Search

We introduce \textit{ImmersePro}, an innovative framework specifically designed to transform single-view videos into stereo videos. This framework utilizes a novel dual-branch architecture comprising a disparity branch and a context branch on video data by leveraging spatial-temporal attention mechanisms. \textit{ImmersePro} employs implicit disparity guidance, enabling the generation of stereo pairs from video sequences without the need for explicit disparity maps, thus reducing potential errors associated with disparity estimation models. In addition to the technical advancements, we introduce the YouTube-SBS dataset, a comprehensive collection of 423 stereo videos sourced from YouTube. This dataset is unprecedented in its scale, featuring over 7 million stereo pairs, and is designed to facilitate training and benchmarking of stereo video generation models. Our experiments demonstrate the effectiveness of \textit{ImmersePro} in producing high-quality stereo videos, offering significant improvements over existing methods. Compared to the best competitor stereo-from-mono we quantitatively improve the results by 11.76\% (L1), 6.39\% (SSIM), and 5.10\% (PSNR).

Vision Language Place Recognition (VLVPR) enhances robot localization performance by incorporating natural language descriptions from images. By utilizing language information, VLVPR directs robot place matching, overcoming the constraint of solely depending on vision. The essence of multimodal fusion lies in mining the complementary information between different modalities. However, general fusion methods rely on traditional neural architectures and are not well equipped to capture the dynamics of cross modal interactions, especially in the presence of complex intra modal and inter modal correlations. To this end, this paper proposes a novel coarse to fine and end to end connected cross modal place recognition framework, called MambaPlace. In the coarse localization stage, the text description and 3D point cloud are encoded by the pretrained T5 and instance encoder, respectively. They are then processed using Text Attention Mamba (TAM) and Point Clouds Mamba (PCM) for data enhancement and alignment. In the subsequent fine localization stage, the features of the text description and 3D point cloud are cross modally fused and further enhanced through cascaded Cross Attention Mamba (CCAM). Finally, we predict the positional offset from the fused text point cloud features, achieving the most accurate localization. Extensive experiments show that MambaPlace achieves improved localization accuracy on the KITTI360Pose dataset compared to the state of the art methods., Comment: 8 pages

Accurately measuring protein-RNA binding affinity is crucial in many biological processes and drug design. Previous computational methods for protein-RNA binding affinity prediction rely on either sequence or structure features, unable to capture the binding mechanisms comprehensively. The recent emerging pre-trained language models trained on massive unsupervised sequences of protein and RNA have shown strong representation ability for various in-domain downstream tasks, including binding site prediction. However, applying different-domain language models collaboratively for complex-level tasks remains unexplored. In this paper, we propose CoPRA to bridge pre-trained language models from different biological domains via Complex structure for Protein-RNA binding Affinity prediction. We demonstrate for the first time that cross-biological modal language models can collaborate to improve binding affinity prediction. We propose a Co-Former to combine the cross-modal sequence and structure information and a bi-scope pre-training strategy for improving Co-Former's interaction understanding. Meanwhile, we build the largest protein-RNA binding affinity dataset PRA310 for performance evaluation. We also test our model on a public dataset for mutation effect prediction. CoPRA reaches state-of-the-art performance on all the datasets. We provide extensive analyses and verify that CoPRA can (1) accurately predict the protein-RNA binding affinity; (2) understand the binding affinity change caused by mutations; and (3) benefit from scaling data and model size.

Empowering LLMs with the ability to utilize useful information from a long context is crucial for many downstream applications. However, achieving long context lengths with the conventional transformer architecture requires substantial training and inference resources. In this paper, we present FocusLLM, a framework designed to extend the context length of any decoder-only LLM, enabling the model to focus on relevant information from very long sequences. FocusLLM processes long text inputs by dividing them into chunks based on the model's original context length to alleviate the issue of attention distraction. Then, it appends the local context to each chunk as a prompt to extract essential information from each chunk based on a novel parallel decoding mechanism, and ultimately integrates the extracted information into the local context. FocusLLM stands out for great training efficiency and versatility: trained with an 8K input length with much less training cost than previous methods, FocusLLM exhibits superior performance across downstream long-context tasks and maintains strong language modeling ability when handling extensive long texts, even up to 400K tokens. Our code is available at https://github.com/leezythu/FocusLLM.

