arXiv subjects

Bo Wang

Publications and source records attributed to Bo Wang.

At least 397 records · Page 22Linked to original sources

arXiv2024

The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report

This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes. The task of this challenge is to super-resolve an input image with a magnification factor of x4 based on pairs of low and corresponding high-resolution images. The primary objective is to develop networks that optimize various aspects such as runtime, parameters, and FLOPs, while still maintaining a peak signal-to-noise ratio (PSNR) of approximately 26.90 dB on the DIV2K_LSDIR_valid dataset and 26.99 dB on the DIV2K_LSDIR_test dataset. In addition, this challenge has 4 tracks including the main track (overall performance), sub-track 1 (runtime), sub-track 2 (FLOPs), and sub-track 3 (parameters). In the main track, all three metrics (ie runtime, FLOPs, and parameter count) were considered. The ranking of the main track is calculated based on a weighted sum-up of the scores of all other sub-tracks. In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking. In sub-track 2, the number of FLOPs was considered. The score calculated based on the corresponding FLOPs was used to determine the ranking. In sub-track 3, the number of parameters was considered. The score calculated based on the corresponding parameters was used to determine the ranking. RLFN is set as the baseline for efficiency measurement. The challenge had 262 registered participants, and 34 teams made valid submissions. They gauge the state-of-the-art in efficient single-image super-resolution. To facilitate the reproducibility of the challenge and enable other researchers to build upon these findings, the code and the pre-trained model of validated solutions are made publicly available at https://github.com/Amazingren/NTIRE2024_ESR/.

cs.CV↗

arXiv2024

Rapidly growing primordial black holes as seeds of the massive high-redshift JWST Galaxies

A group of massive galaxies at redshifts of $z\gtrsim 7$ have been recently detected by the James Webb Space Telescope (JWST), which were unexpected to form so early within the framework of standard Big Bang cosmology. In this work, we propose that this puzzle can be explained by the presence of some primordial black holes (PBHs) with a mass of $\sim 1000 M_\odot$. These PBHs, clothed in dark matter halo and undergoing super-Eddington accretion, serve as seeds for the early galaxy formation with masses of $\sim 10^{8}-10^{10}~M_\odot$ at high redshift, thus accounting for the JWST observations. Using a hierarchical Bayesian inference framework to constrain the PBH mass distribution models, we find that the Lognormal model with $M_{\rm c}\sim 750M_\odot$ is preferred over other hypotheses. These rapidly growing BHs are expected to emit strong radiation and may appear as high-redshift compact objects, similar to those recently discovered by JWST. Although we focuse on PBHs in this work, the bound on the initial mass of the seed black holes remains robust even if they were formed through astrophysical channels.

astro-ph.CO↗

arXiv2024

Aligning Large Language Models from Self-Reference AI Feedback with one General Principle

In aligning large language models (LLMs), utilizing feedback from existing advanced AI rather than humans is an important method to scale supervisory signals. However, it is highly challenging for AI to understand human intentions and societal values, and provide accurate preference feedback based on these. Current AI feedback methods rely on powerful LLMs, carefully designed specific principles to describe human intentions, and are easily influenced by position bias. To address these issues, we propose a self-reference-based AI feedback framework that enables a 13B Llama2-Chat to provide high-quality feedback under simple and general principles such as ``best for humanity``. Specifically, we allow the AI to first respond to the user's instructions, then generate criticism of other answers based on its own response as a reference, and finally determine which answer better fits human preferences according to the criticism. Additionally, we use a self-consistency method to further reduce the impact of position bias, and employ semantic perplexity to calculate the preference strength differences between different answers. Experimental results show that our method enables 13B and 70B Llama2-Chat annotators to provide high-quality preference feedback, and the policy models trained based on these preference data achieve significant advantages in benchmark datasets through reinforcement learning.

cs.CL↗

arXiv2024

Communication-Efficient MARL for Platoon Stability and Energy-efficiency Co-optimization in Cooperative Adaptive Cruise Control of CAVs

