arXiv subjects

Yanbo Zhang

Publications and source records attributed to Yanbo Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Trichotomy and $tK_m$-goodness of sparse graphs

Let $G$ be a connected graph with $n$ vertices and $n+k-2$ edges and $tK_m$ denote the disjoint union of $t$ complete graphs $K_m$. In this paper, by developing a trichotomy for sparse graphs, we show that for given integers $m\ge 2$ and $t\ge 1$, there exists a positive constant $c$ such that if $1\le k\le cn^{\frac{2}{m-1}}$ and $n$ is large, then $G$ is $tK_m$-good, that is, the Ramsey number is \[ r(G, tK_m)=(n-1)(m-1)+t\,. \] In particular, the above equality holds for any positive integers $k$, $m$, and $t$, provided $n$ is large. The case $t=1$ was obtained by Burr, Erdős, Faudree, Rousseau, and Schelp (1980), and the case $k=1$ was established by Luo and Peng (2023).

math.CO↗

arXiv2025

Senti-iFusion: An Integrity-centered Hierarchical Fusion Framework for Multimodal Sentiment Analysis under Uncertain Modality Missingness

Multimodal Sentiment Analysis (MSA) is critical for human-computer interaction but faces challenges when the modalities are incomplete or missing. Existing methods often assume pre-defined missing modalities or fixed missing rates, limiting their real-world applicability. To address this challenge, we propose Senti-iFusion, an integrity-centered hierarchical fusion framework capable of handling both inter- and intra-modality missingness simultaneously. It comprises three hierarchical components: Integrity Estimation, Integrity-weighted Completion, and Integrity-guided Fusion. First, the Integrity Estimation module predicts the completeness of each modality and mitigates the noise caused by incomplete data. Second, the Integrity-weighted Cross-modal Completion module employs a novel weighting mechanism to disentangle consistent semantic structures from modality-specific representations, enabling the precise recovery of sentiment-related features across language, acoustic, and visual modalities. To ensure consistency in reconstruction, a dual-depth validation with semantic- and feature-level losses ensures consistent reconstruction at both fine-grained (low-level) and semantic (high-level) scales. Finally, the Integrity-guided Adaptive Fusion mechanism dynamically selects the dominant modality for attention-based fusion, ensuring that the most reliable modality, based on completeness and quality, contributes more significantly to the final prediction. Senti-iFusion employs a progressive training approach to ensure stable convergence. Experimental results on popular MSA datasets demonstrate that Senti-iFusion outperforms existing methods, particularly in fine-grained sentiment analysis tasks. The code and our proposed Senti-iFusion model will be publicly available.

cs.HC↗

arXiv2025

Three-color online Ramsey numbers $\tilde{r}(P_3,P_3,P_{\ell})$ and $\tilde{r}(P_3, P_3, C_{\ell})$

For given graphs $G_1, \ldots, G_k$, let $\tilde{r}(G_1, \ldots, G_k)$ denote their online Ramsey number. In an influential paper on the online Ramsey numbers for paths and cycles, Cyman, Dzido, Lapinskas, and Lo (Electron. J. Combin., 2015) determined the exact values of $\tilde{r}(P_3, P_{\ell})$ and $\tilde{r}(P_3, C_{\ell})$. They also conjectured the exact value of $\tilde{r}(P_4, P_{\ell})$ and the limit of $\tilde{r}(P_k, P_{\ell})/\ell$ as $\ell \to \infty$ for $k \ge 5$. The former conjecture was independently confirmed by Bednarska-Bzdȩga (European J. Combin., 2024) and Y.B. Zhang and Y.X. Zhang (arXiv:2302.13640), while the latter was disproved by Mond and Portier (European J. Combin., 2024). In this paper, we extend this line of research to the three-color setting and establish the exact value of $\tilde{r}(P_3,P_3,P_{\ell})$ for $\ell\ge 2$ and $\tilde{r}(P_3, P_3, C_{\ell})$ for $\ell \ge 16$.

math.CO↗

arXiv2025

Equilibrium flow: From Snapshots to Dynamics

Scientific data, from cellular snapshots in biology to celestial distributions in cosmology, often consists of static patterns from underlying dynamical systems. These snapshots, while lacking temporal ordering, implicitly encode the processes that preserve them. This work investigates how strongly such a distribution constrains its underlying dynamics and how to recover them. We introduce the Equilibrium flow method, a framework that learns continuous dynamics that preserve a given pattern distribution. Our method successfully identifies plausible dynamics for 2-D systems and recovers the signature chaotic behavior of the Lorenz attractor. For high-dimensional Turing patterns from the Gray-Scott model, we develop an efficient, training-free variant that achieves high fidelity to the ground truth, validated both quantitatively and qualitatively. Our analysis reveals the solution space is constrained not only by the data but also by the learning model's inductive biases. This capability extends beyond recovering known systems, enabling a new paradigm of inverse design for Artificial Life. By specifying a target pattern distribution, we can discover the local interaction rules that preserve it, leading to the spontaneous emergence of complex behaviors, such as life-like flocking, attraction, and repulsion patterns, from simple, user-defined snapshots.

