Search

Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time, optimizing reasoning capabilities during training remains challenging. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution and optimizes it via variational approaches. LaTRO enables LLMs to concurrently improve both their reasoning process and ability to evaluate reasoning quality, without requiring external feedback or reward models. We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures. On GSM8K, LaTRO improves zero-shot accuracy by an average of 12.5% over base models and 9.6% over supervised fine-tuning across Phi-3.5-mini, Mistral-7B, and Llama-3.1-8B. Our findings suggest that pre-trained LLMs possess latent reasoning capabilities that can be unlocked and enhanced through our proposed optimization approach in a self-improvement manner. The code of LaTRO is available at \url{https://github.com/SalesforceAIResearch/LaTRO}.

Customer Relationship Management (CRM) systems are vital for modern enterprises, providing a foundation for managing customer interactions and data. Integrating AI agents into CRM systems can automate routine processes and enhance personalized service. However, deploying and evaluating these agents is challenging due to the lack of realistic benchmarks that reflect the complexity of real-world CRM tasks. To address this issue, we introduce CRMArena, a novel benchmark designed to evaluate AI agents on realistic tasks grounded in professional work environments. Following guidance from CRM experts and industry best practices, we designed CRMArena with nine customer service tasks distributed across three personas: service agent, analyst, and manager. The benchmark includes 16 commonly used industrial objects (e.g., account, order, knowledge article, case) with high interconnectivity, along with latent variables (e.g., complaint habits, policy violations) to simulate realistic data distributions. Experimental results reveal that state-of-the-art LLM agents succeed in less than 40% of the tasks with ReAct prompting, and less than 55% even with function-calling abilities. Our findings highlight the need for enhanced agent capabilities in function-calling and rule-following to be deployed in real-world work environments. CRMArena is an open challenge to the community: systems that can reliably complete tasks showcase direct business value in a popular work environment.

After entering the era of big data, more and more companies build services with machine learning techniques. However, it is costly for companies to collect data and extract helpful handcraft features on their own. Although it is a way to combine with other companies' data for boosting the model's performance, this approach may be prohibited by laws. In other words, finding the balance between sharing data with others and keeping data from privacy leakage is a crucial topic worthy of close attention. This paper focuses on distributed data and conducts secure model training tasks on a vertical federated learning scheme. Here, secure implies that the whole process is executed in the encrypted domain. Therefore, the privacy concern is released., Comment: accepted by the 20th International Conference on Security & Management (SAM 2021)

Face verification is a well-known image analysis application and is widely used to recognize individuals in contemporary society. However, most real-world recognition systems ignore the importance of protecting the identity-sensitive facial images that are used for verification. To address this problem, we investigate how to implement a secure face verification system that protects the facial images from being imitated. In our work, we use the DeepID2 convolutional neural network to extract the features of a facial image and an EM algorithm to solve the facial verification problem. To maintain the privacy of facial images, we apply homomorphic encryption schemes to encrypt the facial data and compute the EM algorithm in the ciphertext domain. We develop three face verification systems for surveillance (or entrance) control of a local community based on three levels of privacy concerns. The associated timing performances are presented to demonstrate their feasibility for practical implementation., Comment: accepted by International Conference on Digital Image and Signal Processing (DISP) 2019

We introduce the Principled Reasoning and Acting (PRAct) framework, a novel method for learning and enforcing action principles from trajectory data. Central to our approach is the use of text gradients from a reflection and optimization engine to derive these action principles. To adapt action principles to specific task requirements, we propose a new optimization framework, Reflective Principle Optimization (RPO). After execution, RPO employs a reflector to critique current action principles and an optimizer to update them accordingly. We develop the RPO framework under two scenarios: Reward-RPO, which uses environmental rewards for reflection, and Self-RPO, which conducts self-reflection without external rewards. Additionally, two RPO methods, RPO-Traj and RPO-Batch, is introduced to adapt to different settings. Experimental results across four environments demonstrate that the PRAct agent, leveraging the RPO framework, effectively learns and applies action principles to enhance performance., Comment: Accepted to SIG CoNLL 2024

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: ECCV'24 CADL Workshop. Code: https://github.com/MingSun-Tse/LightAvatar-TensorFlow. V2: Corrected speed benchmark with GaussianAvatar

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 dynamic 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/

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