arXiv subjects

Liu Bo

Publications and source records attributed to Liu Bo.

10 recordsLinked to original sources

arXiv2026

The 2026 Singapore Consensus on Global AI Safety Research Priorities

Frontier AI capabilities and autonomy are advancing rapidly. A growing number of real-world incidents make a trusted AI ecosystem essential to embracing AI with confidence. The 2026 Singapore Consensus is an outcome of the second International Scientific Exchange on AI Safety, bringing together over 100 contributors spanning 13 countries from frontier developers, government safety institutes, academia, and civil society. Building on the 2025 report, it presents a global understanding of technical AI safety research problems of top priority, now with a dedicated focus on societal resilience and on managing the risks of increasingly autonomous AI agents.

cs.CY↗

arXiv2023

Motion State: A New Benchmark Multiple Object Tracking

In the realm of video analysis, the field of multiple object tracking (MOT) assumes paramount importance, with the motion state of objects-whether static or dynamic relative to the ground-holding practical significance across diverse scenarios. However, the extant literature exhibits a notable dearth in the exploration of this aspect. Deep learning methodologies encounter challenges in accurately discerning object motion states, while conventional approaches reliant on comprehensive mathematical modeling may yield suboptimal tracking accuracy. To address these challenges, we introduce a Model-Data-Driven Motion State Judgment Object Tracking Method (MoD2T). This innovative architecture adeptly amalgamates traditional mathematical modeling with deep learning-based multi-object tracking frameworks. The integration of mathematical modeling and deep learning within MoD2T enhances the precision of object motion state determination, thereby elevating tracking accuracy. Our empirical investigations comprehensively validate the efficacy of MoD2T across varied scenarios, encompassing unmanned aerial vehicle surveillance and street-level tracking. Furthermore, to gauge the method's adeptness in discerning object motion states, we introduce the Motion State Validation F1 (MVF1) metric. This novel performance metric aims to quantitatively assess the accuracy of motion state classification, furnishing a comprehensive evaluation of MoD2T's performance. Elaborate experimental validations corroborate the rationality of MVF1. In order to holistically appraise MoD2T's performance, we meticulously annotate several renowned datasets and subject MoD2T to stringent testing. Remarkably, under conditions characterized by minimal or moderate camera motion, the achieved MVF1 values are particularly noteworthy, with exemplars including 0.774 for the KITTI dataset, 0.521 for MOT17, and 0.827 for UAVDT.

cs.CV↗

arXiv2022

A Creative Industry Image Generation Dataset Based on Captions

Most image generation methods are difficult to precisely control the properties of the generated images, such as structure, scale, shape, etc., which limits its large-scale application in creative industries such as conceptual design and graphic design, and so on. Using the prompt and the sketch is a practical solution for controllability. Existing datasets lack either prompt or sketch and are not designed for the creative industry. Here is the main contribution of our work. a) This is the first dataset that covers the 4 most important areas of creative industry domains and is labeled with prompt and sketch. b) We provide multiple reference images in the test set and fine-grained scores for each reference which are useful for measurement. c) We apply two state-of-the-art models to our dataset and then find some shortcomings, such as the prompt is more highly valued than the sketch.

cs.CV↗

arXiv2022

Towards Micro-video Thumbnail Selection via a Multi-label Visual-semantic Embedding Model

The thumbnail, as the first sight of a micro-video, plays a pivotal role in attracting users to click and watch. While in the real scenario, the more the thumbnails satisfy the users, the more likely the micro-videos will be clicked. In this paper, we aim to select the thumbnail of a given micro-video that meets most users` interests. Towards this end, we present a multi-label visual-semantic embedding model to estimate the similarity between the pair of each frame and the popular topics that users are interested in. In this model, the visual and textual information is embedded into a shared semantic space, whereby the similarity can be measured directly, even the unseen words. Moreover, to compare the frame to all words from the popular topics, we devise an attention embedding space associated with the semantic-attention projection. With the help of these two embedding spaces, the popularity score of a frame, which is defined by the sum of similarity scores over the corresponding visual information and popular topic pairs, is achieved. Ultimately, we fuse the visual representation score and the popularity score of each frame to select the attractive thumbnail for the given micro-video. Extensive experiments conducted on a real-world dataset have well-verified that our model significantly outperforms several state-of-the-art baselines.

cs.IR↗

arXiv2021

A Benchmark Dataset for Micro-video Thumbnail Selection

The thumbnail, as the first sight of a micro-video, plays a pivotal role in attracting users to click and watch. Although several pioneer efforts have been dedicated to jointly considering the quality and representativeness for selecting the thumbnail, they are limited in exploring the influence of users` interests. While in the real scenario, the more the thumbnails satisfy the users, the more likely the micro-videos will be clicked. In this paper, we aim to select the thumbnail of a given micro-video that meets most users` interests. Towards this end, we construct a large-scale dataset for the micro-video thumbnails. Ultimately, we conduct several baselines on the dataset and demonstrate the effectiveness of our dataset.

