'The White Lotus' creator Mike White drops a hint about the Season 4 location Mashable Tech Science Life Social Good Entertainment Deals Shopping Games Search Cancel * * Search Result Tech Apps & Software Artificial Intelligence Cybersecurity Cryptocurrency Mobile Smart Home Social Media Tech Industry Transportation All Tech Science Space Climate Change Environment All Science Life Digital Culture Family & Parenting Health & Wellness Sex, Dating & Relationships Sleep Careers Mental Health All Life Social Good Activism Gender LGBTQ Racial Justice Sustainability Politics All Social Good Entertainment Games Movies Podcasts TV Shows Watch Guides All Entertainment SHOP THE BEST Laptops Budget Laptops Dating Apps Sexting Apps Hookup Apps VPNs Robot Vaccuums Robot Vaccum & Mop Headphones Speakers Kindles Gift Guides Mashable Choice Mashable Selects All Sex, Dating & Relationships All Laptops All Headphones All Robot Vacuums All VPN All Shopping Games Product Reviews Adult Friend Finder Bumble Premium Tinder Platinum Kindle Paperwhite PS5 vs PS5 Slim All Reviews All Shopping Deals Newsletters VIDEOS Mashable Shows All Videos Home Entertainment TV Shows'The White Lotus' creator Mike White drops a hint about the Season 4 location "I don't think we're gonna go South America." By Sam Haysom Sam Haysom Sam Haysom is the Deputy UK Editor for Mashable. He covers entertainment and online culture, and writes horror fiction in his spare time. Read Full Bio on April 9, 2025 Share on Facebook Share on Twitter Share on Flipboard Watch Next'The White Lotus' Season 3 trailer teases debauchery in Thailand'The White Lotus' Season 3 cast meeting Moo Deng is the crossover you didn't know you needed'The White Lotus' Season 3 star Natasha Rothwell shares BTS of meeting her lizard co-star'The White Lotus' Season 3, episode 6 trailer teases rising tension The White Lotus has so far taken place in Hawaii, Italy, and most recently Thailand -- but where might be a good spot for Season 4? Speaking to Howard Stern following the Season 3 finale, creator Mike White revealed that he's about to set off for Colombia to get out of LA. "Are you thinking maybe the next season will take place in Colombia, so you're going to do research?" asks Stern. "I don't think we're gonna go South America, I think probably not," responds White.

Benefiting from the powerful language expression and planning capabilities of Large Language Models (LLMs), LLM-based autonomous agents have achieved promising performance in various downstream tasks. Recently, based on the development of single-agent systems, researchers propose to construct LLM-based multi-agent systems to tackle more complicated tasks. In this paper, we propose a novel framework, named COPPER, to enhance the collaborative capabilities of LLM-based agents with the self-reflection mechanism. To improve the quality of reflections, we propose to fine-tune a shared reflector, which automatically tunes the prompts of actor models using our counterfactual PPO mechanism. On the one hand, we propose counterfactual rewards to assess the contribution of a single agent's reflection within the system, alleviating the credit assignment problem. On the other hand, we propose to train a shared reflector, which enables the reflector to generate personalized reflections according to agent roles, while reducing the computational resource requirements and improving training stability. We conduct experiments on three datasets to evaluate the performance of our model in multihop question answering, mathematics, and chess scenarios. Experimental results show that COPPER possesses stronger reflection capabilities and exhibits excellent generalization performance across different actor models.

The superior generation capabilities of Denoised Diffusion Probabilistic Models (DDPMs) have been effectively showcased across a multitude of domains. Recently, the application of DDPMs has extended to time series generation tasks, where they have significantly outperformed other deep generative models, often by a substantial margin. However, we have discovered two main challenges with these methods: 1) the inference time is excessively long; 2) there is potential for improvement in the quality of the generated time series. In this paper, we propose a method based on discrete token modeling technique called Similarity-driven Discrete Transformer (SDformer). Specifically, SDformer utilizes a similarity-driven vector quantization method for learning high-quality discrete token representations of time series, followed by a discrete Transformer for data distribution modeling at the token level. Comprehensive experiments show that our method significantly outperforms competing approaches in terms of the generated time series quality while also ensuring a short inference time. Furthermore, without requiring retraining, SDformer can be directly applied to predictive tasks and still achieve commendable results.

As the usage of large language models (LLMs) grows, it becomes increasingly important to serve them quickly and efficiently. While speculative decoding has recently emerged as a promising direction for accelerating LLM serving, existing methods are limited in their ability to scale to larger speculation budgets and adapt to different hyperparameters.

However, identifying the original base model of an LLM is challenging due to potential parameter alterations. In this study, we introduce HuRef, a humanreadable fingerprint for LLMs that uniquely identifies the base model without interfering with training or exposing model parameters to the public. We first observe that the vector direction of LLM parameters remains stable after the model has converged during pretraining, with negligible perturbations through subsequent training steps, including continued pretraining, supervised fine-tuning, and RLHF, which makes it a sufficient condition to identify the base model. The necessity is validated by continuing to train an LLM with an extra term to drive away the model parameters' direction and the model becomes damaged. However, this direction is vulnerable to simple attacks like dimension permutation or matrix rotation, which significantly change it without affecting performance.

