Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and healthcare. To address this, Constrained Markov Decision Processes (CMDPs) are commonly used to enforce safety constraints while optimizing performance. However, existing methods often suffer from significant safety violations or require a high sample complexity to generate near-optimal policies. We address two settings: relaxed feasibility, where small violations are allowed, and strict feasibility, where no violation is allowed. We propose a model-based primal-dual algorithm that balances regret and bounded constraint violations, drawing on techniques from online RL and constrained optimization.

AI agents today are mostly siloed -- they either retrieve and reason over vast amount of digital information and knowledge obtained online; or interact with the physical world through embodied perception, planning and action -- but rarely both. This separation limits their ability to solve tasks that require integrated physical and digital intelligence, such as cooking from online recipes, navigating with dynamic map data, or interpreting real-world landmarks using web knowledge. We introduce \textsc{Embodied Web Agents}, a novel paradigm for AI agents that fluidly bridge embodiment and web-scale reasoning. To operationalize this concept, we first develop the \textsc{Embodied Web Agents} task environments, a unified simulation platform that integrates realistic 3D indoor and outdoor environments with functional web interfaces. Building upon this platform, we construct and release the \textsc{Embodied Web Agents} Benchmark, which encompasses a diverse suite of tasks including cooking, navigation, shopping, tourism, and geolocation -- all requiring coordinated reasoning across physical and digital realms for systematic assessment of cross-domain intelligence. Experimental results reveal significant performance gaps between state-of-the-art AI systems and human capabilities, establishing both challenges and opportunities at the intersection of embodied cognition and web-scale knowledge access.

This paper presents improved native unified multimodal models, \emph{i.e.,} Show-o2, that leverage autoregressive modeling and flow matching. Built upon a 3D causal variational autoencoder space, unified visual representations are constructed through a dual-path of spatial (-temporal) fusion, enabling scalability across image and video modalities while ensuring effective multimodal understanding and generation. Based on a language model, autoregressive modeling and flow matching are natively applied to the language head and flow head, respectively, to facilitate text token prediction and image/video generation. A two-stage training recipe is designed to effectively learn and scale to larger models. The resulting Show-o2 models demonstrate versatility in handling a wide range of multimodal understanding and generation tasks across diverse modalities, including text, images, and videos. Code and models are released at https://github.com/showlab/Show-o.

Musk's $1.8 trillion SpaceX IPO could be'highly undesirable' for some SpaceX is expected to debut on the United States' public markets on Friday in what will be the largest initial public offering (IPOs). Artificial intelligence (AI) giants OpenAI and Anthropic are also widely expected to go public soon, and thanks to a new rule change by tech stock exchange Nasdaq, individual investors could own stock of these companies when they go public in as soon as 15 business days following its first trading day. SpaceX's IPO is generating buzz among retail investors. The Elon Musk-led company is expected to allocate 20 percent of shares to retail investors and has drawn roughly $70bn in orders, according to the Reuters news agency. Historically, there is a waiting period between when a company goes public and when it is listed on the Nasdaq-100 index and/or S&P 500.

Restoring images degraded by adverse weather remains a significant challenge due to the highly non-uniform and spatially heterogeneous nature of weather-induced artifacts, \emph{e.g.}, fine-grained rain streaks versus widespread haze. Accurately estimating the underlying degradation can intuitively provide restoration models with more targeted and effective guidance, enabling adaptive processing strategies. To this end, we propose a Morton-Order Degradation Estimation Mechanism (MODEM) for adverse weather image restoration. Central to MODEM is the Morton-Order 2D-Selective-Scan Module (MOS2D), which integrates Morton-coded spatial ordering with selective state-space models to capture long-range dependencies while preserving local structural coherence. Complementing MOS2D, we introduce a Dual Degradation Estimation Module (DDEM) that disentangles and estimates both global and local degradation priors.