Shannon's perfect-secrecy theorem states that a perfect encryption system that yields zero information to the adversary must be a one-time pad (OTP) with the keys randomly generated and never reused. However, recently discovered exotic properties of quantum entanglement have motivated us to reconsider Shannon's theorem in the quantum regime. In this work we design a quantum encryption method that overcomes Shannon's theorem to achieve perfect secrecy with reusable keys. The mechanism used is fundamentally quantum, demonstrating subtle but critical differences in how information is processed in quantum versus classical systems., Comment: This revision added a worked example and a quantum circuit figure

In the design of a metasurface-assisted system for indoor environments, it is essential to take into account not only the performance gains and coverage extension provided by the metasurface but also the operating costs brought by its reconfigurability, such as powering and cabling. These costs can present challenges, particularly in indoor dense spaces (IDSs). A self-sustainable metasurface (SSM), which retains reconfigurability unlike a static metasurface (SMS), achieves a lower operating cost than a reconfigurable intelligent surface (RIS) by being self-sustainable through power harvesting. In this paper, in order to find a better trade-off between metasurface gain, coverage, and operating cost, the design and performance of an SSM-assisted indoor mmWave communication system are investigated. We first simplify the design of the SSM-assisted system by considering the use of SSMs in a preset-based manner and the formation of coverage groups by associating SSMs with the closest user equipments (UEs). We propose a two-stage iterative algorithm to maximize the minimum data rate in the system by jointly deciding the association between the UEs and the SSMs, the phase-shifts of the SSMs, and allocating time resources for each UE. The non-convexities that exist in the proposed optimization problem are tackled using the feasible point pursuit successive convex approximation method and the concave-convex procedure. To understand the best scenario for using SSM, the resulting performance is compared with that achieved with RIS and SMS. Our numerical results indicate that SSMs are best utilized in a small environment where self-sustainability is easier to achieve when the budget for operating costs is tight., Comment: 13 Pages, 16 Figures, submitted to IEEE Transaction on Wireless Communication, under review

Quantum dynamics simulations (QDSs) are one of the most highly anticipated applications of quantum computing. Quantum circuit depth for implementing Hamiltonian simulation algorithms is commonly time dependent so that long time dynamics simulations become impratical on near-term quantum processors. The Hamiltonian simulation algorithm based on Cartan decomposition (CD) provides an appealing scheme for QDSs with fixed-depth circuits while limited to time-independent case. In this work, we generalize this CD-based Hamiltonian simulation algorithm for studying time-dependent systems by combining it with variational Hamiltonian simulation. The time-dependent and time-independent parts of the Hamiltonian are treated with the variational approach and the CD-based Hamiltonian simulation algorithms, respectively. As such, only fixed-depth quantum circuits are required in this hybrid Hamiltonian simulation algorithm while still maintaining high accuracy. We apply this new algorithm to study the response of spin and molecular systems to $\delta$-kick electric fields and obtain accurate spectra for these excitation processes.

The wave function Ansatze are crucial in the context of the Variational Quantum Eigensolver (VQE). In the Noisy Intermediate-Scale Quantum era, the design of low-depth wave function Ansatze is of great importance for executing quantum simulations of electronic structure on noisy quantum devices. In this work, we present a circuit-efficient implementation of two-body Qubit-Excitation-Based (QEB) operator for building shallow-circuit wave function Ansatze within the framework of Adaptive Derivative-Assembled Pseudo-Trotter (ADAPT) VQE. This new algorithm is applied to study ground- and excited-sate problems for small molecules, demonstrating significant reduction of circuit depths compared to fermionic excitation-based and QEB ADAPT-VQE algorithms. This circuit-efficient algorithm shows great promise for quantum simulations of electronic structures, leading to improved performance on current quantum hardware.