Cooperative adaptive cruise control (CACC) has been recognized as a fundamental function of autonomous driving, in which platoon stability and energy efficiency are outstanding challenges that are difficult to accommodate in real-world operations. This paper studied the CACC of connected and autonomous vehicles (CAVs) based on the multi-agent reinforcement learning algorithm (MARL) to optimize platoon stability and energy efficiency simultaneously. The optimal use of communication bandwidth is the key to guaranteeing learning performance in real-world driving, and thus this paper proposes a communication-efficient MARL by incorporating the quantified stochastic gradient descent (QSGD) and a binary differential consensus (BDC) method into a fully-decentralized MARL framework. We benchmarked the performance of our proposed BDC-MARL algorithm against several several non-communicative andcommunicative MARL algorithms, e.g., IA2C, FPrint, and DIAL, through the evaluation of platoon stability, fuel economy, and driving comfort. Our results show that BDC-MARL achieved the highest energy savings, improving by up to 5.8%, with an average velocity of 15.26 m/s and an inter-vehicle spacing of 20.76 m. In addition, we conducted different information-sharing analyses to assess communication efficacy, along with sensitivity analyses and scalability tests with varying platoon sizes. The practical effectiveness of our approach is further demonstrated using real-world scenarios sourced from open-sourced OpenACC.

eess.SY↗

arXiv2024

Topological water-wave structures manipulating particles

Topological wave structures, such as vortices and skyrmions, appear in a variety of quantum and classical wave fields, including optics and acoustics. In particular, optical vortices have found numerous applications ranging from quantum information to astrophysics. Furthermore, both optical and acoustic structured waves are crucial for manipulation of small particles, from atoms to macroscopic biological objects. Here we report on the controllable generation of topological structures -- wave vortices, skyrmions, and polarization Möbius strips -- in interfering gravity water waves. Most importantly, we demonstrate efficient manipulation of subwavelength and wavelength-order floating particles with topologically structured water waves. This includes trapping of the particles in the high-intensity field zones, as well as controllable orbital and spinning motions due to the orbital and spin angular momenta of water waves. Our results reveal the water-wave counterpart of optical and acoustic manipulations, which paves the avenue for applications in hydrodynamics and microfluidics.

physics.class-ph↗

arXiv2024

Spectrum of the molecular hexaquarks

We investigate the mass spectra of molecular-type hexaquark states in the dibaryon systems. These systems are composed of the charmed baryons $[Σ_c^{(\ast)}$, $Ξ_c^{(\prime,\ast)}]$, doubly charmed baryons $[Ξ_{cc}^{(\ast)}]$, and hyperons $[Σ^{(\ast)}$, $Ξ^{(\ast)}]$. We consider all possible combinations of particle-particle and particle-antiparticle pairs, including the S-wave spin multiplets in each combination. We establish the underlying connections among the molecular tetraquarks, pentaquarks, and hexaquarks with the effective quark-level interactions. We find that the existence of molecular states in $DD^\ast$, $D\bar{D}^\ast$, and $Σ_c\bar{D}^{(\ast)}$ systems leads to the emergence of a large number of deuteron-like hexaquarks in the heavy flavor sectors. Currently, there have been several experimental candidates for molecular tetraquarks and pentaquarks. The experimental search for near-threshold hexaquarks will further advance the establishment of the underlying dynamical picture of hadronic molecules and deepen our understanding of the role of spin-flavor symmetry in near-threshold residual strong interactions.

