Search

Recent works have shown that neural radiance fields (NeRFs) on top of parametric models have reached SOTA quality to build photorealistic head avatars from a monocular video. However, one major limitation of the NeRF-based avatars is the slow rendering speed due to the dense point sampling of NeRF, preventing them from broader utility on resource-constrained devices. We introduce LightAvatar, the first head avatar model based on neural light fields (NeLFs). LightAvatar renders an image from 3DMM parameters and a camera pose via a single network forward pass, without using mesh or volume rendering. The proposed approach, while being conceptually appealing, poses a significant challenge towards real-time efficiency and training stability. To resolve them, we introduce dedicated network designs to obtain proper representations for the NeLF model and maintain a low FLOPs budget. Meanwhile, we tap into a distillation-based training strategy that uses a pretrained avatar model as teacher to synthesize abundant pseudo data for training. A warping field network is introduced to correct the fitting error in the real data so that the model can learn better. Extensive experiments suggest that our method can achieve new SOTA image quality quantitatively or qualitatively, while being significantly faster than the counterparts, reporting 174.1 FPS (512x512 resolution) on a consumer-grade GPU (RTX3090) with no customized optimization., Comment: Appear in ECCV'24 CADL Workshop. Code: https://github.com/MingSun-Tse/LightAvatar-TensorFlow

We investigate the localization behavior of two-body Hubbard model in the presence of non-reciprocal tunneling, where the interaction induced Anderson localization competes with the non-Hermitian skin effects and gives rise to diverse patterns of density profiles. Here, we present the non-Hermitian bound states obtained with the center of mass methods in the conditions of strong repulsive interaction, where a faded diagonal line localization is observed. While for the continuum limit, the non-Hermitian skin effects are manifested by non-zero windings of the eigen-energy spectrum. For the moderate interaction strength, it is illustrated that the system possesses multiple Lyapunov exponents due to the competence above and as a consequence, in sharp contrast to the corner localization, the two-body non-Hermitian continuum states can exhibit multiple localization center. By further including two-photon tunneling, topological nontrivial photon bound pairs can be obtained. Finally, the experimental simulations are proposed based on the platforms of the electrical circuit lattices.

Autonomous agents powered by large language models (LLMs) have attracted significant research interest. However, the open-source community faces many challenges in developing specialized models for agent tasks, driven by the scarcity of high-quality agent datasets and the absence of standard protocols in this area. We introduce and publicly release xLAM, a series of large action models designed for AI agent tasks. The xLAM series includes five models with both dense and mixture-of-expert architectures, ranging from 1B to 8x22B parameters, trained using a scalable, flexible pipeline that unifies, augments, and synthesizes diverse datasets to enhance AI agents' generalizability and performance across varied environments. Our experimental results demonstrate that xLAM consistently delivers exceptional performance across multiple agent ability benchmarks, notably securing the 1st position on the Berkeley Function-Calling Leaderboard, outperforming GPT-4, Claude-3, and many other models in terms of tool use. By releasing the xLAM series, we aim to advance the performance of open-source LLMs for autonomous AI agents, potentially accelerating progress and democratizing access to high-performance models for agent tasks. Models are available at https://huggingface.co/collections/Salesforce/xlam-models-65f00e2a0a63bbcd1c2dade4, Comment: Technical report for the Salesforce xLAM model series

We theoretically propose that van der Waals monolayer Re(Ag$X_3$)$_2$ ($X=$ Cl, Br, I) have four consecutive flat Chern bands in the 120$^\circ$ spiral antiferromagnetic ground state. The nontrivial topology of these Chern bands emerges from the synergy between Re $t_{2g}$ band folding with non-collinear spin configuration and spin-orbit coupling. By constructing maximally localized Wannier functions directly from first-principles calculations, the tight-binding model is developed to describe the consecutive Chern bands. Exact diagonalization suggests that $1/3$ filling of these Chern bands host correlated states such as fractional Chern insulator and charge density wave state. Interestingly, the spin configurations and band topology of Chern bands are tunable by external magnetic field. The general physics from the $d$ orbitals here applies to a large class materials such as Re(Cu$X_3$)$_2$ and Re(Au$X_3$)$_2$. These interesting predictions, if realized experimentally, could greatly promote the research and application of topological quantum physics at elevated temperature.

We present xGen-VideoSyn-1, a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. Building on recent advancements, such as OpenAI's Sora, we explore the latent diffusion model (LDM) architecture and introduce a video variational autoencoder (VidVAE). VidVAE compresses video data both spatially and temporally, significantly reducing the length of visual tokens and the computational demands associated with generating long-sequence videos. To further address the computational costs, we propose a divide-and-merge strategy that maintains temporal consistency across video segments. Our Diffusion Transformer (DiT) model incorporates spatial and temporal self-attention layers, enabling robust generalization across different timeframes and aspect ratios. We have devised a data processing pipeline from the very beginning and collected over 13M high-quality video-text pairs. The pipeline includes multiple steps such as clipping, text detection, motion estimation, aesthetics scoring, and dense captioning based on our in-house video-LLM model. Training the VidVAE and DiT models required approximately 40 and 642 H100 days, respectively. Our model supports over 14-second 720p video generation in an end-to-end way and demonstrates competitive performance against state-of-the-art T2V models., Comment: Accepted by ECCV24 AI4VA

This report introduces xGen-MM (also known as BLIP-3), a framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs. xGen-MM, short for xGen-MultiModal, expands the Salesforce xGen initiative on foundation AI models. Our models undergo rigorous evaluation across a range of tasks, including both single and multi-image benchmarks. Our pre-trained base model exhibits strong in-context learning capabilities and the instruction-tuned model demonstrates competitive performance among open-source LMMs with similar model sizes. In addition, we introduce a safety-tuned model with DPO, aiming to mitigate harmful behaviors such as hallucinations and improve safety. We open-source our models, curated large-scale datasets, and our fine-tuning codebase to facilitate further advancements in LMM research. Associated resources will be available on our project page above.