The quantum equation-of-motion (qEOM) method with singles and doubles has been suggested to study electronically excited states while it fails to predict the excitation energies dominated by double excitations. In this work, we present an efficient implementation of the qEOM method with single, double and triple excitations. In order to reduce the computational complexity, we utilize the point group symmetry and perturbation theory to screen triple excitation operators, and the scaling is reduced from $N_o^6N_v^6$ to $N_o^5N_v^5$. Furthermore, we introduce a perturbation correction to the excitation energy to account for the effect of ignored triple excitation operators. We apply this method to study challenging cases, for which the qEOM-SD method exhibits large errors, such as the 2 $^1\Delta$ excited state of $\rm{CH}^+$ and the 2 $^1\Sigma$ state of $\rm{H}_8$ molecule. Our new method yields the energy errors less than 0.18 eV.

This paper introduces PatchRefiner, an advanced framework for metric single image depth estimation aimed at high-resolution real-domain inputs. While depth estimation is crucial for applications such as autonomous driving, 3D generative modeling, and 3D reconstruction, achieving accurate high-resolution depth in real-world scenarios is challenging due to the constraints of existing architectures and the scarcity of detailed real-world depth data. PatchRefiner adopts a tile-based methodology, reconceptualizing high-resolution depth estimation as a refinement process, which results in notable performance enhancements. Utilizing a pseudo-labeling strategy that leverages synthetic data, PatchRefiner incorporates a Detail and Scale Disentangling (DSD) loss to enhance detail capture while maintaining scale accuracy, thus facilitating the effective transfer of knowledge from synthetic to real-world data. Our extensive evaluations demonstrate PatchRefiner's superior performance, significantly outperforming existing benchmarks on the Unreal4KStereo dataset by 18.1% in terms of the root mean squared error (RMSE) and showing marked improvements in detail accuracy and consistent scale estimation on diverse real-world datasets like CityScape, ScanNet++, and ETH3D.

Finding accurate ground state energy of a many-body system has been a major challenge in quantum chemistry. The integration of classic and quantum computers has shed new light on resolving this outstanding problem. Here we propose QiankunNet-VQE, a transformer based language models enforced with quantum computing to learn and generate quantum states. It has been implemented using up to 12 qubits and attaining an accuracy level competitive with state-of-the-art classical methods. By leveraging both quantum and classical resources, this scheme overcomes the limitations of variational quantum eigensolver(VQE) without the need for cumbersome error mitigation. Moreover, QiankunNet-VQE provides a different route to achieve a practical quantum advantage for solving many-electron Schr\"odinger equation without requiring extremely precise preparation and measurement of the ground-state wavefunction on quantum computer.

Quantum computing is of great potential for chemical system simulations. In this study, we propose an efficient protocol of quantum computer based simulation of chemical systems which enables accurate chemical reaction modeling on noisy intermediate-scale quantum (NISQ) devices. In this protocol, we combine an correlation energy-based active orbital selection, an effective Hamiltonian from the driven similarity renormalization group (DSRG) method, and a noise-resilient wavefunction ansatz. Such a combination gives a quantum resource-efficient way to accurately simulate chemical systems. The power of this protocol is demonstrated by numerical results for systems with up to tens of atoms. Modeling of a Diels-Alder (DA) reaction is also performed on a cloud-based superconducting quantum computer. These results represent an important step forward in realizing quantum utility in the NISQ era.

