arXiv subjects

Bo Liu

Publications and source records attributed to Bo Liu.

At least 325 records · Page 18Linked to original sources

arXiv2024

A Survey of Deep Learning Based Radar and Vision Fusion for 3D Object Detection in Autonomous Driving

With the rapid advancement of autonomous driving technology, there is a growing need for enhanced safety and efficiency in the automatic environmental perception of vehicles during their operation. In modern vehicle setups, cameras and mmWave radar (radar), being the most extensively employed sensors, demonstrate complementary characteristics, inherently rendering them conducive to fusion and facilitating the achievement of both robust performance and cost-effectiveness. This paper focuses on a comprehensive survey of radar-vision (RV) fusion based on deep learning methods for 3D object detection in autonomous driving. We offer a comprehensive overview of each RV fusion category, specifically those employing region of interest (ROI) fusion and end-to-end fusion strategies. As the most promising fusion strategy at present, we provide a deeper classification of end-to-end fusion methods, including those 3D bounding box prediction based and BEV based approaches. Moreover, aligning with recent advancements, we delineate the latest information on 4D radar and its cutting-edge applications in autonomous vehicles (AVs). Finally, we present the possible future trends of RV fusion and summarize this paper.

cs.CV↗

arXiv2024

An Efficient and Multi-private Key Secure Aggregation for Federated Learning

With the emergence of privacy leaks in federated learning, secure aggregation protocols that mainly adopt either homomorphic encryption or threshold secret sharing have been widely developed for federated learning to protect the privacy of the local training data of each client. However, these existing protocols suffer from many shortcomings, such as the dependence on a trusted third party, the vulnerability to clients being corrupted, low efficiency, the trade-off between security and fault tolerance, etc. To solve these disadvantages, we propose an efficient and multi-private key secure aggregation scheme for federated learning. Specifically, we skillfully modify the variant ElGamal encryption technique to achieve homomorphic addition operation, which has two important advantages: 1) The server and each client can freely select public and private keys without introducing a trust third party and 2) Compared to the variant ElGamal encryption, the plaintext space is relatively large, which is more suitable for the deep model. Besides, for the high dimensional deep model parameter, we introduce a super-increasing sequence to compress multi-dimensional data into 1-D, which can greatly reduce encryption and decryption times as well as communication for ciphertext transmission. Detailed security analyses show that our proposed scheme achieves the semantic security of both individual local gradients and the aggregated result while achieving optimal robustness in tolerating both client collusion and dropped clients. Extensive simulations demonstrate that the accuracy of our scheme is almost the same as the non-private approach, while the efficiency of our scheme is much better than the state-of-the-art homomorphic encryption-based secure aggregation schemes. More importantly, the efficiency advantages of our scheme will become increasingly prominent as the number of model parameters increases.

cs.CR↗

arXiv2024

DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data

Proof assistants like Lean have revolutionized mathematical proof verification, ensuring high accuracy and reliability. Although large language models (LLMs) show promise in mathematical reasoning, their advancement in formal theorem proving is hindered by a lack of training data. To address this issue, we introduce an approach to generate extensive Lean 4 proof data derived from high-school and undergraduate-level mathematical competition problems. This approach involves translating natural language problems into formal statements, filtering out low-quality statements, and generating proofs to create synthetic data. After fine-tuning the DeepSeekMath 7B model on this synthetic dataset, which comprises 8 million formal statements with proofs, our model achieved whole-proof generation accuracies of 46.3% with 64 samples and 52% cumulatively on the Lean 4 miniF2F test, surpassing the baseline GPT-4 at 23.0% with 64 samples and a tree search reinforcement learning method at 41.0%. Additionally, our model successfully proved 5 out of 148 problems in the Lean 4 Formalized International Mathematical Olympiad (FIMO) benchmark, while GPT-4 failed to prove any. These results demonstrate the potential of leveraging large-scale synthetic data to enhance theorem-proving capabilities in LLMs. Both the synthetic dataset and the model will be made available to facilitate further research in this promising field.

cs.AI↗

arXiv2024

Thermodynamics of charged black holes in Maxwell-dilaton-massive gravity

Considering the nonminimal coupling of the dilaton field to the massive graviton field in Maxwell-dilaton-massive gravity, we obtain a class of analytical solutions of charged black holes, which are neither asymptotically flat nor (A)dS. The calculated thermodynamic quantities, such as mass, temperature and entropy, verify the validity of the first law of black hole thermodynamics. Moreover, we further investigate the critical behaviors of these black holes in the grand canonical and canonical ensemble, and find a novel critical phenomenon never before observed, known as the ``reverse" reentrant phase transition with a tricritical point. It implies that the system undergoes a novel ``SBH-LBH-SBH" phase transition process, and is the reverse of the ``LBH-SBH-LBH" process observed in reentrant phase transitions.