Video Snapshot Compressive Imaging (SCI) uses a low-speed 2D camera to capture high-speed scenes as snapshot compressed measurements, followed by a reconstruction algorithm to retrieve the high-speed video frames. The fast evolving mobile devices and existing high-performance video SCI reconstruction algorithms motivate us to develop mobile reconstruction methods for real-world applications. Yet, it is still challenging to deploy previous reconstruction algorithms on mobile devices due to the complex inference process, let alone real-time mobile reconstruction. To the best of our knowledge, there is no video SCI reconstruction model designed to run on the mobile devices. Towards this end, in this paper, we present an effective approach for video SCI reconstruction, dubbed MobileSCI, which can run at real-time speed on the mobile devices for the first time. Specifically, we first build a U-shaped 2D convolution-based architecture, which is much more efficient and mobile-friendly than previous state-of-the-art reconstruction methods. Besides, an efficient feature mixing block, based on the channel splitting and shuffling mechanisms, is introduced as a novel bottleneck block of our proposed MobileSCI to alleviate the computational burden. Finally, a customized knowledge distillation strategy is utilized to further improve the reconstruction quality. Extensive results on both simulated and real data show that our proposed MobileSCI can achieve superior reconstruction quality with high efficiency on the mobile devices. Particularly, we can reconstruct a 256 X 256 X 8 snapshot compressed measurement with real-time performance (about 35 FPS) on an iPhone 15. Code is available at https://github.com/mcao92/MobileSCI., Comment: 9 pages, Accepted by ACM MM 2024

While randomized trials may be the gold standard for evaluating the effectiveness of the treatment intervention, in some special circumstances, single-arm clinical trials utilizing external control may be considered. The causal treatment effect of interest for single-arm studies is usually the average treatment effect on the treated (ATT) rather than the average treatment effect (ATE). Although methods have been developed to estimate the ATT, the selection and use of these methods require a thorough comparison and in-depth understanding of the advantages and disadvantages of these methods. In this study, we conducted simulations under different identifiability assumptions to compare the performance metrics (e.g., bias, standard deviation (SD), mean squared error (MSE), type I error rate) for a variety of methods, including the regression model, propensity score matching, Mahalanobis distance matching, coarsened exact matching, inverse probability weighting, augmented inverse probability weighting (AIPW), AIPW with SuperLearner, and targeted maximum likelihood estimator (TMLE) with SuperLearner. Our simulation results demonstrate that the doubly robust methods in general have smaller biases than other methods. In terms of SD, nonmatching methods in general have smaller SDs than matching-based methods. The performance of MSE is a trade-off between the bias and SD, and no method consistently performs better in term of MSE. The identifiability assumptions are critical to the models' performance: violation of the positivity assumption can lead to a significant inflation of type I errors in some methods; violation of the unconfoundedness assumption can lead to a large bias for all methods... (Further details are available in the main body of the paper)., Comment: 24 pages, 13 figures

Large language model (LLM) agents have shown great potential in solving real-world software engineering (SWE) problems. The most advanced open-source SWE agent can resolve over 27% of real GitHub issues in SWE-Bench Lite. However, these sophisticated agent frameworks exhibit varying strengths, excelling in certain tasks while underperforming in others. To fully harness the diversity of these agents, we propose DEI (Diversity Empowered Intelligence), a framework that leverages their unique expertise. DEI functions as a meta-module atop existing SWE agent frameworks, managing agent collectives for enhanced problem-solving. Experimental results show that a DEI-guided committee of agents is able to surpass the best individual agent's performance by a large margin. For instance, a group of open-source SWE agents, with a maximum individual resolve rate of 27.3% on SWE-Bench Lite, can achieve a 34.3% resolve rate with DEI, making a 25% improvement and beating most closed-source solutions. Our best-performing group excels with a 55% resolve rate, securing the highest ranking on SWE-Bench Lite. Our findings contribute to the growing body of research on collaborative AI systems and their potential to solve complex software engineering challenges.

Infrared small target detection faces the inherent challenge of precisely localizing dim targets amidst complex background clutter. Traditional approaches struggle to balance detection precision and false alarm rates. To break this dilemma, we propose SeRankDet, a deep network that achieves high accuracy beyond the conventional hit-miss trade-off, by following the ``Pick of the Bunch'' principle. At its core lies our Selective Rank-Aware Attention (SeRank) module, employing a non-linear Top-K selection process that preserves the most salient responses, preventing target signal dilution while maintaining constant complexity. Furthermore, we replace the static concatenation typical in U-Net structures with our Large Selective Feature Fusion (LSFF) module, a dynamic fusion strategy that empowers SeRankDet with adaptive feature integration, enhancing its ability to discriminate true targets from false alarms. The network's discernment is further refined by our Dilated Difference Convolution (DDC) module, which merges differential convolution aimed at amplifying subtle target characteristics with dilated convolution to expand the receptive field, thereby substantially improving target-background separation. Despite its lightweight architecture, the proposed SeRankDet sets new benchmarks in state-of-the-art performance across multiple public datasets. The code is available at https://github.com/GrokCV/SeRankDet., Comment: IEEE TGRS 2024

We introduce WarpSci, a domain agnostic framework designed to overcome crucial system bottlenecks encountered in the application of reinforcement learning to intricate environments with vast datasets featuring high-dimensional observation or action spaces. Notably, our framework eliminates the need for data transfer between the CPU and GPU, enabling the concurrent execution of thousands of simulations on a single or multiple GPUs. This high data throughput architecture proves particularly advantageous for data-driven scientific research, where intricate environment models are commonly essential.

Video Snapshot Compressive Imaging (SCI) aims to use a low-speed 2D camera to capture high-speed scene as snapshot compressed measurements, followed by a reconstruction algorithm to reconstruct the high-speed video frames. State-of-the-art (SOTA) deep learning-based algorithms have achieved impressive performance, yet with heavy computational workload. Network quantization is a promising way to reduce computational cost. However, a direct low-bit quantization will bring large performance drop. To address this challenge, in this paper, we propose a simple low-bit quantization framework (dubbed Q-SCI) for the end-to-end deep learning-based video SCI reconstruction methods which usually consist of a feature extraction, feature enhancement, and video reconstruction module. Specifically, we first design a high-quality feature extraction module and a precise video reconstruction module to extract and propagate high-quality features in the low-bit quantized model. In addition, to alleviate the information distortion of the Transformer branch in the quantized feature enhancement module, we introduce a shift operation on the query and key distributions to further bridge the performance gap. Comprehensive experimental results manifest that our Q-SCI framework can achieve superior performance, e.g., 4-bit quantized EfficientSCI-S derived by our Q-SCI framework can theoretically accelerate the real-valued EfficientSCI-S by 7.8X with only 2.3% performance gap on the simulation testing datasets. Code is available at https://github.com/mcao92/QuantizedSCI., Comment: 18 pages, Accepted by ECCV 2024