Choreographers determine what the dances look like, while cameramen determine the final presentation of dances. Recently, various methods and datasets have showcased the feasibility of dance synthesis. However, camera movement synthesis with music and dance remains an unsolved challenging problem due to the scarcity of paired data. Thus, we present DCM, a new multi-modal 3D dataset, which for the first time combines camera movement with dance motion and music audio. This dataset encompasses 108 dance sequences (3.2 hours) of paired dance-camera-music data from the anime community, covering 4 music genres. With this dataset, we uncover that dance camera movement is multifaceted and human-centric, and possesses multiple influencing factors, making dance camera synthesis a more challenging task compared to camera or dance synthesis alone. To overcome these difficulties, we propose DanceCamera3D, a transformer-based diffusion model that incorporates a novel body attention loss and a condition separation strategy. For evaluation, we devise new metrics measuring camera movement quality, diversity, and dancer fidelity. Utilizing these metrics, we conduct extensive experiments on our DCM dataset, providing both quantitative and qualitative evidence showcasing the effectiveness of our DanceCamera3D model. Code and video demos are available at https://github.com/Carmenw1203/DanceCamera3D-Official., Comment: Accept to CVPR 2024

The task of financial analysis primarily encompasses two key areas: stock trend prediction and the corresponding financial question answering. Currently, machine learning and deep learning algorithms (ML&DL) have been widely applied for stock trend predictions, leading to significant progress. However, these methods fail to provide reasons for predictions, lacking interpretability and reasoning processes. Also, they can not integrate textual information such as financial news or reports. Meanwhile, large language models (LLMs) have remarkable textual understanding and generation ability. But due to the scarcity of financial training datasets and limited integration with real-time knowledge, LLMs still suffer from hallucinations and are unable to keep up with the latest information. To tackle these challenges, we first release AlphaFin datasets, combining traditional research datasets, real-time financial data, and handwritten chain-of-thought (CoT) data. It has a positive impact on training LLMs for completing financial analysis. We then use AlphaFin datasets to benchmark a state-of-the-art method, called Stock-Chain, for effectively tackling the financial analysis task, which integrates retrieval-augmented generation (RAG) techniques. Extensive experiments are conducted to demonstrate the effectiveness of our framework on financial analysis., Comment: COLING 2024. The first three authors contributed equally. Project website: https://github.com/AlphaFin-proj/AlphaFin

Multi-scale deformable attention (MSDeformAttn) has emerged as a key mechanism in various vision tasks, demonstrating explicit superiority attributed to multi-scale grid-sampling. However, this newly introduced operator incurs irregular data access and enormous memory requirement, leading to severe PE underutilization. Meanwhile, existing approaches for attention acceleration cannot be directly applied to MSDeformAttn due to lack of support for this distinct procedure. Therefore, we propose a dedicated algorithm-architecture co-design dubbed DEFA, the first-of-its-kind method for MSDeformAttn acceleration. At the algorithm level, DEFA adopts frequency-weighted pruning and probability-aware pruning for feature maps and sampling points respectively, alleviating the memory footprint by over 80%. At the architecture level, it explores the multi-scale parallelism to boost the throughput significantly and further reduces the memory access via fine-grained layer fusion and feature map reusing. Extensively evaluated on representative benchmarks, DEFA achieves 10.1-31.9x speedup and 20.3-37.7x energy efficiency boost compared to powerful GPUs. It also rivals the related accelerators by 2.2-3.7x energy efficiency improvement while providing pioneering support for MSDeformAttn., Comment: Accepted to DAC 2024

In this report, we present our solution to the multi-task robustness track of the 1st Visual Continual Learning (VCL) Challenge at ICCV 2023 Workshop. We propose a vanilla framework named UniNet that seamlessly combines various visual perception algorithms into a multi-task model. Specifically, we choose DETR3D, Mask2Former, and BinsFormer for 3D object detection, instance segmentation, and depth estimation tasks, respectively. The final submission is a single model with InternImage-L backbone, and achieves a 49.6 overall score (29.5 Det mAP, 80.3 mTPS, 46.4 Seg mAP, and 7.93 silog) on SHIFT validation set. Besides, we provide some interesting observations in our experiments which may facilitate the development of multi-task learning in dense visual prediction., Comment: Technical Report