hep-ph↗

arXiv2024

Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models

Large language models (LLMs) have achieved impressive performance across various natural language benchmarks, prompting a continual need to curate more difficult datasets for larger LLMs, which is costly and time-consuming. In this paper, we propose to automate dataset updating and provide systematic analysis regarding its effectiveness in dealing with benchmark leakage issue, difficulty control, and stability. Thus, once the current benchmark has been mastered or leaked, we can update it for timely and reliable evaluation. There are two updating strategies: 1) mimicking strategy to generate similar samples based on original data, preserving stylistic and contextual essence, and 2) extending strategy that further expands existing samples at varying cognitive levels by adapting Bloom's taxonomy of educational objectives. Extensive experiments on updated MMLU and BIG-Bench demonstrate the stability of the proposed strategies and find that the mimicking strategy can effectively alleviate issues of overestimation from benchmark leakage. In cases where the efficient mimicking strategy fails, our extending strategy still shows promising results. Additionally, by controlling the difficulty, we can better discern the models' performance and enable fine-grained analysis neither too difficult nor too easy an exam can fairly judge students' learning status. To the best of our knowledge, we are the first to automate updating benchmarks for reliable and timely evaluation. Our demo leaderboard can be found at https://yingjiahao14.github.io/Automating-DatasetUpdates/.

cs.CL↗

arXiv2024

A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential

Retrieval-Augmented Generation (RAG) is an effective solution to supplement necessary knowledge to large language models (LLMs). Targeting its bottleneck of retriever performance, "generate-then-read" pipeline is proposed to replace the retrieval stage with generation from the LLM itself. Although promising, this research direction is underexplored and still cannot work in the scenario when source knowledge is given. In this paper, we formalize a general "A + B" framework with varying combinations of foundation models and types for systematic investigation. We explore the efficacy of the base and chat versions of LLMs and found their different functionalities suitable for generator A and reader B, respectively. Their combinations consistently outperform single models, especially in complex scenarios. Furthermore, we extend the application of the "A + B" framework to scenarios involving source documents through continuous learning, enabling the direct integration of external knowledge into LLMs. This approach not only facilitates effective acquisition of new knowledge but also addresses the challenges of safety and helpfulness post-adaptation. The paper underscores the versatility of the "A + B" framework, demonstrating its potential to enhance the practical application of LLMs across various domains.

cs.CL↗

arXiv2024

Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models

Learning multi-task models for jointly detecting stance and verifying rumors poses challenges due to the need for training data of stance at post level and rumor veracity at claim level, which are difficult to obtain. To address this issue, we leverage large language models (LLMs) as the foundation annotators for the joint stance detection (SD) and rumor verification (RV) tasks, dubbed as JSDRV. We introduce a novel reinforcement tuning framework to enhance the joint predictive capabilities of LLM-based SD and RV components. Specifically, we devise a policy for selecting LLM-annotated data at the two levels, employing a hybrid reward mechanism to choose high-quality labels for effective LLM fine-tuning on both tasks. Results demonstrate that JSDRV improves the capabilities of LLMs in the joint tasks, not only outperforming state-of-the-art methods but also generalizing to non-LLMs accommodated as task models.

cs.CL↗

arXiv2024

Enhancing Retrieval-Augmented LMs with a Two-stage Consistency Learning Compressor

Despite the prevalence of retrieval-augmented language models (RALMs), the seamless integration of these models with retrieval mechanisms to enhance performance in document-based tasks remains challenging. While some post-retrieval processing Retrieval-Augmented Generation (RAG) methods have achieved success, most still lack the ability to distinguish pertinent from extraneous information, leading to potential inconsistencies and reduced precision in the generated output, which subsequently affects the truthfulness of the language model's responses. To address these limitations, this work proposes a novel two-stage consistency learning approach for retrieved information compression in retrieval-augmented language models to enhance performance. By incorporating consistency learning, the aim is to generate summaries that maintain coherence and alignment with the intended semantic representations of a teacher model while improving faithfulness to the original retrieved documents. The proposed method is empirically validated across multiple datasets, demonstrating notable enhancements in precision and efficiency for question-answering tasks. It outperforms existing baselines and showcases the synergistic effects of combining contrastive and consistency learning paradigms within the retrieval-augmented generation framework.

