Recent video diffusion models have enhanced video editing, but it remains challenging to handle instructional editing and diverse tasks (e.g., adding, removing, changing) within a unified framework. In this paper, we introduce VEGGIE, a Video Editor with Grounded Generation from Instructions, a simple end-to-end framework that unifies video concept editing, grounding, and reasoning based on diverse user instructions. Specifically, given a video and text query, VEGGIE first utilizes an MLLM to interpret user intentions in instructions and ground them to the video contexts, generating frame-specific grounded task queries for pixel-space responses. A diffusion model then renders these plans and generates edited videos that align with user intent. To support diverse tasks and complex instructions, we employ a curriculum learning strategy: first aligning the MLLM and video diffusion model with large-scale instructional image editing data, followed by end-to-end fine-tuning on high-quality multitask video data. Additionally, we introduce a novel data synthesis pipeline to generate paired instructional video editing data for model training. It transforms static image data into diverse, high-quality video editing samples by leveraging Image-to-Video models to inject dynamics. VEGGIE shows strong performance in instructional video editing with different editing skills, outperforming the best instructional baseline as a versatile model, while other models struggle with multi-tasking. VEGGIE also excels in video object grounding and reasoning segmentation, where other baselines fail. We further reveal how the multiple tasks help each other and highlight promising applications like zero-shot multimodal instructional and in-context video editing.

Humanoid robots are anticipated to acquire a wide range of locomotion capabilities while ensuring natural movement across varying speeds and terrains. Existing methods encounter a fundamental dilemma in learning humanoid locomotion: reinforcement learning with handcrafted rewards can achieve agile locomotion but produces unnatural gaits, while Generative Adversarial Imitation Learning (GAIL) with motion capture data yields natural movements but suffers from unstable training processes and restricted agility. Integrating these approaches proves challenging due to the inherent heterogeneity between expert policies and human motion datasets. To address this, we introduce StyleLoco, a novel two-stage framework that bridges this gap through a Generative Adversarial Distillation (GAD) process. Our framework begins by training a teacher policy using reinforcement learning to achieve agile and dynamic locomotion. It then employs a multi-discriminator architecture, where distinct discriminators concurrently extract skills from both the teacher policy and motion capture data. This approach effectively combines the agility of reinforcement learning with the natural fluidity of human-like movements while mitigating the instability issues commonly associated with adversarial training. Through extensive simulation and real-world experiments, we demonstrate that StyleLoco enables humanoid robots to perform diverse locomotion tasks with the precision of expertly trained policies and the natural aesthetics of human motion, successfully transferring styles across different movement types while maintaining stable locomotion across a broad spectrum of command inputs.

--Simulation-based testing has emerged as an essential tool for verifying and validating autonomous vehicles (A Vs). However, contemporary methodologies, such as deterministic and imitation learning-based driver models, struggle to capture the variability of human-like driving behavior . Given these challenges, we propose HAD-Gen, a general framework for realistic traffic scenario generation that simulates diverse human-like driving behaviors. It then employs maximum entropy inverse reinforcement learning on each of the clusters to learn the reward function corresponding to each driving style. Using these reward functions, the method integrates offline reinforcement learning pre-training and multi-agent reinforcement learning algorithms to obtain general and robust driving policies. Multi-perspective simulation results show that our proposed scenario generation framework can simulate diverse, human-like driving behaviors with strong generalization capability. The proposed framework achieves a 90.96% goal-reaching rate, an off-road rate of 2.08%, and a collision rate of 6.91% in the generalization test, outperforming prior approaches by over 20% in goal-reaching performance. UTONOMOUS vehicles (A Vs) represent a groundbreaking advancement in transportation technology, with the potential to enhance road safety, reduce traffic congestion, and improve overall mobility efficiency [1]. Over the past decade, significant progress has been made in transforming A Vs from theoretical concepts into practical implementations, with numerous prototypes successfully navigating urban environments [2]. Despite these advancements, ensuring the safety and reliability of A Vs across diverse real-world scenarios remains a significant challenge [3]. This work was funded by UK Research and Innovation (UKRI) under the UK government's Horizon Europe funding guarantee [grant number EP/Z533464/1]. Cheng Wang is with the School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh EH14 4AS, United Kingdom (e-mail: cheng.wang@hw.ac.uk). Lingxin Kong is with the School of Automation and Software Engineering, Shanxi University, Taiyuan 030031, China (e-mail: 202223601006@email.sxu.edu.cn).