cs.IR↗

arXiv2021

Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning

Transductive zero-shot learning (T-ZSL) which could alleviate the domain shift problem in existing ZSL works, has received much attention recently. However, an open problem in T-ZSL: how to effectively make use of unseen-class samples for training, still remains. Addressing this problem, we first empirically analyze the roles of unseen-class samples with different degrees of hardness in the training process based on the uneven prediction phenomenon found in many ZSL methods, resulting in three observations. Then, we propose two hardness sampling approaches for selecting a subset of diverse and hard samples from a given unseen-class dataset according to these observations. The first one identifies the samples based on the class-level frequency of the model predictions while the second enhances the former by normalizing the class frequency via an approximate class prior estimated by an explored prior estimation algorithm. Finally, we design a new Self-Training framework with Hardness Sampling for T-ZSL, called STHS, where an arbitrary inductive ZSL method could be seamlessly embedded and it is iteratively trained with unseen-class samples selected by the hardness sampling approach. We introduce two typical ZSL methods into the STHS framework and extensive experiments demonstrate that the derived T-ZSL methods outperform many state-of-the-art methods on three public benchmarks. Besides, we note that the unseen-class dataset is separately used for training in some existing transductive generalized ZSL (T-GZSL) methods, which is not strict for a GZSL task. Hence, we suggest a more strict T-GZSL data setting and establish a competitive baseline on this setting by introducing the proposed STHS framework to T-GZSL.

cs.CV↗

arXiv2016

Exciton-plasmon Coupling and Electromagnetically Induced Transparency in Monolayer Semiconductors Hybridized with Ag Nanoparticles

Hybrid systems of excitons strongly coupled to localized surface plasmons supported by metallic nanoparticles define a new approach to control light-matter interactions. Here, we report exciton-plasmon coupling in two-dimensional (2D) semiconductors, such as MoS2 and WS2, hybridized with silver nanoparticles. Prominent photoluminescence enhancement in monolayer MoS2 was observed with localized surface plasmon resonance (LSPR) tuned to the exciton resonance. By tuning the excitation energy, the contributions from near field enhancement and radiative emission rate enhancement via Purcell effect were resolved. Strong coherent dipole-dipole coupling between excitons and LSPR in resonant condition manifests as an electromagnetically induced transparency window in the extinction spectra of the localized surface plasmon. In this strong coupling regime a new quasi-particle, known as a plexciton, is expected to exhibit distinct properties, which exist in neither of the original particles. Our results demonstrate that 2D semiconductors hybridized with plasmonic structures not only hold great promise in the applications of energy-harvesting and light-emitting devices, but also provide an attractive platform for fundamental investigations of exciton-plasmon interactions in the strong coupling regime.

physics.optics↗

arXiv2013

Consensus in continuous-time multi-agent systems under discontinuous nonlinear protocols

In this paper, we provide a theoretical analysis for nonlinear discontinuous consensus protocols in networks of multiagents over weighted directed graphs. By integrating the analytic tools from nonsmooth stability analysis and graph theory, we investigate networks with both fixed topology and randomly switching topology. For networks with a fixed topology, we provide a sufficient and necessary condition for asymptotic consensus, and the consensus value can be explicitly calculated. As to networks with switching topologies, we provide a sufficient condition for the network to realize consensus almost surely. Particularly, we consider the case that the switching sequence is independent and identically distributed. As applications of the theoretical results, we introduce a generalized blinking model and show that consensus can be realized almost surely under the proposed protocols. Numerical simulations are also provided to illustrate the theoretical results.

math.OC↗

arXiv2008

Isospin Dynamics in Heavy Ion Collisions: from Coulomb Barrier to Quark Gluon Plasma

Heavy Ion Collisions (HIC) represent a unique tool to probe the in-medium nuclear interaction in regions away from saturation. In this report we present a selection of new reaction observables in dissipative collisions particularly sensitive to the symmetry term of the nuclear Equation of State (Iso-EoS). We will first discuss the Isospin Equilibration Dynamics. At low energies this manifests via the recently observed Dynamical Dipole Radiation, due to a collective neutron-proton oscillation with the symmetry term acting as a restoring force. At higher beam energies Iso-EoS effects will be seen in Imbalance Ratio Measurements, in particular from the correlations with the total kinetic energy loss. For fragmentation reactions in central events we suggest to look at the coupling between isospin distillation and radial flow. In Neck Fragmentation reactions important $Iso-EoS$ information can be obtained from the correlation between isospin content and alignement. The high density symmetry term can be probed from isospin effects on heavy ion reactions at relativistic energies (few AGeV range). Rather isospin sensitive observables are proposed from nucleon/cluster emissions, collective flows and meson production. The possibility to shed light on the controversial neutron/proton effective mass splitting in asymmetric matter is also suggested. A large symmetry repulsion at high baryon density will also lead to an "earlier" hadron-deconfinement transition in n-rich matter. A suitable treatment of the isovector interaction in the partonic EoS appears very relevant.

nucl-th↗

arXiv2007

Isospin Effects on Meson Production in Relativistic Heavy Ion Collisions

We show that the phenomenology of isospin effects on heavy ion reactions at intermediate energies (few AGeV range) is extremely rich and can allow a ``direct'' study of the covariant structure of the isovector interaction in a high density hadron medium. We work within a relativistic transport frame, beyond a cascade picture, consistently derived from effective Lagrangians, where isospin effects are accounted for in the mean field and collision terms. We show that rather sensitive observables are provided by the pion/kaon production (π^-/π^+, K^0/K^+ yields). Relevant non-equilibrium effects are stressed. The possibility of the transition to a mixed hadron-quark phase, at high baryon and isospin density, is finally suggested. Some signatures could come from an expected ``neutron trapping'' effect.

nucl-th↗