In the vast landscape of internet information, recommender systems (RecSys) have become essential for guiding users through a sea of choices aligned with their preferences. These systems have applications in diverse domains, such as news feeds, game suggestions, and shopping recommendations. Personalization is a key technique in RecSys, where modern methods leverage representation learning to encode user/item interactions into embeddings, forming the foundation for personalized recommendations. However, integrating information from multiple sources to enhance recommendation performance remains challenging. This paper introduces a novel approach named PMTRec, the first personalized multi-task learning algorithm to obtain comprehensive user/item embeddings from various information sources. Addressing challenges specific to personalized RecSys, we develop modules to handle personalized task weights, diverse task orientations, and variations in gradient magnitudes across tasks. PMTRec dynamically adjusts task weights based on gradient norms for each user/item, employs a Task Focusing module to align gradient combinations with the main recommendation task, and uses a Gradient Magnitude Balancing module to ensure balanced training across tasks. Through extensive experiments on three real-world datasets with different scales, we demonstrate that PMTRec significantly outperforms existing multi-task learning methods, showcasing its effectiveness in achieving enhanced recommendation accuracy by leveraging multiple tasks simultaneously. Our contributions open new avenues for advancing personalized multi-task training in recommender systems., Comment: 11 pages

Infrared small target detection poses unique challenges due to the scarcity of intrinsic target features and the abundance of similar background distractors. We argue that background semantics play a pivotal role in distinguishing visually similar objects for this task. To address this, we introduce a new task -- clustered infrared small target detection, and present DenseSIRST, a novel benchmark dataset that provides per-pixel semantic annotations for background regions, enabling the transition from sparse to dense target detection. Leveraging this dataset, we propose the Background-Aware Feature Exchange Network (BAFE-Net), which transforms the detection paradigm from a single task focused on the foreground to a multi-task architecture that jointly performs target detection and background semantic segmentation. BAFE-Net introduces a cross-task feature hard-exchange mechanism to embed target and background semantics between the two tasks. Furthermore, we propose the Background-Aware Gaussian Copy-Paste (BAG-CP) method, which selectively pastes small targets into sky regions during training, avoiding the creation of false alarm targets in complex non-sky backgrounds. Extensive experiments validate the effectiveness of BAG-CP and BAFE-Net in improving target detection accuracy while reducing false alarms. The DenseSIRST dataset, code, and trained models are available at https://github.com/GrokCV/BAFE-Net.

Vision foundation models are renowned for their generalization ability due to massive training data. Nevertheless, they demand tremendous training resources, and the training data is often inaccessible, e.g., CLIP, DINOv2, posing great challenges to developing derivatives that could advance research in this field. In this work, we offer a very simple and general solution, named Proteus, to distill foundation models into smaller equivalents on ImageNet-1K without access to the original training data. Specifically, we remove the designs from conventional knowledge distillation settings that result in dataset bias and present three levels of training objectives, i.e., token, patch, and feature, to maximize the efficacy of knowledge transfer. In this manner, Proteus is trained at ImageNet-level costs with surprising ability, facilitating the accessibility of training foundation models for the broader research community. Leveraging DINOv2-g/14 as the teacher, Proteus-L/14 matches the performance of the Oracle method DINOv2-L/14 (142M training data) across 15 benchmarks and outperforms other vision foundation models including CLIP-L/14 (400M), OpenCLIP-L/14 (400M/2B) and SynCLR-L/14 (600M).

The advancement of function-calling agent models requires diverse, reliable, and high-quality datasets. This paper presents APIGen, an automated data generation pipeline designed to synthesize verifiable high-quality datasets for function-calling applications. We leverage APIGen and collect 3,673 executable APIs across 21 different categories to generate diverse function-calling datasets in a scalable and structured manner. Each data in our dataset is verified through three hierarchical stages: format checking, actual function executions, and semantic verification, ensuring its reliability and correctness. We demonstrate that models trained with our curated datasets, even with only 7B parameters, can achieve state-of-the-art performance on the Berkeley Function-Calling Benchmark, outperforming multiple GPT-4 models. Moreover, our 1B model achieves exceptional performance, surpassing GPT-3.5-Turbo and Claude-3 Haiku. We release a dataset containing 60,000 high-quality entries, aiming to advance the field of function-calling agent domains. The dataset is available on Huggingface: https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k and the project homepage: https://apigen-pipeline.github.io/

Neural networks (NNs) have demonstrated strong capabilities of representing high-dimensional, complex functional relations, and hence have been widely used to characterize complex constitutive relations for various types of materials, such as polycrystals, polymers, etc. However, to construct a reliable NN-based constitutive model, a considerable amount of data, i.e. stress-strain states along different loading paths is needed, which can be expensive to collect. To address such challenge, we develop a hybrid finite element method (FEM) - NN optimization framework to learn complex hyperelastic constitutive relations from full-field data. The key advantage of this framework is that it can make use of the non-uniform displacement field due to the geometric inhomogeneities for training NN-based constitutive models. Since such data can provide many different stress-strain states in a single test, it can greatly reduce the number of experiments needed for the training of NNs. Besides, we adopt a mechanics-informed neural network (MINN) as our architecture to ensure that our NN-based models satisfy all necessary physical constraints by construction, such as objectivity, material symmetry, polyconvexity, etc. Such architecture is also key to the convergence of our optimization framework. We then use both synthetic and experimental data to test the performance of our proposed framework on various isotropic hyperelastic materials. Results show that our optimization framework can be used to train NN-based constitutive models for hyperelastic materials with high accuracy and efficiency using data generated from simple tests, which can also be easily adapted to characterize complex constitutive models for a broader range of materials., Comment: 14 pages,7 figures

We study the inverse problem of Coded Aperture Snapshot Spectral Imaging (CASSI), which captures a spatial-spectral data cube using snapshot 2D measurements and uses algorithms to reconstruct 3D hyperspectral images (HSI). However, current methods based on Convolutional Neural Networks (CNNs) struggle to capture long-range dependencies and non-local similarities. The recently popular Transformer-based methods are poorly deployed on downstream tasks due to the high computational cost caused by self-attention. In this paper, we propose Coarse-Fine Spectral-Aware Deformable Convolution Network (CFSDCN), applying deformable convolutional networks (DCN) to this task for the first time. Considering the sparsity of HSI, we design a deformable convolution module that exploits its deformability to capture long-range dependencies and non-local similarities. In addition, we propose a new spectral information interaction module that considers both coarse-grained and fine-grained spectral similarities. Extensive experiments demonstrate that our CFSDCN significantly outperforms previous state-of-the-art (SOTA) methods on both simulated and real HSI datasets., Comment: 7 pages, 5 figures, Accepted by ICIP2024

The deployment of Large Language Models (LLMs) and Large Multimodal Models (LMMs) on mobile devices has gained significant attention due to the benefits of enhanced privacy, stability, and personalization. However, the hardware constraints of mobile devices necessitate the use of models with fewer parameters and model compression techniques like quantization. Currently, there is limited understanding of quantization's impact on various task performances, including LLM tasks, LMM tasks, and, critically, trust and safety. There is a lack of adequate tools for systematically testing these models on mobile devices. To address these gaps, we introduce MobileAIBench, a comprehensive benchmarking framework for evaluating mobile-optimized LLMs and LMMs. MobileAIBench assesses models across different sizes, quantization levels, and tasks, measuring latency and resource consumption on real devices. Our two-part open-source framework includes a library for running evaluations on desktops and an iOS app for on-device latency and hardware utilization measurements. Our thorough analysis aims to accelerate mobile AI research and deployment by providing insights into the performance and feasibility of deploying LLMs and LMMs on mobile platforms.

