparsity issue for high-dimensional features.

In recent years, deep learning methods bring incredible progress to the field of object detection. However, in the field of remote sensing image processing, existing methods neglect the relationship between imaging configuration and detection performance, and do not take into account the importance of detection performance feedback for improving image quality. Therefore, detection performance is limited by the passive nature of the conventional object detection framework. In order to solve the above limitations, this paper takes adaptive brightness adjustment and scale adjustment as examples, and proposes an active object detection method based on deep reinforcement learning. The goal of adaptive image attribute learning is to maximize the detection performance. With the help of active object detection and image attribute adjustment strategies, low-quality images can be converted into high-quality images, and the overall performance is improved without retraining the detector.

Baidu runs the largest commercial web search engine in China, serving hundreds of millions of online users every day in response to a great variety of queries. In order to build a high-efficiency sponsored search engine, we used to adopt a three-layer funnel-shaped structure to screen and sort hundreds of ads from billions of ad candidates subject to the requirement of low response latency and the restraints of computing resources. Given a user query, the top matching layer is responsible for providing semantically relevant ad candidates to the next layer, while the ranking layer at the bottom concerns more about business indicators (e.g., CPM, ROI, etc.) of those ads. The clear separation between the matching and ranking objectives results in a lower commercial return. The Mobius project has been established to address this serious issue. It is our first attempt to train the matching layer to consider CPM as an additional optimization objective besides the query-ad relevance, via directly predicting CTR (click-through rate) from billions of query-ad pairs. Specifically, this paper will elaborate on how we adopt active learning to overcome the insufficiency of click history at the matching layer when training our neural click networks offline, and how we use the SOTA ANN search technique for retrieving ads more efficiently (Here "ANN'' stands for approximate nearest neighbor search). We contribute the solutions to Mobius-V1 as the first version of our next generation query-ad matching system.

Accurate segmentation of the prostate in computed tomography (CT) images is important in image-guided radiotherapy; however, difficulties remain associated with this task. In this study, an automatic framework is designed for prostate segmentation in CT images. We propose a novel image feature extraction method, namely, variant scale patch, which can provide rich image information in a low dimensional feature space. We assume that the samples from different classes lie on different nonlinear submanifolds and design a new segmentation criterion called local independent projection (LIP). In our method, a dictionary containing training samples is constructed. To utilize the latest image information, we use an online updated strategy to construct this dictionary. In the proposed LIP, locality is emphasized rather than sparsity; local anchor embedding is performed to determine the dictionary coefficients. Several morphological operations are performed to improve the achieved results. The proposed method has been evaluated based on 330 3-D images of 24 patients. Results show that the proposed method is robust and effective in segmenting prostate in CT images.