hep-th↗

arXiv2024

Context-Enhanced Video Moment Retrieval with Large Language Models

Current methods for Video Moment Retrieval (VMR) struggle to align complex situations involving specific environmental details, character descriptions, and action narratives. To tackle this issue, we propose a Large Language Model-guided Moment Retrieval (LMR) approach that employs the extensive knowledge of Large Language Models (LLMs) to improve video context representation as well as cross-modal alignment, facilitating accurate localization of target moments. Specifically, LMR introduces a context enhancement technique with LLMs to generate crucial target-related context semantics. These semantics are integrated with visual features for producing discriminative video representations. Finally, a language-conditioned transformer is designed to decode free-form language queries, on the fly, using aligned video representations for moment retrieval. Extensive experiments demonstrate that LMR achieves state-of-the-art results, outperforming the nearest competitor by up to 3.28\% and 4.06\% on the challenging QVHighlights and Charades-STA benchmarks, respectively. More importantly, the performance gains are significantly higher for localization of complex queries.

cs.CV↗

arXiv2024

Quantum droplets in dipolar condensate mixtures with arbitrary dipole orientations

Through considering a two-component dipolar Bose-Einstein condensate, we investigate the influence of the angle between the polarization orientations of the two species on the ground states, and show that the miscibility between the two components can be adjusted not only by the inter-component contact interaction but also by the polarization angle. Particularly, in the presence of an external confinement, the two species exhibit a preference for splitting into multiple droplets separated from each other in the immiscible regime, featuring a zig-zag like profile. Furthermore, the number of separated droplets depends solely on the polarization angle. This introduces a promising degree of freedom for exploring emergent states of matter in dipolar quantum gases.

cond-mat.quant-gas↗

arXiv2024

EasyGen: Easing Multimodal Generation with BiDiffuser and LLMs

We present EasyGen, an efficient model designed to enhance multimodal understanding and generation by harnessing the capabilities of diffusion models and large language models (LLMs), Unlike existing multimodal models that predominately depend on encoders like CLIP or ImageBind and need ample amounts of training data to bridge modalities,EasyGen leverages BiDiffuser,a bidirectional conditional diffusion model, to foster more efficient modality interactions. Easygen achieves text generation by training a projection layer linking BiDiffuser and an LLM, and facilities image generation by training an adapter to align the LLM's text space with the BiDiffuser's image space, Comprehensive quantitative and qualitative experiments show that EasyGen excels in data-efficient training, high-quality image generation, and extendibility, effectively addressing the challenges in multimodal generation. The source code is available at https://github.com/zxy556677/EasyGen.

cs.AI↗

arXiv2024

One nose but two nostrils: Learn to align with sparse connections between two olfactory cortices

The integration of neural representations in the two hemispheres is an important problem in neuroscience. Recent experiments revealed that odor responses in cortical neurons driven by separate stimulation of the two nostrils are highly correlated. This bilateral alignment points to structured inter-hemispheric connections, but detailed mechanism remains unclear. Here, we hypothesized that continuous exposure to environmental odors shapes these projections and modeled it as online learning with local Hebbian rule. We found that Hebbian learning with sparse connections achieves bilateral alignment, exhibiting a linear trade-off between speed and accuracy. We identified an inverse scaling relationship between the number of cortical neurons and the inter-hemispheric projection density required for desired alignment accuracy, i.e., more cortical neurons allow sparser inter-hemispheric projections. We next compared the alignment performance of local Hebbian rule and the global stochastic-gradient-descent (SGD) learning for artificial neural networks. We found that although SGD leads to the same alignment accuracy with modestly sparser connectivity, the same inverse scaling relation holds. We showed that their similar performance originates from the fact that the update vectors of the two learning rules align significantly throughout the learning process. This insight may inspire efficient sparse local learning algorithms for more complex problems.

q-bio.NC↗

arXiv2024

The Performance of AC-coupled Strip LGAD developed by IHEP

The AC-coupled Strip LGAD (Strip AC-LGAD) is a novel LGAD design that diminishes the density of readout electronics through the use of strip electrodes, enabling the simultaneous measurement of time and spatial information. The Institute of High Energy Physics has designed a long Strip AC-LGAD prototype with a strip electrode length of 5.7 mm and pitches of 150 $μm$, 200 $μm$, and 250 $μm$. Spatial and timing resolutions of the long Strip AC-LGAD are studied by pico-second laser test and beta source tests. The laser test demonstrates that spatial resolution improves as the pitch size decreases, with an optimal resolution achieved at 8.3 $μ$m. Furthermore, the Beta source test yields a timing resolution of 37.6 ps.