The study of the mechanism of exchange bias phenomena and the achievement of its efficient control are of great importance, as it promotes the revelation of unique exchange interactions and the development of exotic applications. However, it is challenging due to the elusive interface between magnetic phases. In this study, we report an unprecedented exchange bias phenomenon observed in ultrathin uncompensated antiferromagnetic MnBi$_2$Te$_4$. The magnitude and direction of the exchange field can be intentionally controlled by designing a magnetic field sweep protocol without a field cooling process. The combined experimental and theoretical simulation results indicate that the spin-flip process assisted by the ubiquitous defect-induced pinning domain sites with varying inner exchange interactions might give rise to the emergence and robustness of this peculiar exchange bias. The temperature and thickness dependence of the exchange bias phenomena are systematically investigated for further study and exploitation of its unique properties. This mechanism hold promise for highly tunable exchange bias in prevalent magnetic systems by engineering the properties of domain structures, and also offers promising avenues for the design of spintronic devices combing its topology based on MnBi$_2$Te$_4$., Comment: 8 pages, 4 figures

Current training pipelines in object recognition neglect Hue Jittering when doing data augmentation as it not only brings appearance changes that are detrimental to classification, but also the implementation is inefficient in practice. In this study, we investigate the effect of hue variance in the context of video understanding and find this variance to be beneficial since static appearances are less important in videos that contain motion information. Based on this observation, we propose a data augmentation method for video understanding, named Motion Coherent Augmentation (MCA), that introduces appearance variation in videos and implicitly encourages the model to prioritize motion patterns, rather than static appearances. Concretely, we propose an operation SwapMix to efficiently modify the appearance of video samples, and introduce Variation Alignment (VA) to resolve the distribution shift caused by SwapMix, enforcing the model to learn appearance invariant representations. Comprehensive empirical evaluation across various architectures and different datasets solidly validates the effectiveness and generalization ability of MCA, and the application of VA in other augmentation methods. Code is available at https://github.com/BeSpontaneous/MCA-pytorch., Comment: Accepted by ICLR2024

The interplay between non-trivial topology and strong electron interaction can generate a variety of exotic quantum matter. Here we theoretically propose that monolayer transition metal trihalides MoF$_3$ and W$X_3$ ($X$= Cl, Br, I) have isolated nearly flat band near the Fermi level with higher Chern number $\mathcal{C}=+3$ and $\mathcal{C}=-2$, respectively. The nontrivial topology of these flat Chern bands originates from the effective $sd^2$ hybridization of transition metal atom, which transform the apparent atomic $d$ orbitals on a hexagonal lattice into $(s, p_+, p_-)$ orbitals on a triangular lattice. Interestingly, the quantum geometry of flat Chern bands in these materials are comparable with those in moir\'e systems exhibiting fractional Chern insulator state. The Hofstadter butterfly of such flat Chern bands are further studied. These natural materials, if realized experimentally, could offer new platforms to explore correlated phenomena driven by flat Chern band with higher Chern number., Comment: 7 pages, 4 figures

The booming success of LLMs initiates rapid development in LLM agents. Though the foundation of an LLM agent is the generative model, it is critical to devise the optimal reasoning strategies and agent architectures. Accordingly, LLM agent research advances from the simple chain-of-thought prompting to more complex ReAct and Reflection reasoning strategy; agent architecture also evolves from single agent generation to multi-agent conversation, as well as multi-LLM multi-agent group chat. However, with the existing intricate frameworks and libraries, creating and evaluating new reasoning strategies and agent architectures has become a complex challenge, which hinders research investigation into LLM agents. Thus, we open-source a new AI agent library, AgentLite, which simplifies this process by offering a lightweight, user-friendly platform for innovating LLM agent reasoning, architectures, and applications with ease. AgentLite is a task-oriented framework designed to enhance the ability of agents to break down tasks and facilitate the development of multi-agent systems. Furthermore, we introduce multiple practical applications developed with AgentLite to demonstrate its convenience and flexibility. Get started now at: \url{https://github.com/SalesforceAIResearch/AgentLite}., Comment: preprint. Library is available at https://github.com/SalesforceAIResearch/AgentLite

Autonomous agents powered by large language models (LLMs) have garnered significant research attention. However, fully harnessing the potential of LLMs for agent-based tasks presents inherent challenges due to the heterogeneous nature of diverse data sources featuring multi-turn trajectories. In this paper, we introduce \textbf{AgentOhana} as a comprehensive solution to address these challenges. \textit{AgentOhana} aggregates agent trajectories from distinct environments, spanning a wide array of scenarios. It meticulously standardizes and unifies these trajectories into a consistent format, streamlining the creation of a generic data loader optimized for agent training. Leveraging the data unification, our training pipeline maintains equilibrium across different data sources and preserves independent randomness across devices during dataset partitioning and model training. Additionally, we present \textbf{xLAM-v0.1}, a large action model tailored for AI agents, which demonstrates exceptional performance across various benchmarks. Begin the exploration at \url{https://github.com/SalesforceAIResearch/xLAM}., Comment: Add GitHub repo link at \url{https://github.com/SalesforceAIResearch/xLAM} and HuggingFace model link at \url{https://huggingface.co/Salesforce/xLAM-v0.1-r}

