Efficient fine-tuning of large language models for task-specific applications is imperative, yet the vast number of parameters in these models makes their training increasingly challenging. Despite numerous proposals for effective methods, a substantial memory overhead remains for gradient computations during updates. Can we fine-tune a series of task-specific small models and transfer their knowledge directly to a much larger model without additional training? In this paper, we explore weak-to-strong specialization using logit arithmetic, facilitating a direct answer to this question. Existing weak-to-strong methods often employ a static knowledge transfer ratio and a single small model for transferring complex knowledge, which leads to suboptimal performance.

However, they often fail to produce realistic geometric details, resulting in overly smooth surfaces or geometric details inaccurately baked in albedo maps. To address this, we introduce a new method that incorporates touch as an additional modality to improve the geometric details of generated 3D assets. We design a lightweight 3D texture field to synthesize visual and tactile textures, guided by 2D diffusion model priors on both visual and tactile domains. We condition the visual texture generation on high-resolution tactile normals and guide the patch-based tactile texture refinement with a customized TextureDreambooth. We further present a multi-part generation pipeline that enables us to synthesize different textures across various regions. To our knowledge, we are the first to leverage high-resolution tactile sensing to enhance geometric details for 3D generation tasks. We evaluate our method in both text-to-3D and image-to-3D settings. Our experiments demonstrate that our method provides customized and realistic fine geometric textures while maintaining accurate alignment between two modalities of vision and touch.

These settings are consistent with CAT-R and CAT-A. For CAT-R-2, we apply regular-Rwin, and set [sw, sh] as [4, 16] (same as CAT-R). We set the MLP expansion ratio as 2, consistent with SwinIR [13]. For CAT-A-2, we apply axial-Rwin, and set sl as 4 for all CATB in each RG. The MLP expansion ratio is set as 4. Best and second best results are colored with red and blue.

Predicting the future trajectory of a person remains a challenging problem, due to randomness and subjectivity of human movement. However, the moving patterns of human in a constrained scenario typically conform to a limited number of regularities to a certain extent, because of the scenario restrictions (e.g., floor plan, roads, and obstacles) and person-person or person-object interactivity. Thus, an individual person in this scenario should follow one of the regularities as well. In other words, a person's subsequent trajectory has likely been traveled by others. Based on this hypothesis, we propose to forecast a person's future trajectory by learning from the implicit scene regularities. We call the regularities, inherently derived from the past dynamics of the people and the environment in the scene, scene history.

Users typically engage with LLMs interactively, yet most existing benchmarks evaluate them in a static, single-turn format, posing reliability concerns in interactive scenarios. We identify a key obstacle towards reliability: LLMs are trained to answer any question, even with incomplete context or insufficient knowledge.

This paper proposes a theoretical analysis of recommendation systems in an online setting, where items are sequentially recommended to users over time. In each round, a user, randomly picked from a population of m users, requests a recommendation. The decision-maker observes the user and selects an item from a catalogue of n items. Importantly, an item cannot be recommended twice to the same user. The probabilities that a user likes each item are unknown. The performance of the recommendation algorithm is captured through its regret, considering as a reference an Oracle algorithm aware of these probabilities. We investigate various structural assumptions on these probabilities: we derive for each structure regret lower bounds, and devise algorithms achieving these limits. Interestingly, our analysis reveals the relative weights of the different components of regret: the component due to the constraint of not presenting the same item twice to the same user, that due to learning the chances users like items, and finally that arising when learning the underlying structure.

For centuries, the Rub' al-Khali desert near Saudi Arabia and Dubai -- known as the Empty Quarter -- was dismissed as a lifeless sea of sand. In 2002, Sheikh Mohammed bin Rashid Al Maktoum, ruler of Dubai, spotted unusual dune formations and a large black deposit while flying over the desert. That led to the discovery of Saruq Al-Hadid, an archaeological site rich in remnants of copper and iron smelting, which is now believed to be part of a 5,000-year-old civilization buried beneath the sands. Researchers have now found traces of this ancient society approximately 10 feet beneath the desert surface, hidden in plain sight and long overlooked due to the harsh environment and shifting dunes of the Empty Quarter. This discovery brings fresh life to the legend of a mythical city known as'Atlantis of the Sands.'

Artificial intelligence systems could account for nearly half of datacentre power consumption by the end of this year, analysis has revealed. The estimates by Alex de Vries-Gao, the founder of the Digiconomist tech sustainability website, came as the International Energy Agency forecast that AI would require almost as much energy by the end of this decade as Japan uses today. De Vries-Gao's calculations, to be published in the sustainable energy journal Joule, are based on the power consumed by chips made by Nvidia and Advanced Micro Devices that are used to train and operate AI models. The paper also takes into account the energy consumption of chips used by other companies, such as Broadcom. The IEA estimates that all data centres – excluding mining for cryptocurrencies – consumed 415 terawatt hours (TWh) of electricity last year.

The best results are highlighted by bold. It can be clearly seen that our alternating reverse filtering network performs the best compared with other state-of-the-art methods in all the indexes, indicating the superiority of our proposed method. Images in the last row are the MSE residues between the fused results and the ground truth. Compared with other competing methods, our model has minor spatial and spectral distortions. It can be easily concluded from the observation of MSE maps.

The machine is designed to inspect industrial sites, respond to disasters, carry out logistics operations and support scientific research. Deep Robotics, a company from China, has unveiled a durable four-legged robot built to operate in extreme environments that humans struggle to traverse. It's called the Lynx M20, and it builds upon the agility of its predecessor, the Lynx robot dog. This versatile machine is designed to handle anything from inspecting industrial sites and responding to disasters to carrying out logistics operations and supporting scientific research. Here's what you need to know.