Masked Diffusion Models (MDMs) have emerged as a powerful generative modeling technique. Despite their remarkable results, they typically suffer from slow inference with several steps. In this paper, we propose Di$\mathtt{[M]}$O, a novel approach that distills masked diffusion models into a one-step generator. Di$\mathtt{[M]}$O addresses two key challenges: (1) the intractability of using intermediate-step information for one-step generation, which we solve through token-level distribution matching that optimizes model output logits by an 'on-policy framework' with the help of an auxiliary model; and (2) the lack of entropy in the initial distribution, which we address through a token initialization strategy that injects randomness while maintaining similarity to teacher training distribution. We show Di$\mathtt{[M]}$O's effectiveness on both class-conditional and text-conditional image generation, impressively achieving performance competitive to multi-step teacher outputs while drastically reducing inference time. To our knowledge, we are the first to successfully achieve one-step distillation of masked diffusion models and the first to apply discrete distillation to text-to-image generation, opening new paths for efficient generative modeling.

Dialogic learning fosters motivation and deeper understanding in education through purposeful and structured dialogues. Foundational models offer a transformative potential for child-robot interactions, enabling the design of personalized, engaging, and scalable interactions. However, their integration into educational contexts presents challenges in terms of ensuring age-appropriate and safe content and alignment with pedagogical goals. We introduce a hybrid approach to designing personalized educational dialogues in child-robot interactions. By combining rule-based systems with LLMs for selective offline content generation and human validation, the framework ensures educational quality and developmental appropriateness. We illustrate this approach through a project aimed at enhancing reading motivation, in which a robot facilitated book-related dialogues.

Robotics Reinforcement Learning (RL) often relies on carefully engineered auxiliary rewards to supplement sparse primary learning objectives to compensate for the lack of large-scale, real-world, trial-and-error data. While these auxiliary rewards accelerate learning, they require significant engineering effort, may introduce human biases, and cannot adapt to the robot's evolving capabilities during training. In this paper, we introduce Reward Training Wheels (RTW), a teacher-student framework that automates auxiliary reward adaptation for robotics RL. To be specific, the RTW teacher dynamically adjusts auxiliary reward weights based on the student's evolving capabilities to determine which auxiliary reward aspects require more or less emphasis to improve the primary objective. We demonstrate RTW on two challenging robot tasks: navigation in highly constrained spaces and off-road vehicle mobility on vertically challenging terrain. In simulation, RTW outperforms expert-designed rewards by 2.35% in navigation success rate and improves off-road mobility performance by 122.62%, while achieving 35% and 3X faster training efficiency, respectively. Physical robot experiments further validate RTW's effectiveness, achieving a perfect success rate (5/5 trials vs. 2/5 for expert-designed rewards) and improving vehicle stability with up to 47.4% reduction in orientation angles.

Large Language Models (LLMs) have revo lutionized natural language processing Natural Language Processing (NLP), with Chat Generative Pre-trained Transformer (ChatGPT) standing out as a notable exampledue to its advanced capabilities and widespread applications. This survey provides a comprehensive analysis of ChatGPT, exploring its architecture, training processes, and functionalities. We examine its integration into various domains across industries such as customer service, education, healthcare, and entertainment. A comparative analysis with other LLMs highlights ChatGPT's unique features and performance metrics. Regarding benchmarks, the paper examines ChatGPT's comparative performance against other LLMs and discusses potential risks such as misinformation, bias, and data privacy concerns. Additionally, we offer a number of figures and tables that outline the backdrop of the discussion, the main ideas of the article, the numerous LLM models, a thorough list of datasets used for pre-training, fine-tuning, and evaluation, as well as particular LLM applications with pertinent references. Finally, we identify future research directions and technological advancements, underscoring the evolving landscape of LLMs and their profound impact on artificial intelligence Artificial Intelligence (AI) and society.