Natural language serves as a common and straightforward control signal for humans to interact seamlessly with machines. Recognizing the importance of this interface, the machine learning community is investing considerable effort in generating data that is semantically coherent with textual instructions. While strides have been made in text-to-data generation spanning image editing, audio synthesis, video creation, and beyond, low-resource areas characterized by expensive annotations or complex data structures, such as molecules, motion dynamics, and time series, often lack textual labels. This deficiency impedes supervised learning, thereby constraining the application of advanced generative models for text-to-data tasks. In response to these challenges in the low-resource scenario, we propose Text2Data, a novel approach that utilizes unlabeled data to understand the underlying data distribution through an unsupervised diffusion model. Subsequently, it undergoes controllable finetuning via a novel constraint optimization-based learning objective that ensures controllability and effectively counteracts catastrophic forgetting. Comprehensive experiments demonstrate that Text2Data is able to achieve enhanced performance regarding controllability across various modalities, including molecules, motions and time series, when compared to existing baselines., Comment: We propose a method that can achieve text-to-data generation under low-resource situation

Causal discovery aims to recover information about an unobserved causal graph from the observable data it generates. Layerings are orderings of the variables which place causes before effects. In this paper, we provide ways to recover layerings of a graph by accessing the data via a conditional entropy oracle, when distributions are discrete. Our algorithms work by repeatedly removing sources or sinks from the graph. Under appropriate assumptions and conditioning, we can separate the sources or sinks from the remainder of the nodes by comparing their conditional entropy to the unconditional entropy of their noise. Our algorithms are provably correct and run in worst-case quadratic time. The main assumptions are faithfulness and injective noise, and either known noise entropies or weakly monotonically increasing noise entropies along directed paths. In addition, we require one of either a very mild extension of faithfulness, or strictly monotonically increasing noise entropies, or expanding noise injectivity to include an additional single argument in the structural functions.

High entropy alloys (HEAs) have attracted substantial interest in recent years. Thus far, most investigations have focused on their applications as structural materials rather than functional materials. In this paper, we show that FeMnNiAlCr HEAs can potentially be applied as both a structural and functional material for high-efficiency concentrated solar thermal power (CSP) systems working at >700 degrees C. The HEA itself would be used in high-temperature tubing to carry working fluids, while its surface oxide would act as a high-efficiency solar thermal absorber. These HEAs have demonstrated yield strengths 2-3x greater than that of stainless steel at 700 degrees C and a creep lifetime >800 h at 700 degrees C under a typical CSP tubing mechanical load of 35 MPa. Their Mn-rich surface oxides maintain a high optical-to-thermal conversion efficiency of ~87% under 1000x solar concentration for 20 simulated day-night thermal cycles between 750 degrees C and environmental temperature. These HEAs have also sustained immersion in unpurified bromide molten salts for 14 days at 750{\deg}C with <2% weight loss, in contrast to 70% weight loss from a 316 stainless steel reference. The simultaneous achievement of promising mechanical, optical, and thermochemical properties in this FeMnNiAlCr system opens the door to new applications of HEAs in solar energy harvesting.

Bulk-boundary correspondences (BBCs) remain the central topic in modern condensed matter physics, and are gaining increasing interests with the recent discovery of non-Hermitian skin effects. However, there still exist profound features of BBCs that are beyond the existing framework. Here, we report the unexpected behavior of BBC when the Hamiltonian contains term of the form $d_0(k) I$, which serves as a momentum dependent energy shift. For Hermitian cases, momentum dependent energy shift can force the system to be semimetal, where topological phase transitions can take place with the upper and the lower bands keeping untouched. The proper modified BBC should be reconstructed from the perspective of the direct band gap. In non-Hermitian cases, skin effects are found to be capable of coexisting with the preserved BBC, of which the process can be greatly facilitated by the complex $d_0(k)I$. Remarkably, such results can be led a further step and contrary to the intuitive consideration, the modified BBC in Hermitian systems can be restored to be conventional by including extra non-Hermiticity. The physical origin for these phenomena lies in that $d_0(k)I$ can drastically change the point gap topology. Finally, the corresponding experimental simulations are proposed via the platforms of electric circuits.

Prognostics and health management (PHM) is essential for industrial operation and maintenance, focusing on predicting, diagnosing, and managing the health status of industrial systems. The emergence of the ChatGPT-Like large-scale language model (LLM) has begun to lead a new round of innovation in the AI field. It has extensively promoted the level of intelligence in various fields. Therefore, it is also expected further to change the application paradigm in industrial PHM and promote PHM to become intelligent. Although ChatGPT-Like LLMs have rich knowledge reserves and powerful language understanding and generation capabilities, they lack domain-specific expertise, significantly limiting their practicability in PHM applications. To this end, this study explores the ChatGPT-Like LLM empowered by the local knowledge base (LKB) in industrial PHM to solve the above limitations. In addition, we introduce the method and steps of combining the LKB with LLMs, including LKB preparation, LKB vectorization, prompt engineering, etc. Experimental analysis of real cases shows that combining the LKB with ChatGPT-Like LLM can significantly improve its performance and make ChatGPT-Like LLMs more accurate, relevant, and able to provide more insightful information. This can promote the development of ChatGPT-Like LLMs in industrial PHM and promote their efficiency and quality.

In recent decades, Industrial Fault Diagnosis (IFD) has emerged as a crucial discipline concerned with detecting and gathering vital information about industrial equipment's health condition, thereby facilitating the identification of failure types and severities. The pursuit of precise and effective fault recognition has garnered substantial attention, culminating in a focus on automating equipment monitoring to preclude safety accidents and reduce reliance on human labor. The advent of artificial neural networks (ANNs) has been instrumental in augmenting intelligent IFD algorithms, particularly in the context of big data. Despite these advancements, ANNs, being a simplified biomimetic neural network model, exhibit inherent limitations such as resource and data dependencies and restricted cognitive capabilities. To address these limitations, the third-generation Spiking Neural Network (SNN), founded on principles of Brain-inspired computing, has surfaced as a promising alternative. The SNN, characterized by its biological neuron dynamics and spiking information encoding, demonstrates exceptional potential in representing spatiotemporal features. Consequently, developing SNN-based IFD models has gained momentum, displaying encouraging performance. Nevertheless, this field lacks systematic surveys to illustrate the current situation, challenges, and future directions. Therefore, this paper systematically reviews the theoretical progress of SNN-based models to answer the question of what SNN is. Subsequently, it reviews and analyzes existing SNN-based IFD models to explain why SNN needs to be used and how to use it. More importantly, this paper systematically answers the challenges, solutions, and opportunities of SNN in IFD., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

This paper presents an alternative method to prove the heat kernel asymptotics for the Kodaira Laplacian with respect to the high power of a holomorphic Hermitian line bundle $(L,h^L)$ over a possibly non-compact Hermitian manifold $(M,\omega)$. The approach used in this work employs a scaling technique and is applicable to $M$ regardless of its compactness.

