Imitation from videos often fails when expert demonstrations and learner environments exhibit domain shifts, such as discrepancies in lighting, color, or texture. While visual randomization partially addresses this problem by augmenting training data, it remains computationally intensive and inherently reactive, struggling with unseen scenarios. We propose a different approach: instead of randomizing appearances, we eliminate their influence entirely by rethinking the sensory representation itself. Inspired by biological vision systems that prioritize temporal transients (e.g., retinal ganglion cells) and by recent sensor advancements, we introduce event-inspired perception for visually robust imitation. Our method converts standard RGB videos into a sparse, event-based representation that encodes temporal intensity gradients, discarding static appearance features. This biologically grounded approach disentangles motion dynamics from visual style, enabling robust visual imitation from observations even in the presence of visual mismatches between expert and agent environments. By training policies on event streams, we achieve invariance to appearance-based distractors without requiring computationally expensive and environment-specific data augmentation techniques. Experiments across the DeepMind Control Suite and the Adroit platform for dynamic dexterous manipulation show the efficacy of our method. Our code is publicly available at Eb-LAIfO.

We study offline imitation learning (IL) in cooperative multi-agent settings, where demonstrations have unlabeled mixed quality - containing both expert and suboptimal trajectories. Our proposed solution is structured in two stages: trajectory labeling and multi-agent imitation learning, designed jointly to enable effective learning from heterogeneous, unlabeled data. In the first stage, we combine advances in large language models and preference-based reinforcement learning to construct a progressive labeling pipeline that distinguishes expert-quality trajectories. In the second stage, we introduce MisoDICE, a novel multi-agent IL algorithm that leverages these labels to learn robust policies while addressing the computational complexity of large joint state-action spaces. By extending the popular single-agent DICE framework to multi-agent settings with a new value decomposition and mixing architecture, our method yields a convex policy optimization objective and ensures consistency between global and local policies. We evaluate MisoDICE on multiple standard multi-agent RL benchmarks and demonstrate superior performance, especially when expert data is scarce.

Recent advances in cross-prompt automated essay scoring (AES) typically train models jointly on all source prompts, often requiring additional access to unlabeled target prompt essays simultaneously. However, using all sources is suboptimal in our pilot study, and re-accessing source datasets during adaptation raises privacy concerns. We propose a source-free adaptation approach that selectively merges individually trained source models' parameters instead of datasets. In particular, we simulate joint training through linear combinations of task vectors -- the parameter updates from fine-tuning. To optimize the combination's coefficients, we propose Prior-encoded Information Maximization (PIM), an unsupervised objective which promotes the model's score discriminability regularized by priors pre-computed from the sources. We employ Bayesian optimization as an efficient optimizer of PIM. Experimental results with LLMs on in-dataset and cross-dataset adaptation show that our method (1) consistently outperforms training jointly on all sources, (2) maintains superior robustness compared to other merging methods, (3) excels under severe distribution shifts where recent leading cross-prompt methods struggle, all while retaining computational efficiency.

Deep reinforcement learning (DRL) has been widely used for dynamic algorithm configuration, particularly in evolutionary computation, which benefits from the adaptive update of parameters during the algorithmic execution. However, applying DRL to algorithm configuration for multi-objective combinatorial optimization (MOCO) problems remains relatively unexplored. This paper presents a novel graph neural network (GNN) based DRL to configure multi-objective evolutionary algorithms. We model the dynamic algorithm configuration as a Markov decision process, representing the convergence of solutions in the objective space by a graph, with their embeddings learned by a GNN to enhance the state representation. Experiments on diverse MOCO challenges indicate that our method outperforms traditional and DRL-based algorithm configuration methods in terms of efficacy and adaptability. It also exhibits advantageous generalizability across objective types and problem sizes, and applicability to different evolutionary computation methods.

Modern portfolio construction demands robust methods for integrating data-driven insights into asset allocation. The Black-Litterman model offers a powerful Bayesian approach to adjust equilibrium returns using investor views to form a posterior expectation along with market priors. Mainstream research mainly generates subjective views through statistical models or machine learning methods, among which hybrid models combined with decomposition algorithms perform well. However, most hybrid models do not pay enough attention to noise, and time series decomposition methods based on single variables make it difficult to fully utilize information between multiple variables. Multivariate decomposition also has problems of low efficiency and poor component quality. In this study, we propose a novel hybrid forecasting model SSA-MAEMD-TCN to automate and improve the view generation process. The proposed model combines Singular Spectrum Analysis (SSA) for denoising, Multivariate Aligned Empirical Mode Decomposition (MA-EMD) for frequency-aligned decomposition, and Temporal Convolutional Networks (TCNs) for deep sequence learning to capture complex temporal patterns across multiple financial indicators. Empirical tests on the Nasdaq 100 Index stocks show a significant improvement in forecasting performance compared to baseline models based on MAEMD and MEMD. The optimized portfolio performs well, with annualized returns and Sharpe ratios far exceeding those of the traditional portfolio over a short holding period, even after accounting for transaction costs.

Recent work has demonstrated that large-scale, multi-animal models are powerful tools for characterizing the relationship between neural activity and behavior. Current large-scale approaches, however, focus exclusively on either predicting neural activity from behavior (encoding) or predicting behavior from neural activity (decoding), limiting their ability to capture the bidirectional relationship between neural activity and behavior. To bridge this gap, we introduce a multimodal, multi-task model that enables simultaneous Neural Encoding and Decoding at Scale (NEDS). Central to our approach is a novel multi-task-masking strategy, which alternates between neural, behavioral, within-modality, and cross-modality masking. We pretrain our method on the International Brain Laboratory (IBL) repeated site dataset, which includes recordings from 83 animals performing the same visual decision-making task. In comparison to other large-scale models, we demonstrate that NEDS achieves state-of-the-art performance for both encoding and decoding when pretrained on multi-animal data and then fine-tuned on new animals. Surprisingly, NEDS's learned embeddings exhibit emergent properties: even without explicit training, they are highly predictive of the brain regions in each recording. Altogether, our approach is a step towards a foundation model of the brain that enables seamless translation between neural activity and behavior.