cs.LG↗

arXiv2025

Ramsey goodness of stars and fans for the Hajós graph

Given two graphs $G_1$ and $G_2$, the Ramsey number $R(G_1,G_2)$ denotes the smallest integer $N$ such that any red-blue coloring of the edges of $K_N$ contains either a red $G_1$ or a blue $G_2$. Let $G_1$ be a graph with chromatic number $χ$ and chromatic surplus $s$, and let $G_2$ be a connected graph with $n$ vertices. The graph $G_2$ is said to be Ramsey-good for the graph $G_1$ (or simply $G_1$-good) if, for $n \ge s$, \[R(G_1,G_2)=(χ-1)(n-1)+s.\] The $G_1$-good property has been extensively studied for star-like graphs when $G_1$ is a graph with $χ(G_1)\ge 3$, as seen in works by Burr-Faudree-Rousseau-Schelp (J. Graph Theory, 1983), Li-Rousseau (J. Graph Theory, 1996), Lin-Li-Dong (European J. Combin., 2010), Fox-He-Wigderson (Adv. Combin., 2023), and Liu-Li (J. Graph Theory, 2025), among others. However, all prior results require $G_1$ to have chromatic surplus $1$. In this paper, we extend this investigation to graphs with chromatic surplus 2 by considering the Hajós graph $H_a$. For a star $K_{1,n}$, we prove that $K_{1,n}$ is $H_a$-good if and only if $n$ is even. For a fan $F_n$ with $n\ge 111$, we prove that $F_n$ is $H_a$-good.

math.CO↗

arXiv2025

ZapGPT: Free-form Language Prompting for Simulated Cellular Control

Human language is one of the most expressive tools for conveying intent, yet most artificial or biological systems lack mechanisms to interpret or respond meaningfully to it. Bridging this gap could enable more natural forms of control over complex, decentralized systems. In AI and artificial life, recent work explores how language can specify high-level goals, but most systems still depend on engineered rewards, task-specific supervision, or rigid command sets, limiting generalization to novel instructions. Similar constraints apply in synthetic biology and bioengineering, where the locus of control is often genomic rather than environmental perturbation. A key open question is whether artificial or biological collectives can be guided by free-form natural language alone, without task-specific tuning or carefully designed evaluation metrics. We provide one possible answer here by showing, for the first time, that simple agents' collective behavior can be guided by free-form language prompts: one AI model transforms an imperative prompt into an intervention that is applied to simulated cells; a second AI model scores how well the prompt describes the resulting cellular dynamics; and the former AI model is evolved to improve the scores generated by the latter. Unlike previous work, our method does not require engineered fitness functions or domain-specific prompt design. We show that the evolved system generalizes to unseen prompts without retraining. By treating natural language as a control layer, the system suggests a future in which spoken or written prompts could direct computational, robotic, or biological systems to desired behaviors. This work provides a concrete step toward this vision of AI-biology partnerships, in which language replaces mathematical objective functions, fixed rules, and domain-specific programming.

cs.AI↗

arXiv2025

Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answers

Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and problem-solving across various domains. However, their ability to perform complex, multi-step reasoning task-essential for applications in science, medicine, and law-remains an area of active investigation. This paper examines the reasoning capabilities of contemporary LLMs, analyzing their strengths, limitations, and potential for improvement. The study uses prompt engineering techniques on the Graduate-Level GoogleProof Q&A (GPQA) dataset to assess the scientific reasoning of GPT-4o. Five popular prompt engineering techniques and two tailored promptings were tested: baseline direct answer (zero-shot), chain-of-thought (CoT), zero-shot CoT, self-ask, self-consistency, decomposition, and multipath promptings. Our findings indicate that while LLMs exhibit emergent reasoning abilities, they often rely on pattern recognition rather than true logical inference, leading to inconsistencies in complex problem-solving. The results indicated that self-consistency outperformed the other prompt engineering technique with an accuracy of 52.99%, followed by direct answer (52.23%). Zero-shot CoT (50%) outperformed multipath (48.44%), decomposition (47.77%), self-ask (46.88%), and CoT (43.75%). Self-consistency performed the second worst in explaining the answers. Simple techniques such as direct answer, CoT, and zero-shot CoT have the best scientific reasoning. We propose a research agenda aimed at bridging these gaps by integrating structured reasoning frameworks, hybrid AI approaches, and human-in-the-loop methodologies. By critically evaluating the reasoning mechanisms of LLMs, this paper contributes to the ongoing discourse on the future of artificial general intelligence and the development of more robust, trustworthy AI systems.