Code LLMs have emerged as a specialized research field, with remarkable studies dedicated to enhancing model's coding capabilities through fine-tuning on pre-trained models. Previous fine-tuning approaches were typically tailored to specific downstream tasks or scenarios, which meant separate fine-tuning for each task, requiring extensive training resources and posing challenges in terms of deployment and maintenance. Furthermore, these approaches failed to leverage the inherent interconnectedness among different code-related tasks. To overcome these limitations, we present a multi-task fine-tuning framework, MFTcoder, that enables simultaneous and parallel fine-tuning on multiple tasks. By incorporating various loss functions, we effectively address common challenges in multi-task learning, such as data imbalance, varying difficulty levels, and inconsistent convergence speeds. Extensive experiments have conclusively demonstrated that our multi-task fine-tuning approach outperforms both individual fine-tuning on single tasks and fine-tuning on a mixed ensemble of tasks. Moreover, MFTcoder offers efficient training capabilities, including efficient data tokenization modes and PEFT fine-tuning, resulting in significantly improved speed compared to traditional fine-tuning methods. MFTcoder seamlessly integrates with several mainstream open-source LLMs, such as CodeLLama and Qwen. Leveraging the CodeLLama foundation, our MFTcoder fine-tuned model, \textsc{CodeFuse-CodeLLama-34B}, achieves an impressive pass@1 score of 74.4\% on the HumaneEval benchmark, surpassing GPT-4 performance (67\%, zero-shot). MFTCoder is open-sourced at \url{https://github.com/codefuse-ai/MFTCOder}

While large language models based on the transformer architecture have demonstrated remarkable in-context learning (ICL) capabilities, understandings of such capabilities are still in an early stage, where existing theory and mechanistic understanding focus mostly on simple scenarios such as learning simple function classes. This paper takes initial steps on understanding ICL in more complex scenarios, by studying learning with representations. Concretely, we construct synthetic in-context learning problems with a compositional structure, where the label depends on the input through a possibly complex but fixed representation function, composed with a linear function that differs in each instance. By construction, the optimal ICL algorithm first transforms the inputs by the representation function, and then performs linear ICL on top of the transformed dataset. We show theoretically the existence of transformers that approximately implement such algorithms with mild depth and size. Empirically, we find trained transformers consistently achieve near-optimal ICL performance in this setting, and exhibit the desired dissection where lower layers transforms the dataset and upper layers perform linear ICL. Through extensive probing and a new pasting experiment, we further reveal several mechanisms within the trained transformers, such as concrete copying behaviors on both the inputs and the representations, linear ICL capability of the upper layers alone, and a post-ICL representation selection mechanism in a harder mixture setting. These observed mechanisms align well with our theory and may shed light on how transformers perform ICL in more realistic scenarios.

Code Large Language Models (Code LLMs) have gained significant attention in the industry due to their wide applications in the full lifecycle of software engineering. However, the effectiveness of existing models in understanding non-English inputs for multi-lingual code-related tasks is still far from well studied. This paper introduces CodeFuse-13B, an open-sourced pre-trained code LLM. It is specifically designed for code-related tasks with both English and Chinese prompts and supports over 40 programming languages. CodeFuse achieves its effectiveness by utilizing a high quality pre-training dataset that is carefully filtered by program analyzers and optimized during the training process. Extensive experiments are conducted using real-world usage scenarios, the industry-standard benchmark HumanEval-x, and the specially designed CodeFuseEval for Chinese prompts. To assess the effectiveness of CodeFuse, we actively collected valuable human feedback from the AntGroup's software development process where CodeFuse has been successfully deployed. The results demonstrate that CodeFuse-13B achieves a HumanEval pass@1 score of 37.10%, positioning it as one of the top multi-lingual code LLMs with similar parameter sizes. In practical scenarios, such as code generation, code translation, code comments, and testcase generation, CodeFuse performs better than other models when confronted with Chinese prompts., Comment: Accepted by ICSE-SEIP 2024

Latent graph inference (LGI) aims to jointly learn the underlying graph structure and node representations from data features. However, existing LGI methods commonly suffer from the issue of supervision starvation, where massive edge weights are learned without semantic supervision and do not contribute to the training loss. Consequently, these supervision-starved weights, which may determine the predictions of testing samples, cannot be semantically optimal, resulting in poor generalization. In this paper, we observe that this issue is actually caused by the graph sparsification operation, which severely destroys the important connections established between pivotal nodes and labeled ones. To address this, we propose to restore the corrupted affinities and replenish the missed supervision for better LGI. The key challenge then lies in identifying the critical nodes and recovering the corrupted affinities. We begin by defining the pivotal nodes as $k$-hop starved nodes, which can be identified based on a given adjacency matrix. Considering the high computational burden, we further present a more efficient alternative inspired by CUR matrix decomposition. Subsequently, we eliminate the starved nodes by reconstructing the destroyed connections. Extensive experiments on representative benchmarks demonstrate that reducing the starved nodes consistently improves the performance of state-of-the-art LGI methods, especially under extremely limited supervision (6.12% improvement on Pubmed with a labeling rate of only 0.3%).

A five-level M-type scheme in atomic ensembles is proposed to generate a one-dimensional bipartite superradiance lattice in momentum space. By taking advantage of this tunable atomic system, we show that various types of Su-Schrieffer-Heeger (SSH) model, including the standard SSH and extended SSH model, can be realized. Interestingly, it is shown that through changing the Rabi frequencies and detunings in our proposed scheme, there is a topological phase transition from topological trivial regime with winding number being 0 to topological non-trivial regime with winding number being 2. Furthermore, a robust flat band with higher winding number (being 2) can be achieved in the above topological non-trivial regime, where the superradiance spectra can be utilized as a tool for experimental detection. Our proposal would provide a promising approach to explore new physics, such as fractional topological phases, in the flat bands with higher topological number., Comment: 5 pages, 3 figures

Intrinsic magnetic topological insulators offers an ideal platform to explore exotic topological phenomena, such as axion electrodynamics, quantum anomalous Hall (QAH) effect and Majorana edge modes. However, these emerging new physical effects have rarely been experimentally observed due to the limited choice of suitable materials. Here, we predict the van der Waals layered V$_2$WS$_4$ and its related materials show intralayer ferromagnetic and interlayer antiferromagnetic exchange interactions. We find extremely rich magnetic topological states in V$_2$WS$_4$, including an antiferromagnetic topological insulator, the axion state with the long-sought quantized topological magnetoelectric effect, three-dimensional QAH state, as well as a collection of QAH insulators and intrinsic axion insulators in odd- and even-layer films, respectively. Remarkably, the N\'eel temperature of V$_2$WS$_4$ is predicted to be much higher than that of MnBi$_2$Te$_4$. These interesting predictions, if realized experimentally, could greatly promote the topological quantum physics research and application., Comment: 7 pages, 4 figures