physics.ins-det↗

arXiv2024

HiH: A Multi-modal Hierarchy in Hierarchy Network for Unconstrained Gait Recognition

Gait recognition has achieved promising advances in controlled settings, yet it significantly struggles in unconstrained environments due to challenges such as view changes, occlusions, and varying walking speeds. Additionally, efforts to fuse multiple modalities often face limited improvements because of cross-modality incompatibility, particularly in outdoor scenarios. To address these issues, we present a multi-modal Hierarchy in Hierarchy network (HiH) that integrates silhouette and pose sequences for robust gait recognition. HiH features a main branch that utilizes Hierarchical Gait Decomposer (HGD) modules for depth-wise and intra-module hierarchical examination of general gait patterns from silhouette data. This approach captures motion hierarchies from overall body dynamics to detailed limb movements, facilitating the representation of gait attributes across multiple spatial resolutions. Complementing this, an auxiliary branch, based on 2D joint sequences, enriches the spatial and temporal aspects of gait analysis. It employs a Deformable Spatial Enhancement (DSE) module for pose-guided spatial attention and a Deformable Temporal Alignment (DTA) module for aligning motion dynamics through learned temporal offsets. Extensive evaluations across diverse indoor and outdoor datasets demonstrate HiH's state-of-the-art performance, affirming a well-balanced trade-off between accuracy and efficiency.

cs.CV↗

arXiv2024

Dual-Role AoI-based Incentive Mechanism for HD map Crowdsourcing

A high-quality fresh high-definition (HD) map is vital in enhancing transportation efficiency and safety in autonomous driving. Vehicle-based crowdsourcing offers a promising approach for updating HD maps. However, recruiting crowdsourcing vehicles involves making the challenging tradeoff between the HD map freshness and recruitment costs. Existing studies on HD map crowdsourcing often (1) prioritize maximizing spatial coverage and (2) overlook the dual role of crowdsourcing vehicles in HD maps, as vehicles serve both as contributors and customers of HD maps. This motivates us to propose the Dual-Role Age of Information (AoI) based Incentive Mechanism (DRAIM) to address these issues. % Specifically, we propose the trajectory age of information, incorporating the expected AoI of the HD map and the trajectory, to quantify a vehicle's HD map usage utility, which is freshness- and trajectory-dependent. DRAIM aims to achieve the company's tradeoff between freshness and recruitment costs.

cs.GT↗

arXiv2024

How Good Are LLMs at Out-of-Distribution Detection?

Out-of-distribution (OOD) detection plays a vital role in enhancing the reliability of machine learning (ML) models. The emergence of large language models (LLMs) has catalyzed a paradigm shift within the ML community, showcasing their exceptional capabilities across diverse natural language processing tasks. While existing research has probed OOD detection with relative small-scale Transformers like BERT, RoBERTa and GPT-2, the stark differences in scales, pre-training objectives, and inference paradigms call into question the applicability of these findings to LLMs. This paper embarks on a pioneering empirical investigation of OOD detection in the domain of LLMs, focusing on LLaMA series ranging from 7B to 65B in size. We thoroughly evaluate commonly-used OOD detectors, scrutinizing their performance in both zero-grad and fine-tuning scenarios. Notably, we alter previous discriminative in-distribution fine-tuning into generative fine-tuning, aligning the pre-training objective of LLMs with downstream tasks. Our findings unveil that a simple cosine distance OOD detector demonstrates superior efficacy, outperforming other OOD detectors. We provide an intriguing explanation for this phenomenon by highlighting the isotropic nature of the embedding spaces of LLMs, which distinctly contrasts with the anisotropic property observed in smaller BERT family models. The new insight enhances our understanding of how LLMs detect OOD data, thereby enhancing their adaptability and reliability in dynamic environments. We have released the source code at \url{https://github.com/Awenbocc/LLM-OOD} for other researchers to reproduce our results.

cs.CL↗

arXiv2024

VI-OOD: A Unified Representation Learning Framework for Textual Out-of-distribution Detection

Out-of-distribution (OOD) detection plays a crucial role in ensuring the safety and reliability of deep neural networks in various applications. While there has been a growing focus on OOD detection in visual data, the field of textual OOD detection has received less attention. Only a few attempts have been made to directly apply general OOD detection methods to natural language processing (NLP) tasks, without adequately considering the characteristics of textual data. In this paper, we delve into textual OOD detection with Transformers. We first identify a key problem prevalent in existing OOD detection methods: the biased representation learned through the maximization of the conditional likelihood $p(y\mid x)$ can potentially result in subpar performance. We then propose a novel variational inference framework for OOD detection (VI-OOD), which maximizes the likelihood of the joint distribution $p(x, y)$ instead of $p(y\mid x)$. VI-OOD is tailored for textual OOD detection by efficiently exploiting the representations of pre-trained Transformers. Through comprehensive experiments on various text classification tasks, VI-OOD demonstrates its effectiveness and wide applicability. Our code has been released at \url{https://github.com/liam0949/LLM-OOD}.

