Bayesian neural networks (BNNs) treat neural network weights as random variables, which aim to provide posterior uncertainty estimates and avoid overfitting by performing inference on the posterior weights. However, the selection of appropriate prior distributions remains a challenging task, and BNNs may suffer from catastrophic inflated variance or poor predictive performance when poor choices are made for the priors. Existing BNN designs apply different priors to weights, while the behaviours of these priors make it difficult to sufficiently shrink noisy signals or they are prone to overshrinking important signals in the weights. To alleviate this problem, we propose a novel R2D2-Net, which imposes the R^2-induced Dirichlet Decomposition (R2D2) prior to the BNN weights. The R2D2-Net can effectively shrink irrelevant coefficients towards zero, while preventing key features from over-shrinkage. To approximate the posterior distribution of weights more accurately, we further propose a variational Gibbs inference algorithm that combines the Gibbs updating procedure and gradient-based optimization. This strategy enhances stability and consistency in estimation when the variational objective involving the shrinkage parameters is non-convex. We also analyze the evidence lower bound (ELBO) and the posterior concentration rates from a theoretical perspective. Experiments on both natural and medical image classification and uncertainty estimation tasks demonstrate satisfactory performance of our method.

Offline reinforcement learning (RL) aims to learn an effective policy from a static dataset. To alleviate extrapolation errors, existing studies often uniformly regularize the value function or policy updates across all states. However, due to substantial variations in data quality, the fixed regularization strength often leads to a dilemma: Weak regularization strength fails to address extrapolation errors and value overestimation, while strong regularization strength shifts policy learning toward behavior cloning, impeding potential performance enabled by Bellman updates. To address this issue, we propose the selective state-adaptive regularization method for offline RL. Specifically, we introduce state-adaptive regularization coefficients to trust state-level Bellman-driven results, while selectively applying regularization on high-quality actions, aiming to avoid performance degradation caused by tight constraints on low-quality actions. By establishing a connection between the representative value regularization method, CQL, and explicit policy constraint methods, we effectively extend selective state-adaptive regularization to these two mainstream offline RL approaches. Extensive experiments demonstrate that the proposed method significantly outperforms the state-of-the-art approaches in both offline and offline-to-online settings on the D4RL benchmark.

Weak-to-strong generalization, where a student model trained on imperfect labels generated by a weaker teacher nonetheless surpasses that teacher, has been widely observed but the mechanisms that enable it have remained poorly understood. In this paper, through a theoretical analysis of simple models, we uncover three core mechanisms that can drive this phenomenon. First, by analyzing ridge regression, we study the interplay between the teacher and student regularization and prove that a student can compensate for a teacher's under-regularization and achieve lower test error. We also analyze the role of the parameterization regime of the models. Second, by analyzing weighted ridge regression, we show that a student model with a regularization structure more aligned to the target, can outperform its teacher. Third, in a nonlinear multi-index setting, we demonstrate that a student can learn easy, task-specific features from the teacher while leveraging its own broader pre-training to learn hard-to-learn features that the teacher cannot capture.

Meta-reinforcement learning trains a single reinforcement learning agent on a distribution of tasks to quickly generalize to new tasks outside of the training set at test time. From a Bayesian perspective, one can interpret this as performing amortized variational inference on the posterior distribution over training tasks. Among the various meta-reinforcement learning approaches, a common method is to represent this distribution with a point-estimate using a recurrent neural network. We show how one can augment this point estimate to give full distributions through the Laplace approximation, either at the start of, during, or after learning, without modifying the base model architecture. With our approximation, we are able to estimate distribution statistics (e.g., the entropy) of non-Bayesian agents and observe that point-estimate based methods produce overconfident estimators while not satisfying consistency. Furthermore, when comparing our approach to full-distribution based learning of the task posterior, our method performs on par with variational baselines while having much fewer parameters.

Collision-free motion planning for redundant robot manipulators in complex environments is yet to be explored. Although recent advancements at the intersection of deep reinforcement learning (DRL) and robotics have highlighted its potential to handle versatile robotic tasks, current DRL-based collision-free motion planners for manipulators are highly costly, hindering their deployment and application. This is due to an overreliance on the minimum distance between the manipulator and obstacles, inadequate exploration and decision-making by DRL, and inefficient data acquisition and utilization. In this article, we propose URPlanner, a universal paradigm for collision-free robotic motion planning based on DRL. URPlanner offers several advantages over existing approaches: it is platform-agnostic, cost-effective in both training and deployment, and applicable to arbitrary manipulators without solving inverse kinematics. To achieve this, we first develop a parameterized task space and a universal obstacle avoidance reward that is independent of minimum distance. Second, we introduce an augmented policy exploration and evaluation algorithm that can be applied to various DRL algorithms to enhance their performance. Third, we propose an expert data diffusion strategy for efficient policy learning, which can produce a large-scale trajectory dataset from only a few expert demonstrations. Finally, the superiority of the proposed methods is comprehensively verified through experiments.

Diffusion models have emerged as a powerful class of generative models, capable of producing high-quality samples that generalize beyond the training data. However, evaluating this generalization remains challenging: theoretical metrics are often impractical for high-dimensional data, while no practical metrics rigorously measure generalization. In this work, we bridge this gap by introducing probability flow distance ($\texttt{PFD}$), a theoretically grounded and computationally efficient metric to measure distributional generalization. Specifically, $\texttt{PFD}$ quantifies the distance between distributions by comparing their noise-to-data mappings induced by the probability flow ODE. Moreover, by using $\texttt{PFD}$ under a teacher-student evaluation protocol, we empirically uncover several key generalization behaviors in diffusion models, including: (1) scaling behavior from memorization to generalization, (2) early learning and double descent training dynamics, and (3) bias-variance decomposition. Beyond these insights, our work lays a foundation for future empirical and theoretical studies on generalization in diffusion models.