The dynamics of biomolecules are crucial for our understanding of their functioning in living systems. However, current 3D imaging techniques, such as cryogenic electron microscopy (cryo-EM), require freezing the sample, which limits the observation of their conformational changes in real time. The innovative liquid-phase electron microscopy (liquid-phase EM) technique allows molecules to be placed in the native liquid environment, providing a unique opportunity to observe their dynamics. In this paper, we propose TEMPOR, a Temporal Electron MicroscoPy Object Reconstruction algorithm for liquid-phase EM that leverages an implicit neural representation (INR) and a dynamical variational auto-encoder (DVAE) to recover time series of molecular structures. We demonstrate its advantages in recovering different motion dynamics from two simulated datasets, 7bcq and Cas9. To our knowledge, our work is the first attempt to directly recover 3D structures of a temporally-varying particle from liquid-phase EM movies. It provides a promising new approach for studying molecules' 3D dynamics in structural biology.

End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by leveraging sophisticated natural language understanding and natural language generation capabilities of pre-trained models. This work enables the TOD systems with more flexibility through a simple cache. The cache provides the flexibility to dynamically update the TOD systems and handle both existing and unseen dialogue scenarios. Towards this end, we first fine-tune a retrieval module to effectively retrieve the most relevant information entries from the cache. We then train end-to-end TOD models that can refer to and ground on both dialogue history and retrieved information during TOD generation. The cache is straightforward to construct, and the backbone models of TOD systems are compatible with existing pre-trained generative models. Extensive experiments demonstrate the superior performance of our framework, with a notable improvement in non-empty joint goal accuracy by 6.7% compared to strong baselines., Comment: Accepted by SIGDIAL 2023 as a long paper

The massive successes of large language models (LLMs) encourage the emerging exploration of LLM-augmented Autonomous Agents (LAAs). An LAA is able to generate actions with its core LLM and interact with environments, which facilitates the ability to resolve complex tasks by conditioning on past interactions such as observations and actions. Since the investigation of LAA is still very recent, limited explorations are available. Therefore, we provide a comprehensive comparison of LAA in terms of both agent architectures and LLM backbones. Additionally, we propose a new strategy to orchestrate multiple LAAs such that each labor LAA focuses on one type of action, \textit{i.e.} BOLAA, where a controller manages the communication among multiple agents. We conduct simulations on both decision-making and multi-step reasoning environments, which comprehensively justify the capacity of LAAs. Our performance results provide quantitative suggestions for designing LAA architectures and the optimal choice of LLMs, as well as the compatibility of both. We release our implementation code of LAAs to the public at \url{https://github.com/salesforce/BOLAA}., Comment: Preprint

The pursuit of understanding parity anomaly in condensed matter systems has led to significant advancements in both theoretical and experimental research in recent years. In this study, we explore the parity anomaly of massless Dirac fermions in a semimagnetic topological insulator (TI) thin film subjected to a finite magnetic field. Our findings reveal an anomalous half-quantized Hall conductance arising from the occupied electronic states far below the Fermi level, which is directly associated with the parity anomaly. This observation demonstrates a crossover from one-half quantized Hall conductance in a metallic phase at zero field to one or zero quantized Hall conductance in the insulating phase at a strong field in the presence of disorders, serving as a key indicator for confirming parity anomaly. Our work provides valuable insights into the intricate relationship between band topology in condensed matter systems and quantum anomaly in quantum field theory., Comment: 7 pages, 3 figures

Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than merely responding to queries from human users. Most existing language agents, however, are not optimized using environment-specific rewards. Although some agents enable iterative refinement through verbal feedback, they do not reason and plan in ways that are compatible with gradient-based learning from rewards. This paper introduces a principled framework for reinforcing large language agents by learning a retrospective model, which automatically tunes the language agent prompts from environment feedback through policy gradient. Specifically, our proposed agent architecture learns from rewards across multiple environments and tasks, for fine-tuning a pre-trained language model which refines the language agent prompt by summarizing the root cause of prior failed attempts and proposing action plans. Experimental results on various tasks demonstrate that the language agents improve over time and that our approach considerably outperforms baselines that do not properly leverage gradients from the environment. This demonstrates that using policy gradient optimization to improve language agents, for which we believe our work is one of the first, seems promising and can be applied to optimize other models in the agent architecture to enhance agent performances over time.

Despite advancements in conversational AI, language models encounter challenges to handle diverse conversational tasks, and existing dialogue dataset collections often lack diversity and comprehensiveness. To tackle these issues, we introduce DialogStudio: the largest and most diverse collection of dialogue datasets, unified under a consistent format while preserving their original information. Our collection encompasses data from open-domain dialogues, task-oriented dialogues, natural language understanding, conversational recommendation, dialogue summarization, and knowledge-grounded dialogues, making it an incredibly rich and diverse resource for dialogue research and model training. To further enhance the utility of DialogStudio, we identify the licenses for each dataset, design external knowledge and domain-aware prompts for selected dialogues to facilitate instruction-aware fine-tuning. Furthermore, we develop conversational AI models using the dataset collection, and our experiments in both zero-shot and few-shot learning scenarios demonstrate the superiority of DialogStudio. To improve transparency and support dataset and task-based research, as well as language model pre-training, all datasets, licenses, codes, and models associated with DialogStudio are made publicly accessible\footnote{\url{https://github.com/salesforce/DialogStudio}}., Comment: 17 pages, accepted by EACL 2024 Findings as a long paper. All datasets, licenses, codes, and models are available at at https://github.com/salesforce/DialogStudio

In this paper, we propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX. Existing AutoGPT-style techniques have inherent limitations, such as a heavy reliance on precise descriptions for decision-making, and the lack of a systematic approach to leverage try-and-fail procedures akin to traditional Reinforcement Learning (RL). REX introduces an additional layer of rewards and integrates concepts similar to Upper Confidence Bound (UCB) scores, leading to more robust and efficient AI agent performance. This approach has the advantage of enabling the utilization of offline behaviors from logs and allowing seamless integration with existing foundation models while it does not require any model fine-tuning. Through comparative analysis with existing methods such as Chain-of-Thoughts(CoT) and Reasoning viA Planning(RAP), REX-based methods demonstrate comparable performance and, in certain cases, even surpass the results achieved by these existing techniques. Notably, REX-based methods exhibit remarkable reductions in execution time, enhancing their practical applicability across a diverse set of scenarios.