Intelligent agents must be generalists, capable of quickly adapting to various tasks. In reinforcement learning (RL), model-based RL learns a dynamics model of the world, in principle enabling transfer to arbitrary reward functions through planning. However, autoregressive model rollouts suffer from compounding error, making model-based RL ineffective for long-horizon problems. Successor features offer an alternative by modeling a policy's long-term state occupancy, reducing policy evaluation under new rewards to linear regression. Yet, policy optimization with successor features can be challenging. This work proposes a novel class of models, i.e., Distributional Successor Features for Zero-Shot Policy Optimization (DiSPOs), that learn a distribution of successor features of a stationary dataset's behavior policy, along with a policy that acts to realize different successor features within the dataset. By directly modeling long-term outcomes in the dataset, DiSPOs avoid compounding error while enabling a simple scheme for zero-shot policy optimization across reward functions. We present a practical instantiation of DiSPOs using diffusion models and show their efficacy as a new class of transferable models, both theoretically and empirically across various simulated robotics problems.

When Large Language Models (LLMs) are compressed using techniques such as quantization, the predominant way to demonstrate the validity of such techniques is by measuring the model's accuracy on various benchmarks. If the accuracies of the baseline model and the compressed model are close, it is assumed that there was negligible degradation in quality. However, even when the accuracies of the baseline and compressed model are similar, we observe the phenomenon of flips, wherein answers change from correct to incorrect and vice versa in proportion. We conduct a detailed study of metrics across multiple compression techniques, models and datasets, demonstrating that the behavior of compressed models as visible to end-users is often significantly different from the baseline model, even when accuracy is similar. We further evaluate compressed models both qualitatively and quantitatively using MT-Bench and show that compressed models exhibiting high flips are worse than baseline models in this free-form generative task. Thus, we argue that accuracy and perplexity are necessary but not sufficient for evaluating compressed models, since these metrics hide large underlying changes that have not been observed by previous work. Hence, compression techniques should also be evaluated using distance metrics. We propose two such distance metrics, KL-Divergence and % flips, and show that they are well correlated.

In the visual spatial understanding (VSU) area, spatial image-to-text (SI2T) and spatial text-to-image (ST2I) are two fundamental tasks that appear in dual form. Existing methods for standalone SI2T or ST2I perform imperfectly in spatial understanding, due to the difficulty of 3D-wise spatial feature modeling. In this work, we consider modeling the SI2T and ST2I together under a dual learning framework. During the dual framework, we then propose to represent the 3D spatial scene features with a novel 3D scene graph (3DSG) representation that can be shared and beneficial to both tasks.

As Large Language Models (LLMs) are increasingly deployed in specialized domains with continuously evolving knowledge, the need for timely and precise knowledge injection has become essential. Fine-tuning with paraphrased data is a common approach to enhance knowledge injection, yet it faces two significant challenges: high computational costs due to repetitive external model usage and limited sample diversity. To this end, we introduce LaPael, a latent-level paraphrasing method that applies input-dependent noise to early LLM layers. This approach enables diverse and semantically consistent augmentations directly within the model. Furthermore, it eliminates the recurring costs of paraphrase generation for each knowledge update. Our extensive experiments on question-answering benchmarks demonstrate that LaPael improves knowledge injection over standard fine-tuning and existing noise-based approaches. Additionally, combining LaPael with data-level paraphrasing further enhances performance.

In this technical supplement, we provide detailed insights and additional results to support our main paper. Section A.1 outlines the generation process of the SynRS3D dataset, including the tools and plugins used. It also covers the licenses for these plugins. Section A.3 elaborates on the evaluation metrics for different tasks, including the proposed F Section A.4 describes the experimental setup and the selection of hyperparameters for the RS3DAda method. Section A.5 presents the ablation study results and analysis for the RS3DAda method. Section A.6 provides supplementary experimental results combining SynRS3D and real data scenarios, complementing Section 5.2 of the main paper. Section A.9 highlights the performance of models trained on the SynRS3D dataset using RS3DAda in the critical application of disaster mapping in remote sensing. A.1 Detailed Generation Workflow of SynRS3D The generation workflow of SynRS3D involves several key steps, from initializing sensor and sunlight parameters to generating the layout, geometry, and textures of the scene. This comprehensive process ensures that the generated SynRS3D mimics real-world remote sensing scenarios with high fidelity. The main steps of the workflow are as follows: Initialization: Set up the sensor and sunlight parameters using uniform and normal distributions to simulate various conditions. Layout Generation: Define the grid and terrain parameters to create diverse urban and natural environments. Texture Generation: Use advanced models like GPT-4 [1] and Stable Diffusion [18] to generate realistic textures for different categories of land cover.