Search

The discovery of superconductivity in 3$d$-transition metal compounds with strong magnetism is interesting but rare. Especially for Mn-based compounds, there exist only very limited materials that show superconductivity. Here, we report the discovery of superconductivity up to 14.2 K in a Mn-based material MnB$_4$. By applying high pressures, we found the continuous suppression of a weak insulating behavior and the occurrence of superconductivity after about 30 GPa. With further increasing pressure, $T_\text{c}$ is gradually enhanced and reaches the maximum value of about 14.2 K at 150 GPa with a Fermi-Liquid behavior in the normal states. The synchrotron X-ray diffraction data reveal the unchanged monoclinic (S.G: $P2_1/c$) symmetry but an unusual crossover of the lattice parameters $b$ and $c$. Theoretical calculations based on the electron-phonon coupling picture reveal a very low $T_\text{c}$ (less than 1 K), manifesting an exotic pairing mechanism beyond the Bardeen-Cooper-Schrieffer (BCS) theory. Our findings show a promising way to explore high $T_\text{c}$ superconductivity by combining the 3d-transition metal magnetic elements and light elements., Comment: 36 pages total; 24 pages of main text with 5 figures, 12 pages of supplement with 1 table and 8 figures

The precise prediction of multi-scale traffic is a ubiquitous challenge in the urbanization process for car owners, road administrators, and governments. In the case of complex road networks, current and past traffic information from both upstream and downstream roads are crucial since various road networks have different semantic information about traffic. Rationalizing the utilization of semantic information can realize short-term, long-term, and unseen road traffic prediction. As the demands of multi-scale traffic analysis increase, on-demand interactions and visualizations are expected to be available for transportation participants. We have designed a multi-scale traffic generation system, namely TrafficGPT, using three AI agents to process multi-scale traffic data, conduct multi-scale traffic analysis, and present multi-scale visualization results. TrafficGPT consists of three essential AI agents: 1) a text-to-demand agent that is employed with Question & Answer AI to interact with users and extract prediction tasks through texts; 2) a traffic prediction agent that leverages multi-scale traffic data to generate temporal features and similarity, and fuse them with limited spatial features and similarity, to achieve accurate prediction of three tasks; and 3) a suggestion and visualization agent that uses the prediction results to generate suggestions and visualizations, providing users with a comprehensive understanding of traffic conditions. Our TrafficGPT system focuses on addressing concerns about traffic prediction from transportation participants, and conducted extensive experiments on five real-world road datasets to demonstrate its superior predictive and interactive performance

It is well-known that magnetic moments are very harmful to superconductivity. A typical example is the element Mn whose compounds usually exhibit strong magnetism. Thus, it is very hard to achieve superconductivity in materials containing Mn. Here, we report enhanced superconductivity with the superconducting transition temperature ($T_\text{c}$) up to a record high-value of about 26 K in a beta-phase Ti$_{1-x}$Mn$_x$ alloy containing rich magnetic element Mn under high pressures. This is contrary to the intuition that the magnetic moments always suppress superconductivity. Under high pressures, we also found that in the middle-pressure regime, the Pauli limit of the upper critical field is surpassed. The synchrotron X-ray diffraction data shows an unchanged beta-phase with a continuous contraction of the cell volume, which is well supported by the first-principles calculations. Although the theoretical results based on electron-phonon coupling (EPC) can interpret the $T_\text{c}$ value in a certain pressure region, the monotonic enhancement of superconductivity by pressure cannot seek support from the theory. Our results show a surprising enhancement of superconductivity in Ti$_{1-x}$Mn$_x$ alloy with a considerable Mn content., Comment: 28 pages, 5 figures. Comments are welcome and appreciated

We present ZSL-RPPO, an improved zero-shot learning architecture that overcomes the limitations of teacher-student neural networks and enables generating robust, reliable, and versatile locomotion for quadrupedal robots in challenging terrains. We propose a new algorithm RPPO (Recurrent Proximal Policy Optimization) that directly trains recurrent neural network in partially observable environments and results in more robust training using domain randomization. Our locomotion controller supports extensive perturbation across simulation-to-reality transfer for both intrinsic and extrinsic physical parameters without further fine-tuning. This can avoid the significant decline of student's performance during simulation-to-reality transfer and therefore enhance the robustness and generalization of the locomotion controller. We deployed our controller on the Unitree A1 and Aliengo robots in real environment and exteroceptive perception is provided by either a solid-state Lidar or a depth camera. Our locomotion controller was tested in various challenging terrains like slippery surfaces, Grassy Terrain, and stairs. Our experiment results and comparison show that our approach significantly outperforms the state-of-the-art.