We introduce an approach for 3D head avatar generation and editing with multi-modal conditioning based on a 3D Generative Adversarial Network (GAN) and a Latent Diffusion Model (LDM). 3D GANs can generate high-quality head avatars given a single or no condition. However, it is challenging to generate samples that adhere to multiple conditions of different modalities. On the other hand, LDMs excel at learning complex conditional distributions. To this end, we propose to exploit the conditioning capabilities of LDMs to enable multi-modal control over the latent space of a pre-trained 3D GAN. Our method can generate and edit 3D head avatars given a mixture of control signals such as RGB input, segmentation masks, and global attributes. This provides better control over the generation and editing of synthetic avatars both globally and locally. Experiments show that our proposed approach outperforms a solely GAN-based approach both qualitatively and quantitatively on generation and editing tasks. To the best of our knowledge, our approach is the first to introduce multi-modal conditioning to 3D avatar generation and editing. \\href{avatarmmc-sig24.github.io}{Project Page}

Long-context processing is a critical ability that constrains the applicability of large language models (LLMs). Although there exist various methods devoted to enhancing the long-context processing ability of LLMs, they are developed in an isolated manner and lack systematic analysis and integration of their strengths, hindering further developments. In this paper, we introduce UniMem, a Unified framework that reformulates existing long-context methods from the view of Memory augmentation of LLMs. Distinguished by its four core dimensions-Memory Management, Memory Writing, Memory Reading, and Memory Injection, UniMem empowers researchers to conduct systematic exploration of long-context methods. We re-formulate 16 existing methods based on UniMem and analyze four representative methods: Transformer-XL, Memorizing Transformer, RMT, and Longformer into equivalent UniMem forms to reveal their design principles and strengths. Based on these analyses, we propose UniMix, an innovative approach that integrates the strengths of these algorithms. Experimental results show that UniMix achieves superior performance in handling long contexts with significantly lower perplexity than baselines., Comment: COLM 2024

In this paper, we investigate how metasurfaces can be deployed to deliver high data rates in a millimeter-wave (mmWave) indoor dense space with many blocking objects. These surfaces can either be static metasurfaces (SMSs) that reflect with fixed phase-shifts or reconfigurable intelligent surfaces (RISs) that can reconfigure their phase-shifts to the currently served user. The latter comes with an increased power, cabling, and signaling cost. To see how reconfigurability affects the network performance, we propose an iterative algorithm based on the feasible point pursuit successive convex approximation method. We jointly optimize the types and phase-shifts of the surfaces and the time portion allocated to each user equipment to maximize the minimum data rate achieved by the network. Our numerical results demonstrate that the minimum data rate improves as more RISs are introduced but the gain diminishes after some point. Therefore, introducing more reconfigurability is not always necessary. Another result shows that to reach the same data rate achieved by using 22 SMSs, at least 18 RISs are needed. This suggests that when it is costly to deploy many RISs, as an inexpensive alternative solution, one can reach the same data rate just by densely deploying more SMSs., Comment: 6 pages, 5 figures, Accepted to be presented in IEEE WCNC 2024

