arXiv subjects

Shaojun Tang

Publications and source records attributed to Shaojun Tang.

11 recordsLinked to original sources

arXiv2025

Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience

Autonomous AI is no longer a hard-to-reach concept, it enables the agents to move beyond executing tasks to independently addressing complex problems, adapting to change while handling the uncertainty of the environment. However, what makes the agents truly autonomous? It is agentic reasoning, that is crucial for foundation models to develop symbolic logic, statistical correlations, or large-scale pattern recognition to process information, draw inferences, and make decisions. However, it remains unclear why and how existing agentic reasoning approaches work, in comparison to biological reasoning, which instead is deeply rooted in neural mechanisms involving hierarchical cognition, multimodal integration, and dynamic interactions. In this work, we propose a novel neuroscience-inspired framework for agentic reasoning. Grounded in three neuroscience-based definitions and supported by mathematical and biological foundations, we propose a unified framework modeling reasoning from perception to action, encompassing four core types, perceptual, dimensional, logical, and interactive, inspired by distinct functional roles observed in the human brain. We apply this framework to systematically classify and analyze existing AI reasoning methods, evaluating their theoretical foundations, computational designs, and practical limitations. We also explore its implications for building more generalizable, cognitively aligned agents in physical and virtual environments. Finally, building on our framework, we outline future directions and propose new neural-inspired reasoning methods, analogous to chain-of-thought prompting. By bridging cognitive neuroscience and AI, this work offers a theoretical foundation and practical roadmap for advancing agentic reasoning in intelligent systems. The associated project can be found at: https://github.com/BioRAILab/Awesome-Neuroscience-Agent-Reasoning .

q-bio.NC↗

arXiv2025

HiCMamba: Enhancing Hi-C Resolution and Identifying 3D Genome Structures with State Space Modeling

Hi-C technology measures genome-wide interaction frequencies, providing a powerful tool for studying the 3D genomic structure within the nucleus. However, high sequencing costs and technical challenges often result in Hi-C data with limited coverage, leading to imprecise estimates of chromatin interaction frequencies. To address this issue, we present a novel deep learning-based method HiCMamba to enhance the resolution of Hi-C contact maps using a state space model. We adopt the UNet-based auto-encoder architecture to stack the proposed holistic scan block, enabling the perception of both global and local receptive fields at multiple scales. Experimental results demonstrate that HiCMamba outperforms state-of-the-art methods while significantly reducing computational resources. Furthermore, the 3D genome structures, including topologically associating domains (TADs) and loops, identified in the contact maps recovered by HiCMamba are validated through associated epigenomic features. Our work demonstrates the potential of a state space model as foundational frameworks in the field of Hi-C resolution enhancement.

cs.CV↗

arXiv2024

Rene: A Pre-trained Multi-modal Architecture for Auscultation of Respiratory Diseases

Compared with invasive examinations that require tissue sampling, respiratory sound testing is a non-invasive examination method that is safer and easier for patients to accept. In this study, we introduce Rene, a pioneering large-scale model tailored for respiratory sound recognition. Rene has been rigorously fine-tuned with an extensive dataset featuring a broad array of respiratory audio samples, targeting disease detection, sound pattern classification, and event identification. Our innovative approach applies a pre-trained speech recognition model to process respiratory sounds, augmented with patient medical records. The resulting multi-modal deep-learning framework addresses interpretability and real-time diagnostic challenges that have hindered previous respiratory-focused models. Benchmark comparisons reveal that Rene significantly outperforms existing models, achieving improvements of 10.27%, 16.15%, 15.29%, and 18.90% in respiratory event detection and audio classification on the SPRSound database. Disease prediction accuracy on the ICBHI database improved by 23% over the baseline in both mean average and harmonic scores. Moreover, we have developed a real-time respiratory sound discrimination system utilizing the Rene architecture. Employing state-of-the-art Edge AI technology, this system enables rapid and accurate responses for respiratory sound auscultation(https://github.com/zpforlove/Rene).

cs.SD↗

arXiv2022

Grad-Caflisch pointwise decay estimates revisited

In the influential paper \cite{Caflish-1980-CPAM} which was the starting point of the employment of Hilbert expansion method to the rigorous justifications of the fluid limits of the Boltzmann equation, Caflisch discovered an elegant and crucial estimate on each expansion term (Proposition 3.1 in \cite{Caflish-1980-CPAM}). The proof essentially relied on an estimate of Grad \cite{Grad-1963}, which was on the pointwise decay properties of $\mathcal{L}^{-1}$, the pseudo-inverse operator of the linearized Boltzmann collision operator $\mathcal{L}$, for the hard potential collision kernel, i.e. the power $0\leq \gamma\leq 1$. Caflisch's arguments need the exponential version of Grad's estimate. However, Grad's original paper was only on the polynomial decay. In this paper, we revisit and provide a full proof of the Caflisch-Grad type decay estimates and the corresponding applications in the compressible Euler limit of the Boltzmann equaiton. The main novelty is that for the case collision kernel power $-\frac{3}{2}<\gamma\leq 1$, the proof of the pointwise estimate does not use any derivatives. So the potential applications of this estimate could be wider than in the Hilbert expansion. For the completeness of the result, we also prove the almost everywhere pointwise estimate using derivatives for the case $-3<\gamma\leq -\frac{3}{2}$. Furthermore, in the application to fluid limits, $\mathcal{L}^{-1}$ and the derivatives with respect to the parameters (for example, $(t,x)$, this must happen when $\mathcal{L}$ is linearized around local Maxwellian which depends on $(t,x)$) are not commutative. We detailed analyze the estimate of commutators, which was missing in previous literatures of fluid limits of the Boltzmann equation. This estimate is needed in all compressible fluid limits from Boltzmann equation.