cs.CL↗

arXiv2024

Integration of Computer Networks and Artificial Neural Networks for an AI-based Network Operator

This paper proposes an integrated approach combining computer networks and artificial neural networks to construct an intelligent network operator, functioning as an AI model. State information from computer networks is transformed into embedded vectors, enabling the operator to efficiently recognize different pieces of information and accurately output appropriate operations for the computer network at each step. The operator has undergone comprehensive testing, achieving a 100% accuracy rate, thus eliminating operational risks. Furthermore, a novel algorithm is proposed to emphasize crucial training losses, aiming to enhance the efficiency of operator training. Additionally, a simple computer network simulator is created and encapsulated into training and testing environment components, enabling automation of the data collection, training, and testing processes. This abstract outlines the core contributions of the paper while highlighting the innovative methodology employed in the development and validation of the AI-based network operator.

cs.NI↗

arXiv2024

The Physics potential of the CEPC. Prepared for the US Snowmass Community Planning Exercise (Snowmass 2021)

The Circular Electron Positron Collider (CEPC) is a large-scale collider facility that can serve as a factory of the Higgs, Z, and W bosons and is upgradable to run at the ttbar threshold. This document describes the latest CEPC nominal operation scenario and particle yields and updates the corresponding physics potential. A new detector concept is also briefly described. This submission is for consideration by the Snowmass process.

hep-ph↗

arXiv2024

Accelerate Solving Expensive Scheduling by Leveraging Economical Auxiliary Tasks

To fully leverage the multi-task optimization paradigm for accelerating the solution of expensive scheduling problems, this study has effectively tackled three vital concerns. The primary issue is identifying auxiliary tasks that closely resemble the original expensive task. We suggested a sampling strategy based on job importance, creating a compact matrix by extracting crucial rows from the entire problem specification matrix of the expensive task. This matrix serves as an economical auxiliary task. Mathematically, we proved that this economical auxiliary task bears similarity to its corresponding expensive task. The subsequent concern revolves around making auxiliary tasks more cost-effective. We determined the sampling proportions for the entire problem specification matrix through factorial design experiments, resulting in a more compact auxiliary task. With a reduced search space and shorter function evaluation time, it can rapidly furnish high-quality transferable information for the primary task. The last aspect involves designing transferable deep information from auxiliary tasks. We regarded the job priorities in the (sub-) optimal solutions to the economical auxiliary task as transferable invariants. By adopting a partial solution patching strategy, we augmented specificity knowledge onto the common knowledge to adapt to the target expensive task. The strategies devised for constructing task pairs and facilitating knowledge transfer, when incorporated into various evolutionary multitasking algorithms, were utilized to address expensive instances of permutation flow shop scheduling. Extensive experiments and statistical comparisons have validated that, with the collaborative synergy of these strategies, the performance of evolutionary multitasking algorithms is significantly enhanced in handling expensive scheduling tasks.

math.OC↗

arXiv2024

Intelligent Robotic Control System Based on Computer Vision Technology

The article explores the intersection of computer vision technology and robotic control, highlighting its importance in various fields such as industrial automation, healthcare, and environmental protection. Computer vision technology, which simulates human visual observation, plays a crucial role in enabling robots to perceive and understand their surroundings, leading to advancements in tasks like autonomous navigation, object recognition, and waste management. By integrating computer vision with robot control, robots gain the ability to interact intelligently with their environment, improving efficiency.

cs.RO↗

arXiv2024

Communication Efficient Distributed Training with Distributed Lion

The Lion optimizer has been a promising competitor with the AdamW for training large AI models, with advantages on memory, computation, and sample efficiency. In this paper, we introduce Distributed Lion, an innovative adaptation of Lion for distributed training environments. Leveraging the sign operator in Lion, our Distributed Lion only requires communicating binary or lower-precision vectors between workers to the center server, significantly reducing the communication cost. Our theoretical analysis confirms Distributed Lion's convergence properties. Empirical results demonstrate its robustness across a range of tasks, worker counts, and batch sizes, on both vision and language problems. Notably, Distributed Lion attains comparable performance to standard Lion or AdamW optimizers applied on aggregated gradients, but with significantly reduced communication bandwidth. This feature is particularly advantageous for training large models. In addition, we also demonstrate that Distributed Lion presents a more favorable performance-bandwidth balance compared to existing efficient distributed methods such as deep gradient compression and ternary gradients.

cs.DC↗