--Ensemble learning plays a crucial role in practical applications of online learning due to its enhanced classification performance and adaptable adjustment mechanisms. However, most weight allocation strategies in ensemble learning are heuristic, making it challenging to theoretically guarantee that the ensemble classifier outperforms its base classifiers. T o address this issue, a performance-bounded online ensemble learning method based on multi-armed bandits, named PB-OEL, is proposed in this paper . Specifically, multi-armed bandit with expert advice is incorporated into online ensemble learning, aiming to update the weights of base classifiers and make predictions. A theoretical framework is established to bound the performance of the ensemble classifier relative to base classifiers. By setting expert advice of bandits, the bound exceeds the performance of any base classifier when the length of data stream is sufficiently large. Additionally, performance bounds for scenarios with limited annotations are also derived. Numerous experiments on benchmark datasets and a dataset of real-time safety assessment tasks are conducted. The experimental results validate the theoretical bound to a certain extent and demonstrate that the proposed method outperforms existing state-of-the-art methods. Index T erms --Online ensemble learning, performance bound, multi-armed bandits, concept drift, real-time safety assessment. NLINE learning (OL) holds significant potential for handling continuous data and is widely applied across various domains, including industry, recommendation systems, finance, and control systems [1]-[5]. The objective of OL is to continuously learn and update models from new data, enabling adaptation to non-stationary environments for optimized predictions or decisions. One mainstream idea in OL relies on maintaining a set of vectors for decision, as exemplified by the perceptron algorithm [6], passive-aggressive algorithm [7], confidence weighted-based algorithm [8] and imbalanced class weighted-based algorithm [9].

Learning to reason and carefully explain arguments is central to students' cognitive, mathematical, and computational thinking development. This is particularly challenging in problems under uncertainty and in Bayesian reasoning. With the new generation of large language models (LLMs) capable of reasoning using Chain-of-Thought (CoT), there is an excellent opportunity to learn with them as they explain their reasoning through a dialogue with their artificial internal voice. It is an engaging and excellent opportunity to learn Bayesian reasoning. Furthermore, given that different LLMs sometimes arrive at opposite solutions, CoT generates opportunities for deep learning by detailed comparisons of reasonings. However, unlike humans, we found that they do not autonomously explain using ecologically valid strategies like natural frequencies, whole objects, and embodied heuristics. This is unfortunate, as these strategies help humans avoid critical mistakes and have proven pedagogical value in Bayesian reasoning. In order to overcome these biases and aid understanding and learning, we included prompts that induce LLMs to use these strategies. We found that LLMs with CoT incorporate them but not consistently. They show persistent biases towards symbolic reasoning and avoidance or phobia of ecologically valid strategies.

Large Language Models (LLMs) have demonstrated promising capabilities in solving mathematical reasoning tasks, leveraging Chain-of-Thought (CoT) data as a vital component in guiding answer generation. Current paradigms typically generate CoT and answers directly for a given problem, diverging from human problem-solving strategies to some extent. Humans often solve problems by recalling analogous cases and leveraging their solutions to reason about the current task. Inspired by this cognitive process, we propose \textbf{MetaLadder}, a novel framework that explicitly prompts LLMs to recall and reflect on meta-problems, those structurally or semantically analogous problems, alongside their CoT solutions before addressing the target problem. Additionally, we introduce a problem-restating mechanism to enhance the model's comprehension of the target problem by regenerating the original question, which further improves reasoning accuracy. Therefore, the model can achieve reasoning transfer from analogical problems, mimicking human-like "learning from examples" and generalization abilities. Extensive experiments on mathematical benchmarks demonstrate that our MetaLadder significantly boosts LLMs' problem-solving accuracy, largely outperforming standard CoT-based methods (\textbf{10.3\%} accuracy gain) and other methods. Our code and data has been released at https://github.com/LHL3341/MetaLadder.