Recent advances in uncertainty estimation for Large Language Models (LLMs) during downstream adaptation have addressed key challenges of reliability and simplicity. However, existing Bayesian methods typically require multiple sampling iterations during inference, creating significant efficiency issues that limit practical deployment. In this paper, we investigate the possibility of eliminating the need for test-time sampling for LLM uncertainty estimation. Specifically, when given an off-the-shelf Bayesian LLM, we distill its aligned confidence into a non-Bayesian student LLM by minimizing the divergence between their predictive distributions. Unlike typical calibration methods, our distillation is carried out solely on the training dataset without the need of an additional validation dataset. This simple yet effective approach achieves N-times more efficient uncertainty estimation during testing, where N is the number of samples traditionally required by Bayesian LLMs. Our extensive experiments demonstrate that uncertainty estimation capabilities on training data can successfully generalize to unseen test data through our distillation technique, consistently producing results comparable to (or even better than) state-of-the-art Bayesian LLMs.

--Diffusion models (DMs) have recently achieved significant success in wireless communications systems due to their denoising capabilities. The broadcast nature of wireless signals makes them susceptible not only to Gaussian noise, but also to unaware interference. This raises the question of whether DMs can effectively mitigate interference in wireless semantic communication systems. In this paper, we model the interference cancellation problem as a maximum a posteriori (MAP) problem over the joint posterior probability of the signal and interference, and theoretically prove that the solution provides excellent estimates for the signal and interference. T o solve this problem, we develop an interference cancellation diffusion model (ICDM), which decomposes the joint posterior into independent prior probabilities of the signal and interference, along with the channel transition probablity. The log-gradients of these distributions at each time step are learned separately by DMs and accurately estimated through deriving. ICDM further integrates these gradients with advanced numerical iteration method, achieving accurate and rapid interference cancellation. Extensive experiments demonstrate that ICDM significantly reduces the mean square error (MSE) and enhances perceptual quality compared to schemes without ICDM. For example, on the CelebA dataset under the Rayleigh fading channel with a signal-to-noise ratio (SNR) of 20 dB and signal to interference plus noise ratio (SINR) of 0 dB, ICDM reduces the MSE by 4 . Diffusion models (DMs) [1]-[4], which utilize a score function to model the gradient of the conditional data distribution, have recently achieved remarkable success in the field of artificial intelligence generated content (AIGC). These models are capable of generating controllable and high-quality content in various domains, including long-form text generation, controllable image generation, and consistent video generation. They have also become a fundamental technology for large language models (LLMs) such as GPT -4o. The inherent controllability of the content generated by diffusion models has significantly driven their application across diverse fields [5]-[7].

Ensuring safe operation of safety-critical complex systems interacting with their environment poses significant challenges, particularly when the system's world model relies on machine learning algorithms to process the perception input. A comprehensive safety argumentation requires knowledge of how faults or functional insufficiencies propagate through the system and interact with external factors, to manage their safety impact. While statistical analysis approaches can support the safety assessment, associative reasoning alone is neither sufficient for the safety argumentation nor for the identification and investigation of safety measures. A causal understanding of the system and its interaction with the environment is crucial for safeguarding safety-critical complex systems. It allows to transfer and generalize knowledge, such as insights gained from testing, and facilitates the identification of potential improvements. This work explores using causal Bayesian networks to model the system's causalities for safety analysis, and proposes measures to assess causal influences based on Pearl's framework of causal inference. We compare the approach of causal Bayesian networks to the well-established fault tree analysis, outlining advantages and limitations. In particular, we examine importance metrics typically employed in fault tree analysis as foundation to discuss suitable causal metrics. An evaluation is performed on the example of a perception system for automated driving. Overall, this work presents an approach for causal reasoning in safety analysis that enables the integration of data-driven and expert-based knowledge to account for uncertainties arising from complex systems operating in open environments.

Vision-Language-Action (VLA) models have demonstrated significant potential in the field of embodied intelligence, enabling agents to follow human instructions to complete complex tasks in physical environments. Existing embodied agents are often trained through behavior cloning, which requires expensive data and computational resources and is constrained by human demonstrations. To address this issue, many researchers explore the application of reinforcement fine-tuning to embodied agents. However, typical reinforcement fine-tuning methods for embodied agents usually rely on sparse, outcome-based rewards, which struggle to provide fine-grained feedback for specific actions within an episode, thus limiting the model's manipulation capabilities and generalization performance. In this paper, we propose RFTF, a novel reinforcement fine-tuning method that leverages a value model to generate dense rewards in embodied scenarios. Specifically, our value model is trained using temporal information, eliminating the need for costly robot action labels. In addition, RFTF incorporates a range of techniques, such as GAE and sample balance to enhance the effectiveness of the fine-tuning process. By addressing the sparse reward problem in reinforcement fine-tuning, our method significantly improves the performance of embodied agents, delivering superior generalization and adaptation capabilities across diverse embodied tasks. Experimental results show that embodied agents fine-tuned with RFTF achieve new state-of-the-art performance on the challenging CALVIN ABC-D with an average success length of 4.296. Moreover, RFTF enables rapid adaptation to new environments. After fine-tuning in the D environment of CALVIN for a few episodes, RFTF achieved an average success length of 4.301 in this new environment.