Single image depth estimation is a foundational task in computer vision and generative modeling. However, prevailing depth estimation models grapple with accommodating the increasing resolutions commonplace in today's consumer cameras and devices. Existing high-resolution strategies show promise, but they often face limitations, ranging from error propagation to the loss of high-frequency details. We present PatchFusion, a novel tile-based framework with three key components to improve the current state of the art: (1) A patch-wise fusion network that fuses a globally-consistent coarse prediction with finer, inconsistent tiled predictions via high-level feature guidance, (2) A Global-to-Local (G2L) module that adds vital context to the fusion network, discarding the need for patch selection heuristics, and (3) A Consistency-Aware Training (CAT) and Inference (CAI) approach, emphasizing patch overlap consistency and thereby eradicating the necessity for post-processing. Experiments on UnrealStereo4K, MVS-Synth, and Middleburry 2014 demonstrate that our framework can generate high-resolution depth maps with intricate details. PatchFusion is independent of the base model for depth estimation. Notably, our framework built on top of SOTA ZoeDepth brings improvements for a total of 17.3% and 29.4% in terms of the root mean squared error (RMSE) on UnrealStereo4K and MVS-Synth, respectively.

The Multi-Modal Large Language Model (MLLM) refers to an extension of the Large Language Model (LLM) equipped with the capability to receive and infer multi-modal data. Spatial awareness stands as one of the crucial abilities of MLLM, encompassing diverse skills related to understanding spatial relationships among objects and between objects and the scene area. Industries such as autonomous driving, smart healthcare, robotics, virtual, and augmented reality heavily demand MLLM's spatial awareness capabilities. However, there exists a noticeable gap between the current spatial awareness capabilities of MLLM and the requirements set by human needs. To address this issue, this paper proposes using more precise spatial position information between objects to guide MLLM in providing more accurate responses to user-related inquiries. Specifically, for a particular multi-modal task, we utilize algorithms for acquiring geometric spatial information and scene graphs to obtain relevant geometric spatial information and scene details of objects involved in the query. Subsequently, based on this information, we direct MLLM to address spatial awareness-related queries posed by the user. Extensive experiments were conducted in benchmarks such as MME, MM-Vet, and other multi-modal large language models. The experimental results thoroughly confirm the efficacy of the proposed method in enhancing the spatial awareness tasks and associated tasks of MLLM.

Multi-modal Large Language Model (MLLM) refers to a model expanded from a Large Language Model (LLM) that possesses the capability to handle and infer multi-modal data. Current MLLMs typically begin by using LLMs to decompose tasks into multiple subtasks, then employing individual pre-trained models to complete specific subtasks, and ultimately utilizing LLMs to integrate the results of each subtasks to obtain the results of the task. In real-world scenarios, when dealing with large projects, it is common practice to break down the project into smaller sub-projects, with different teams providing corresponding solutions or results. The project owner then decides which solution or result to use, ensuring the best possible outcome for each subtask and, consequently, for the entire project. Inspired by this, this study considers selecting multiple pre-trained models to complete the same subtask. By combining the results from multiple pre-trained models, the optimal subtask result is obtained, enhancing the performance of the MLLM. Specifically, this study first selects multiple pre-trained models focused on the same subtask based on distinct evaluation approaches, and then invokes these models in parallel to process input data and generate corresponding subtask results. Finally, the results from multiple pre-trained models for the same subtask are compared using the LLM, and the best result is chosen as the outcome for that subtask. Extensive experiments are conducted in this study using GPT-4 annotated datasets and human-annotated datasets. The results of various evaluation metrics adequately demonstrate the effectiveness of the proposed approach in this paper.