cs.CL↗

arXiv2024

MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results

The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the scarcity of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). Building on the achievements of the previous MIPI Workshops held at ECCV 2022 and CVPR 2023, we introduce our third MIPI challenge including three tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Nighttime Flare Removal track on MIPI 2024. In total, 170 participants were successfully registered, and 14 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2024/.

cs.CV↗

arXiv2024

Beware of Overestimated Decoding Performance Arising from Temporal Autocorrelations in Electroencephalogram Signals

Researchers have reported high decoding accuracy (>95%) using non-invasive Electroencephalogram (EEG) signals for brain-computer interface (BCI) decoding tasks like image decoding, emotion recognition, auditory spatial attention detection, etc. Since these EEG data were usually collected with well-designed paradigms in labs, the reliability and robustness of the corresponding decoding methods were doubted by some researchers, and they argued that such decoding accuracy was overestimated due to the inherent temporal autocorrelation of EEG signals. However, the coupling between the stimulus-driven neural responses and the EEG temporal autocorrelations makes it difficult to confirm whether this overestimation exists in truth. Furthermore, the underlying pitfalls behind overestimated decoding accuracy have not been fully explained due to a lack of appropriate formulation. In this work, we formulate the pitfall in various EEG decoding tasks in a unified framework. EEG data were recorded from watermelons to remove stimulus-driven neural responses. Labels were assigned to continuous EEG according to the experimental design for EEG recording of several typical datasets, and then the decoding methods were conducted. The results showed the label can be successfully decoded as long as continuous EEG data with the same label were split into training and test sets. Further analysis indicated that high accuracy of various BCI decoding tasks could be achieved by associating labels with EEG intrinsic temporal autocorrelation features. These results underscore the importance of choosing the right experimental designs and data splits in BCI decoding tasks to prevent inflated accuracies due to EEG temporal autocorrelation.

eess.SP↗

arXiv2024

Spin Hamiltonians in the Modulated Momenta of Light

Photonic solvers that are able to find the ground states of different spin Hamiltonians can be used to study many interactive physical systems and combinatorial optimization problems. Here, we establish a real-and-momentum space correspondence of spin Hamiltonians by spatial light transport. The real-space spin interaction is determined by modulating the momentum-space flow of light. This principle is formulated as a generalized Plancherel theorem, allowing us to implement a simple optical simulator that can find the ground states for any displacement-dependent spin interactions. Particularly, we use this principle to reveal the exotic magnetic phase diagram from a J1-J2-J3 model, and we also observe the vortex-mediated Berezinskii-Kosterlitz-Thouless dynamics from the XY model. These experiments exhibit high calculation precision by subtly controlling spin interactions from the momentum space of light, offering a promising scheme to explore novel physical effects.

physics.optics↗

arXiv2024

Light curves of the explosion of ONe WD+CO WD merger remnant and type Icn supernovae

Type Icn supernovae (SNe Icn) are a newly detected rare subtype of interacting stripped-envelope supernovae which show narrow P-Cygni lines of highly ionized carbon, oxygen, and neon in their early spectra due to the interactions of the SNe ejecta with dense hydrogen- and helium-deficient circumstellar material (CSM). It has been suggested that SNe Icn may have multiple progenitor channels, such as the explosion of carbon-rich Wolf-Rayet stars, or the explosion of stripped-envelope SNe which undergo binary interactions. Among the SNe Icn, SN 2019jc shows unique properties, and previous work inferred that it may stem from the ultra-stripped supernova, but other possibilities still exist. In this work, we aim to simulate the light curves from the explosions of oxygen-neon and carbon-oxygen double white dwarf (WD) merger remnants, and to further investigate whether the corresponding explosions can appear as some particular SNe Icn. We generate the light curves from the explosive remnants and analyse the influence of different parameters on the light curves, such as the ejecta mass, explosion energy, mass of Ni56 and CSM properties. Comparing our results with some SNe Icn, we found that the light curves from the explosions of double WD merger remnants can explain the observable properties of SN 2019jc, which inferred that this special SN Icn may have a different progenitor. Our results indicated that double WD merger may be an alternative model in producing at least one of the SNe Icn.