We propose L2T, an advancement of visual instruction tuning (VIT). While VIT equips Multimodal LLMs (MLLMs) with promising multimodal capabilities, the current design choices for VIT often result in overfitting and shortcut learning, potentially degrading performance. This gap arises from an overemphasis on instruction-following abilities, while neglecting the proactive understanding of visual information. Inspired by this, L2T adopts a simple yet effective approach by incorporating the loss function into both the instruction and response sequences. It seamlessly expands the training data, and regularizes the MLLMs from overly relying on language priors. Based on this merit, L2T achieves a significant relative improvement of up to 9% on comprehensive multimodal benchmarks, requiring no additional training data and incurring negligible computational overhead.

Classifier-Free Guidance (CFG) significantly enhances controllability in generative models by interpolating conditional and unconditional predictions. However, standard CFG often employs a static unconditional input, which can be suboptimal for iterative generation processes where model uncertainty varies dynamically. We introduce Adaptive Classifier-Free Guidance (A-CFG), a novel method that tailors the unconditional input by leveraging the model's instantaneous predictive confidence. At each step of an iterative (masked) diffusion language model, A-CFG identifies tokens in the currently generated sequence for which the model exhibits low confidence. These tokens are temporarily re-masked to create a dynamic, localized unconditional input. This focuses CFG's corrective influence precisely on areas of ambiguity, leading to more effective guidance. We integrate A-CFG into a state-of-the-art masked diffusion language model and demonstrate its efficacy. Experiments on diverse language generation benchmarks show that A-CFG yields substantial improvements over standard CFG, achieving, for instance, a 3.9 point gain on GPQA. Our work highlights the benefit of dynamically adapting guidance mechanisms to model uncertainty in iterative generation.

To tackle long-horizon tasks, recent hierarchical vision-language-action (VLAs) frameworks employ vision-language model (VLM)-based planners to decompose complex manipulation tasks into simpler sub-tasks that low-level visuomotor policies can handle. Typically, the VLM planner needs finetuning to learn to decompose a new task, which requires target task demonstrations segmented into sub-tasks by either human annotation or heuristic rules.

Spiking Neural Networks (SNNs), as a biologically inspired neural network architecture, have garnered significant attention due to their exceptional energy efficiency and increasing potential for various applications. In this work, we extend the use of SNNs to neural rendering tasks and introduce Spik-NeRF (Spiking Neural Radiance Fields). We observe that the binary spike activation map of traditional SNNs lacks sufficient information capacity, leading to information loss and a subsequent decline in the performance of spiking neural rendering models. To address this limitation, we propose the use of ternary spike neurons, which enhance the information-carrying capacity in the spiking neural rendering model. With ternary spike neurons, Spik-NeRF achieves performance that is on par with, or nearly identical to, traditional ANN-based rendering models. Additionally, we present a re-parameterization technique for inference that allows Spik-NeRF with ternary spike neurons to retain the event-driven, multiplication-free advantages typical of binary spike neurons. Furthermore, to further boost the performance of Spik-NeRF, we employ a distillation method, using an ANN-based NeRF to guide the training of our Spik-NeRF model, which is more compatible with the ternary neurons compared to the standard binary neurons. We evaluate Spik-NeRF on both realistic and synthetic scenes, and the experimental results demonstrate that Spik-NeRF achieves rendering performance comparable to ANN-based NeRF models.

It has been shown that the chain of thought (CoT) can enhance the power of LLMs to simulate a Turing machine or an algorithm, and in particular its mathematical reasoning ability. The memorization capability of LLMs is an important aspect of their expressive ability, which offers valuable insight into designing models with enhanced generalization potential. Currently, the optimal memorization capacities of transformers have been established for both the general dataset and the dataset that satisfies a specific separability condition. However, the question of whether the CoT can improve the memorization capability of LLMs remains unexamined. To fill this gap, we establish the memorization capability for fixed-precision autoregressive transformers with or without CoT. Precisely, we first give the necessary and sufficient conditions for transformers to memorize a finite language and then provide the upper and lower bounds for the number of parameters of the memorization transformers. Our result indicates that the classes of languages that can be memorized by transformers with or without CoT do not contain each other, and the same number of parameters is needed for transformers with or without CoT to memorize, implying that CoT does not enhance a transformer's memorization power significantly. We further show that CoT can not help transformers to memory certain infinite languages.