math.AP↗

arXiv2021

Compressible Euler limit from Boltzmann equation with complete diffusive boundary condition in half-space

In this paper, we prove the compressible Euler limit from the Boltzmann equation with hard sphere collisional kernel and complete diffusive boundary condition in half-space by employing the Hilbert expansion which includes interior and Knudsen layers. This rigorously justifies the corresponding formal analysis in Sone's book \cite{Sone-2007-Book} in the context of short time smooth solutions, and also generalizes the classic Caflisch's result \cite{Caflish-1980-CPAM} to initial-boundary problem case.

math.AP↗

arXiv2021

Compressible Euler limit from Boltzmann equation with Maxwell reflection boundary condition in half-space

Starting from the local-in-time classical solution to the compressible Euler system with impermeable boundary condition in half-space, by employing the coupled weak viscous layers (governed by linearized compressible Prandtl equations with Robin boundary condition) and linear kinetic boundary layers, and the analytical tools in \cite{Guo-Jang-Jiang-2010-CPAM} and some new boundary estimates both for Prandtl and Knudsen layers, we proved the local-in-time existence of Hilbert expansion type classical solutions to the scaled Boltzmann equation with Maxwell reflection boundary condition with accommodation coefficient $\alpha_\varepsilon=O(\sqrt{\varepsilon})$ when the Knudsen number $\varepsilon$ small enough. As a consequence, this justifies the corresponding case of formal analysis in Sone's books \cite{Sone-2002book, Sone-2007-Book}. This also extends the results in \cite{GHW-2020} from specular to Maxwell reflection boundary condition. Both of this paper and \cite{GHW-2020} can be viewed as generalizations of Caflisch's classic work \cite{Caflish-1980-CPAM} to the cases with boundary.

math.AP↗

arXiv2020

Entropy inequality and energy dissipation of inertial Qian-Sheng model for nematic liquid crystals

For the inertial Qian-Sheng model of nematic liquid crystals in the $Q$-tensor framework, we illustrate the roles played by the entropy inequality and energy dissipation in the well-posedness of smooth solutions when we employ energy method. We first derive the coefficients requirements from the entropy inequality, and point out the entropy inequality is insufficient to guarantee energy dissipation. We then introduce a novel Condition (H) which ensures the energy dissipation. We prove that when both the entropy inequality and Condition (H) are obeyed, the local in time smooth solutions exist for large initial data. Otherwise, we can only obtain small data local solutions. Furthermore, to extend the solutions globally in time and obtain the decay of solutions, we require at least one of the two conditions: entropy inequality, or $\tilde{\mu}_2= \mu_2$, which significantly enlarge the range of the coefficients in previous works.

math.AP↗

arXiv2019

Incompressible limit of the Ericksen-Leslie hyperbolic liquid crystal model in compressible flow

Ericksen and Leslie proposed a hydrodynamic model for liquid crystals in the format of conservation laws in the 1960s. Their original model includes inertial and compressibility effects, which makes the model a coupled parabolic-hyperbolic system. In this paper we build up the connection between the compressible and incompressible parabolic-hyperbolic liquid crystal model in the framework of classical solutions. We first derive the scaled Ericksen-Leslie system with dimensionless numbers, including Mach, Reynolds, and Ericksen numbers. In particular, we introduce the so-called inertial constant $\chi$ which characterizes the inertial effect of the liquid crystal molecular. Next, we establish the energy estimates uniform in the Mach number $\epsilon$ for both the compressible system and its time-derivative system with small data. Then, we pass to the limit $\epsilon \rightarrow 0$ in the compressible system, so that we establish the global classical solution of the incompressible system by the compactness arguments. Moreover, we also obtain the convergence rates associated with $L^2$-norm in the case of well-prepared initial data. This is the first result on the incompressible limit of the compressible parabolic-hyperbolic liquid crystal model and confirms the relations of different parabolic-hyperbolic liquid crystal model rigorously.

math.AP↗

arXiv2018

A scaling limit from the wave map to the heat flow into $\mathbb{S}^2$

In this paper we study a limit connecting a scaled wave map with the heat flow into the unit sphere $\mathbb{S}^2$. We show quantitatively how that the two equations are connected by means of an initial layer correction. This limit is motivated as a first step into understanding the limit of zero inertia for the hyperbolic-parabolic Ericksen-Leslie's liquid crystal model.

math.AP↗

arXiv2017

On well-posedness of Ericksen-Leslie's parabolic-hyperbolic liquid crystal model in compressible flow

We study the Ericksen-Leslie's parabolic-hyperbolic liquid crystal model in compressible flow. Inspired by our study for incompressible case \cite{Jiang-Luo-arXiv-2017} and some techniques from compressible Navier-Stokes equations, we prove the local-in-time existence of the classical solution to the system with finite initial energy, under some constraints on the Leslie coefficients which ensure the basic energy law is dissipative. Furthermore, with an additional assumption on the coefficients which provides a damping effect, and the smallness of the initial energy, the global classical solution can be established.

math.AP↗

arXiv2017

Asymptotic stability of viscous contact wave and rarefaction waves for the system of heat-conductive ideal gas without viscosity

This paper is concerned with the Cauchy problem of heat-conductive ideal gas without viscosity. We show that, for the non-viscous case, if the strengths of the wave patterns and the initial perturbation are suitably small, the unique global-in-time solution exists and asymptotically tends toward the corresponding the viscous contact wave or the composition of a viscous contact wave with rarefaction waves determined by the initial condition, which extended the results by Huang-Li-Matsumura[13], where they treated the viscous and heat-conductive ideal gas.

math.AP↗