With the rapid advancement of large language models (LLMs), there is a pressing need for a comprehensive evaluation suite to assess their capabilities and limitations. Existing LLM leaderboards often reference scores reported in other papers without consistent settings and prompts, which may inadvertently encourage cherry-picking favored settings and prompts for better results. In this work, we introduce GPT-Fathom, an open-source and reproducible LLM evaluation suite built on top of OpenAI Evals. We systematically evaluate 10+ leading LLMs as well as OpenAI's legacy models on 20+ curated benchmarks across 7 capability categories, all under aligned settings. Our retrospective study on OpenAI's earlier models offers valuable insights into the evolutionary path from GPT-3 to GPT-4. Currently, the community is eager to know how GPT-3 progressively improves to GPT-4, including technical details like whether adding code data improves LLM's reasoning capability, which aspects of LLM capability can be improved by SFT and RLHF, how much is the alignment tax, etc. Our analysis sheds light on many of these questions, aiming to improve the transparency of advanced LLMs., Comment: Accepted by NAACL 2024

Marine debris is an important issue for environmental protection, but current methods for locating marine debris are yet limited. In order to achieve higher efficiency and wider applicability in the localization of Marine debris, this study tries to combine the instance segmentation of YOLOv7 with different attention mechanisms and explores the best model. By utilizing a labelled dataset consisting of satellite images containing ocean debris, we examined three attentional models including lightweight coordinate attention, CBAM (combining spatial and channel focus), and bottleneck transformer (based on self-attention). Box detection assessment revealed that CBAM achieved the best outcome (F1 score of 77%) compared to coordinate attention (F1 score of 71%) and YOLOv7/bottleneck transformer (both F1 scores around 66%). Mask evaluation showed CBAM again leading with an F1 score of 73%, whereas coordinate attention and YOLOv7 had comparable performances (around F1 score of 68%/69%) and bottleneck transformer lagged behind at F1 score of 56%. These findings suggest that CBAM offers optimal suitability for detecting marine debris. However, it should be noted that the bottleneck transformer detected some areas missed by manual annotation and displayed better mask precision for larger debris pieces, signifying potentially superior practical performance.

Building a scalable and real-time recommendation system is vital for many businesses driven by time-sensitive customer feedback, such as short-videos ranking or online ads. Despite the ubiquitous adoption of production-scale deep learning frameworks like TensorFlow or PyTorch, these general-purpose frameworks fall short of business demands in recommendation scenarios for various reasons: on one hand, tweaking systems based on static parameters and dense computations for recommendation with dynamic and sparse features is detrimental to model quality; on the other hand, such frameworks are designed with batch-training stage and serving stage completely separated, preventing the model from interacting with customer feedback in real-time. These issues led us to reexamine traditional approaches and explore radically different design choices. In this paper, we present Monolith, a system tailored for online training. Our design has been driven by observations of our application workloads and production environment that reflects a marked departure from other recommendations systems. Our contributions are manifold: first, we crafted a collisionless embedding table with optimizations such as expirable embeddings and frequency filtering to reduce its memory footprint; second, we provide an production-ready online training architecture with high fault-tolerance; finally, we proved that system reliability could be traded-off for real-time learning. Monolith has successfully landed in the BytePlus Recommend product., Comment: ORSUM@ACM RecSys 2022

Rayleigh scattering of the cosmic microwave background (CMB) by neutral hydrogen shortly after recombination leaves frequency-dependent imprints on intensity and polarization fluctuations. High signal-to-noise observations of CMB Rayleigh scattering would provide additional insight into the physics of recombination, including greater constraining power for parameters like the primordial helium fraction, the light relic density, and the sum of neutrino masses. However, such a measurement of CMB Rayleigh scattering is challenging due to the presence of astrophysical foregrounds, which are more intense at the high frequencies, where the effects of Rayleigh scattering are most prominent. Here we forecast the detectability of CMB Rayleigh scattering including foreground removal using blind internal linear combination methods for a set of near-future surveys. We show that atmospheric effects for ground-based observatories and astrophysical foregrounds pose a significant hindrance to detecting CMB Rayleigh scattering with experiments planned for this decade, though a high-significance measurement should be possible with a future CMB satellite., Comment: 14 pages, 12 figures

The click-through rate (CTR) prediction task is to predict whether a user will click on the recommended item. As mind-boggling amounts of data are produced online daily, accelerating CTR prediction model training is critical to ensuring an up-to-date model and reducing the training cost. One approach to increase the training speed is to apply large batch training. However, as shown in computer vision and natural language processing tasks, training with a large batch easily suffers from the loss of accuracy. Our experiments show that previous scaling rules fail in the training of CTR prediction neural networks. To tackle this problem, we first theoretically show that different frequencies of ids make it challenging to scale hyperparameters when scaling the batch size. To stabilize the training process in a large batch size setting, we develop the adaptive Column-wise Clipping (CowClip). It enables an easy and effective scaling rule for the embeddings, which keeps the learning rate unchanged and scales the L2 loss. We conduct extensive experiments with four CTR prediction networks on two real-world datasets and successfully scaled 128 times the original batch size without accuracy loss. In particular, for CTR prediction model DeepFM training on the Criteo dataset, our optimization framework enlarges the batch size from 1K to 128K with over 0.1% AUC improvement and reduces training time from 12 hours to 10 minutes on a single V100 GPU. Our code locates at https://github.com/bytedance/LargeBatchCTR., Comment: AAAI 2023