Artificial Intelligence (AI) is one of the major technological advancements of this century, bearing incredible potential for users through AI-powered applications and tools in numerous domains. Being often black-box (i.e., its decision-making process is unintelligible), developers typically resort to eXplainable Artificial Intelligence (XAI) techniques to interpret the behaviour of AI models to produce systems that are transparent, fair, reliable, and trustworthy. However, presenting explanations to the user is not trivial and is often left as a secondary aspect of the system's design process, leading to AI systems that are not useful to end-users. This paper presents a Systematic Literature Review on Explanation User Interfaces (XUIs) to gain a deeper understanding of the solutions and design guidelines employed in the academic literature to effectively present explanations to users. To improve the contribution and real-world impact of this survey, we also present a framework for Human-cEnteRed developMent of Explainable user interfaceS (HERMES) to guide practitioners and academics in the design and evaluation of XUIs.

Reward models trained with conventional Reinforcement Learning from AI Feedback (RLAIF) methods suffer from limited generalizability, which hinders the alignment performance of the policy model during reinforcement learning (RL). This challenge stems from various issues, including distribution shift, preference label noise, and mismatches between overly challenging samples and model capacity. In this paper, we attempt to enhance the generalizability of reward models through a data-centric approach, driven by the insight that these issues are inherently intertwined from the perspective of data difficulty. To address this, we propose a novel framework, $\textit{Curriculum-RLAIF}$, which constructs preference pairs with varying difficulty levels and produces a curriculum that progressively incorporates preference pairs of increasing difficulty for reward model training. Our experimental results suggest that reward models trained with Curriculum-RLAIF achieve improved generalizability, significantly increasing the alignment performance of the policy model by a large margin without incurring additional inference costs compared to various non-curriculum baselines. Detailed analysis and comparisons with alternative approaches, including data selection via external pretrained reward models or internal self-selection mechanisms, as well as other curriculum strategies, further demonstrate the superiority of our approach in terms of simplicity, efficiency, and effectiveness.

Existing chain-of-thought (CoT) distillation methods can effectively transfer reasoning abilities to base models but suffer from two major limitations: excessive verbosity of reasoning traces and inadequate adaptability to problem difficulty. Long reasoning traces significantly increase inference costs, and uniform-length solutions prevent base models from learning adaptive reasoning strategies. To address these issues, we propose a difficulty-aware prompting (DAP) method to dynamically shorten reasoning traces without performance loss. In our approach, a large teacher model first judges each problem's difficulty and then rewrites its reasoning traces to an appropriate shorter length, yielding concise yet complete reasoning traces. Leveraging the DAP pipeline, we curate a distilled dataset called LiteCoT consisting of 100K concise reasoning examples, with solutions averaging only 720 tokens (an order of magnitude shorter than typical CoTs). Using LiteCoT, we distilled a new family of reasoning models called Liter (1.5B, 7B, and 32B) based on the Qwen2.5 architecture. Experiments show that a student model fine-tuned on just 100K of these difficulty-pruned CoT samples outperforms a model distilled on 800K original Long CoT samples, while significantly reducing training and inference costs. Our method also generalizes well: across 11 diverse benchmarks, the shorter difficulty-aware CoTs achieve equal or better accuracy than Long chains, using far fewer tokens. For example, on the challenging AIME24 exam, our approach reaches $74.2\%$ Pass@1 using only about 5K inference tokens, surpassing other methods that consume many more tokens. Our code and data are available at https://github.com/Evanwu1125/LiteCoT.

Text Image Machine Translation (TIMT)-the task of translating textual content embedded in images-is critical for applications in accessibility, cross-lingual information access, and real-world document understanding. However, TIMT remains a complex challenge due to the need for accurate optical character recognition (OCR), robust visual-text reasoning, and high-quality translation, often requiring cascading multi-stage pipelines. Recent advances in large-scale Reinforcement Learning (RL) have improved reasoning in Large Language Models (LLMs) and Multimodal LLMs (MLLMs), but their application to end-to-end TIMT is still underexplored. To bridge this gap, we introduce MT$^{3}$, the first framework to apply Multi-Task RL to MLLMs for end-to-end TIMT. MT$^{3}$ adopts a multi-task optimization paradigm targeting three key sub-skills: text recognition, context-aware reasoning, and translation. It is trained using a novel multi-mixed reward mechanism that adapts rule-based RL strategies to TIMT's intricacies, offering fine-grained, non-binary feedback across tasks. Furthermore, to facilitate the evaluation of TIMT in authentic cross-cultural and real-world social media contexts, we introduced XHSPost, the first social media TIMT benchmark. Our MT$^{3}$-7B-Zero achieves state-of-the-art results on the latest in-domain MIT-10M benchmark, outperforming strong baselines such as Qwen2.5-VL-72B and InternVL2.5-78B by notable margins across multiple metrics. Additionally, the model shows strong generalization to out-of-distribution language pairs and datasets. In-depth analyses reveal how multi-task synergy, reinforcement learning initialization, curriculum design, and reward formulation contribute to advancing MLLM-driven TIMT.