astro-ph.HE↗

arXiv2024

Training-free Subject-Enhanced Attention Guidance for Compositional Text-to-image Generation

Existing subject-driven text-to-image generation models suffer from tedious fine-tuning steps and struggle to maintain both text-image alignment and subject fidelity. For generating compositional subjects, it often encounters problems such as object missing and attribute mixing, where some subjects in the input prompt are not generated or their attributes are incorrectly combined. To address these limitations, we propose a subject-driven generation framework and introduce training-free guidance to intervene in the generative process during inference time. This approach strengthens the attention map, allowing for precise attribute binding and feature injection for each subject. Notably, our method exhibits exceptional zero-shot generation ability, especially in the challenging task of compositional generation. Furthermore, we propose a novel metric GroundingScore to evaluate subject alignment thoroughly. The obtained quantitative results serve as compelling evidence showcasing the effectiveness of our proposed method. The code will be released soon.

cs.CV↗

arXiv2024

EVA-X: A Foundation Model for General Chest X-ray Analysis with Self-supervised Learning

The diagnosis and treatment of chest diseases play a crucial role in maintaining human health. X-ray examination has become the most common clinical examination means due to its efficiency and cost-effectiveness. Artificial intelligence analysis methods for chest X-ray images are limited by insufficient annotation data and varying levels of annotation, resulting in weak generalization ability and difficulty in clinical dissemination. Here we present EVA-X, an innovative foundational model based on X-ray images with broad applicability to various chest disease detection tasks. EVA-X is the first X-ray image based self-supervised learning method capable of capturing both semantic and geometric information from unlabeled images for universal X-ray image representation. Through extensive experimentation, EVA-X has demonstrated exceptional performance in chest disease analysis and localization, becoming the first model capable of spanning over 20 different chest diseases and achieving leading results in over 11 different detection tasks in the medical field. Additionally, EVA-X significantly reduces the burden of data annotation in the medical AI field, showcasing strong potential in the domain of few-shot learning. The emergence of EVA-X will greatly propel the development and application of foundational medical models, bringing about revolutionary changes in future medical research and clinical practice. Our codes and models are available at: https://github.com/hustvl/EVA-X.

cs.CV↗

arXiv2024

Boosting Single Positive Multi-label Classification with Generalized Robust Loss

Multi-label learning (MLL) requires comprehensive multi-semantic annotations that is hard to fully obtain, thus often resulting in missing labels scenarios. In this paper, we investigate Single Positive Multi-label Learning (SPML), where each image is associated with merely one positive label. Existing SPML methods only focus on designing losses using mechanisms such as hard pseudo-labeling and robust losses, mostly leading to unacceptable false negatives. To address this issue, we first propose a generalized loss framework based on expected risk minimization to provide soft pseudo labels, and point out that the former losses can be seamlessly converted into our framework. In particular, we design a novel robust loss based on our framework, which enjoys flexible coordination between false positives and false negatives, and can additionally deal with the imbalance between positive and negative samples. Extensive experiments show that our approach can significantly improve SPML performance and outperform the vast majority of state-of-the-art methods on all the four benchmarks.

cs.LG↗

arXiv2024

Positivity of the Hypergeometric Coon Amplitude

We utilize a novel method for the partial-wave unitarity recently suggested in [1] to analyse the hypergeometric Coon amplitude. In this approach we use a new type of harmonic numbers as a basis. Owing to the properties of the harmonic numbers this method bypasses lots of difficulties and can be used to derive a clear and unified form for the partial-wave coefficients. This new approach further streamlines the partial-wave unitarity analysis. As an instance, we re-derive the unitarity bounds from Regge trajectory analysis and find the new critical condition of the hypergeometric Coon amplitude. Our new method also benefits the discussion on the various limits of this amplitude. Specifically, we demonstrate the manifest positivity of super string below $d\leq10$ from our new perspective.

hep-th↗