Knowledge base question answering (KBQA) is a critical yet challenging task due to the vast number of entities within knowledge bases and the diversity of natural language questions posed by users. Unfortunately, the performance of most KBQA models tends to decline significantly in real-world scenarios where high-quality annotated data is insufficient. To mitigate the burden associated with manual annotation, we introduce FlexKBQA by utilizing Large Language Models (LLMs) as program translators for addressing the challenges inherent in the few-shot KBQA task. Specifically, FlexKBQA leverages automated algorithms to sample diverse programs, such as SPARQL queries, from the knowledge base, which are subsequently converted into natural language questions via LLMs. This synthetic dataset facilitates training a specialized lightweight model for the KB. Additionally, to reduce the barriers of distribution shift between synthetic data and real user questions, FlexKBQA introduces an executionguided self-training method to iterative leverage unlabeled user questions. Furthermore, we explore harnessing the inherent reasoning capability of LLMs to enhance the entire framework. Consequently, FlexKBQA delivers substantial flexibility, encompassing data annotation, deployment, and being domain agnostic. Through extensive experiments on GrailQA, WebQSP, and KQA Pro, we observe that under the few-shot even the more challenging zero-shot scenarios, FlexKBQA achieves impressive results with a few annotations, surpassing all previous baselines and even approaching the performance of supervised models, achieving a remarkable 93% performance relative to the fully-supervised models. We posit that FlexKBQA represents a significant advancement towards exploring better integration of large and lightweight models. The code is open-sourced., Comment: Accepted as AAAI-24 Oral paper; Knowledge Base Question Answering; Large Language Model; Data Generation; Few-Shot & Zero-Shot

Point-cloud-based 3D perception has attracted great attention in various applications including robotics, autonomous driving and AR/VR. In particular, the 3D sparse convolution (SpConv) network has emerged as one of the most popular backbones due to its excellent performance. However, it poses severe challenges to real-time perception on general-purpose platforms, such as lengthy map search latency, high computation cost, and enormous memory footprint. In this paper, we propose SpOctA, a SpConv accelerator that enables high-speed and energy-efficient point cloud processing. SpOctA parallelizes the map search by utilizing algorithm-architecture co-optimization based on octree encoding, thereby achieving 8.8-21.2x search speedup. It also attenuates the heavy computational workload by exploiting inherent sparsity of each voxel, which eliminates computation redundancy and saves 44.4-79.1% processing latency. To optimize on-chip memory management, a SpConv-oriented non-uniform caching strategy is introduced to reduce external memory access energy by 57.6% on average. Implemented on a 40nm technology and extensively evaluated on representative benchmarks, SpOctA rivals the state-of-the-art SpConv accelerators by 1.1-6.9x speedup with 1.5-3.1x energy efficiency improvement., Comment: Accepted to ICCAD 2023

Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical applications. Existing depth estimation systems, however, suffer inevitably from real-world corruptions and perturbations and are struggled to provide reliable depth predictions under such cases. In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation. This challenge was developed based on the newly established KITTI-C and NYUDepth2-C benchmarks. We hosted two stand-alone tracks, with an emphasis on robust self-supervised and robust fully-supervised depth estimation, respectively. Out of more than two hundred participants, nine unique and top-performing solutions have appeared, with novel designs ranging from the following aspects: spatial- and frequency-domain augmentations, masked image modeling, image restoration and super-resolution, adversarial training, diffusion-based noise suppression, vision-language pre-training, learned model ensembling, and hierarchical feature enhancement. Extensive experimental analyses along with insightful observations are drawn to better understand the rationale behind each design. We hope this challenge could lay a solid foundation for future research on robust and reliable depth estimation and beyond. The datasets, competition toolkit, workshop recordings, and source code from the winning teams are publicly available on the challenge website., Comment: Technical Report; 65 pages, 34 figures, 24 tables; Code at https://github.com/ldkong1205/RoboDepth

Accurately solving the Schr\"odinger equation for intricate systems remains a prominent challenge in physical sciences. A paradigm-shifting approach to address this challenge involves the application of artificial intelligence techniques. In this study, we introduce a machine-learning model named QiankunNet, based on the transformer architecture employed in language models. By incorporating the attention mechanism, QiankunNet adeptly captures intricate quantum correlations, which enhances its expressive power. The autoregressive attribute of QiankunNet allows for the adoption of an exceedingly efficient sampling technique to estimate the total energy, facilitating the model training process. Additionally, performance of QiankunNet can be further improved via a pre-training process. This work not only demonstrates the power of artificial intelligence in quantum mechanics but also signifies a pivotal advancement in extending the boundary of systems which can be studied with a full-configuration-interaction accuracy.