The anomalous Hall effect has considerable impact on the progress of condensed matter physics and occurs in systems with time-reversal symmetry breaking. Here we theoretically investigate the anomalous Hall effect in nonmagnetic transition-metal pentatelluride $\mathrm{ZrTe_{5}}$ and $\mathrm{HfTe}_{5}$. In the presence of Zeeman splitting and Dirac mass, there is an intrinsic anomalous Hall conductivity induced by the Berry curvature in the semiclassical treatment. In a finite magnetic field, the anomalous Hall conductivity rapidly decays to zero for constant spin-splitting and vanishes for the magnetic-field-dependent Zeeman energy. A semiclassical formula is derived to depict the magnetic field dependence of the Hall conductivity, which is beneficial for experimental data analysis. Lastly, when the chemical potential is fixed in the magnetic field, a Hall conductivity plateau arises, which may account for the observed anomalous Hall effect in experiments., Comment: 11 pages, 6 figures, reference information is updated

We propose a general theory of anisotropic band flattening in moir\'e systems at the $\Gamma$ valley. For a two-dimensional semiconductor with a rectangular unit cell of $C_{2z}$ or mirror symmetries, we find that a larger effective mass anisotropy $\eta=m_y/m_x$ of the valence or conduction bands in the monolayer will have a stronger tendency to be further enhanced in its twisted bilayer. This gives rise to strong anisotropic band flattening and correlated physics in one dimension effectively. We predict twisted bilayer black phosphorus (tBBP) has giant anisotropic flattened moir\'e bands ($\eta\sim10^4$) from ab initio calculations and continuum model, where the low energy physics is described by the weakly coupled array of one-dimensional wires. We further calculate the phase diagram based on the sliding Luttinger liquid by including the screened Coulomb interactions in tBBP, and find a large parameter space may host the non-Fermi liquid phase. We thus establish tBBP as a promising and experimentally accessible platform for exploring correlated physics in low dimensions., Comment: 5 pages, 4 figures

This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case. Motivated by real-world settings such as loading in game playing, we propose an enhanced feedback model called ``multiple observations in hindsight'', where after each episode of interaction with the POMDP, the learner may collect multiple additional observations emitted from the encountered latent states, but may not observe the latent states themselves. We show that sample-efficient learning under this feedback model is possible for two new subclasses of POMDPs: \emph{multi-observation revealing POMDPs} and \emph{distinguishable POMDPs}. Both subclasses generalize and substantially relax \emph{revealing POMDPs} -- a widely studied subclass for which sample-efficient learning is possible under standard trajectory feedback. Notably, distinguishable POMDPs only require the emission distributions from different latent states to be \emph{different} instead of \emph{linearly independent} as required in revealing POMDPs.

Topological materials with unconventional electronic properties have been investigated intensively for both fundamental and practical interests. Thousands of topological materials have been identified by symmetry-based analysis and ab initio calculations. However, the predicted magnetic topological insulators with genuine full band gaps are rare. Here we employ this database and supervisedly train neural networks to develop a heuristic chemical rule for electronic topology diagnosis. The learned rule is interpretable and diagnoses with a high accuracy whether a material is topological using only its chemical formula and Hubbard $U$ parameter. We next evaluate the model performance in several different regimes of materials. Finally, we integrate machine-learned rule with ab initio calculations to high-throughput screen for magnetic topological insulators in 2D material database. We discover 6 new classes (15 materials) of Chern insulators, among which 4 classes (7 materials) have full band gaps and may motivate for experimental observation. We anticipate the machine-learned rule here can be used as a guiding principle for inverse design and discovery of new topological materials., Comment: 7 pages, 4 figures

Antiferromagnets exhibiting giant anomalous Hall effect (AHE) and anomalous Nernst effect (ANE) have recently aroused broad interest, not only for their potential applications in future electronic devices, but also because of the rich physics arising from the Berry curvature near the Fermi level. $\rm{Co_{1/3}NbS_2}$, by intercalating $\rm{Co^{2+}}$ ions between $\rm{NbS_2}$ layers, is a quasi-two-dimensional layered antiferromagnet with a chiral lattice. A large AHE has been observed in $\rm{Co_{1/3}NbS_2}$, but its origin is under debate. In this letter, we report the large AHE and ANE in exfoliated $\rm{Co_{1/3}NbS_2}$ flakes. By analyzing the thermoelectric data via the Mott relation, we determined that the observed large AHE and ANE primarily result from the intrinsic Berry curvature. We also observed the magnetic domains in $\rm{Co_{1/3}NbS_2}$ by reflective magnetic circular dichroism measurements. Combined with electrical transport measurements, we confirmed that the magnetic reversal in $\rm{Co_{1/3}NbS_2}$ is determined by domain wall motion, and the critical field ($H_c$) exhibits a memory effect of consecutive magnetic sweeps. Our work provides insight into the topological properties of $\rm{Co_{1/3}NbS_2}$ and paves the way to studying the spin configuration and magnetic domain dynamics in this fascinating antiferromagnet., Comment: 8 pages, 4 figures

Neural sequence models based on the transformer architecture have demonstrated remarkable \emph{in-context learning} (ICL) abilities, where they can perform new tasks when prompted with training and test examples, without any parameter update to the model. This work first provides a comprehensive statistical theory for transformers to perform ICL. Concretely, we show that transformers can implement a broad class of standard machine learning algorithms in context, such as least squares, ridge regression, Lasso, learning generalized linear models, and gradient descent on two-layer neural networks, with near-optimal predictive power on various in-context data distributions. Using an efficient implementation of in-context gradient descent as the underlying mechanism, our transformer constructions admit mild size bounds, and can be learned with polynomially many pretraining sequences. Building on these ``base'' ICL algorithms, intriguingly, we show that transformers can implement more complex ICL procedures involving \emph{in-context algorithm selection}, akin to what a statistician can do in real life -- A \emph{single} transformer can adaptively select different base ICL algorithms -- or even perform qualitatively different tasks -- on different input sequences, without any explicit prompting of the right algorithm or task. We both establish this in theory by explicit constructions, and also observe this phenomenon experimentally. In theory, we construct two general mechanisms for algorithm selection with concrete examples: pre-ICL testing, and post-ICL validation. As an example, we use the post-ICL validation mechanism to construct a transformer that can perform nearly Bayes-optimal ICL on a challenging task -- noisy linear models with mixed noise levels. Experimentally, we demonstrate the strong in-context algorithm selection capabilities of standard transformer architectures., Comment: V2 releases code