cs.AI↗

arXiv2025

Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery

With recent Nobel Prizes recognising AI contributions to science, Large Language Models (LLMs) are transforming scientific research by enhancing productivity and reshaping the scientific method. LLMs are now involved in experimental design, data analysis, and workflows, particularly in chemistry and biology. However, challenges such as hallucinations and reliability persist. In this contribution, we review how Large Language Models (LLMs) are redefining the scientific method and explore their potential applications across different stages of the scientific cycle, from hypothesis testing to discovery. We conclude that, for LLMs to serve as relevant and effective creative engines and productivity enhancers, their deep integration into all steps of the scientific process should be pursued in collaboration and alignment with human scientific goals, with clear evaluation metrics. The transition to AI-driven science raises ethical questions about creativity, oversight, and responsibility. With careful guidance, LLMs could evolve into creative engines, driving transformative breakthroughs across scientific disciplines responsibly and effectively. However, the scientific community must also decide how much it leaves to LLMs to drive science, even when associations with 'reasoning', mostly currently undeserved, are made in exchange for the potential to explore hypothesis and solution regions that might otherwise remain unexplored by human exploration alone.

cs.AI↗

arXiv2025

Estimating Quality in Therapeutic Conversations: A Multi-Dimensional Natural Language Processing Framework

Engagement between client and therapist is a critical determinant of therapeutic success. We propose a multi-dimensional natural language processing (NLP) framework that objectively classifies engagement quality in counseling sessions based on textual transcripts. Using 253 motivational interviewing transcripts (150 high-quality, 103 low-quality), we extracted 42 features across four domains: conversational dynamics, semantic similarity as topic alignment, sentiment classification, and question detection. Classifiers, including Random Forest (RF), Cat-Boost, and Support Vector Machines (SVM), were hyperparameter tuned and trained using a stratified 5-fold cross-validation and evaluated on a holdout test set. On balanced (non-augmented) data, RF achieved the highest classification accuracy (76.7%), and SVM achieved the highest AUC (85.4%). After SMOTE-Tomek augmentation, performance improved significantly: RF achieved up to 88.9% accuracy, 90.0% F1-score, and 94.6% AUC, while SVM reached 81.1% accuracy, 83.1% F1-score, and 93.6% AUC. The augmented data results reflect the potential of the framework in future larger-scale applications. Feature contribution revealed conversational dynamics and semantic similarity between clients and therapists were among the top contributors, led by words uttered by the client (mean and standard deviation). The framework was robust across the original and augmented datasets and demonstrated consistent improvements in F1 scores and recall. While currently text-based, the framework supports future multimodal extensions (e.g., vocal tone, facial affect) for more holistic assessments. This work introduces a scalable, data-driven method for evaluating engagement quality of the therapy session, offering clinicians real-time feedback to enhance the quality of both virtual and in-person therapeutic interactions.

cs.CL↗

arXiv2025

Giving Simulated Cells a Voice: Evolving Prompt-to-Intervention Models for Cellular Control

Guiding biological systems toward desired states, such as morphogenetic outcomes, remains a fundamental challenge with far-reaching implications for medicine and synthetic biology. While large language models (LLMs) have enabled natural language as an interface for interpretable control in AI systems, their use as mediators for steering biological or cellular dynamics remains largely unexplored. In this work, we present a functional pipeline that translates natural language prompts into spatial vector fields capable of directing simulated cellular collectives. Our approach combines a large language model with an evolvable neural controller (Prompt-to-Intervention, or P2I), optimized via evolutionary strategies to generate behaviors such as clustering or scattering in a simulated 2D environment. We demonstrate that even with constrained vocabulary and simplified cell models, evolved P2I networks can successfully align cellular dynamics with user-defined goals expressed in plain language. This work offers a complete loop from language input to simulated bioelectric-like intervention to behavioral output, providing a foundation for future systems capable of natural language-driven cellular control.

cs.AI↗

arXiv2025

Human vs. LLM-Based Thematic Analysis for Digital Mental Health Research: Proof-of-Concept Comparative Study

Thematic analysis provides valuable insights into participants' experiences through coding and theme development, but its resource-intensive nature limits its use in large healthcare studies. Large language models (LLMs) can analyze text at scale and identify key content automatically, potentially addressing these challenges. However, their application in mental health interviews needs comparison with traditional human analysis. This study evaluates out-of-the-box and knowledge-base LLM-based thematic analysis against traditional methods using transcripts from a stress-reduction trial with healthcare workers. OpenAI's GPT-4o model was used along with the Role, Instructions, Steps, End-Goal, Narrowing (RISEN) prompt engineering framework and compared to human analysis in Dedoose. Each approach developed codes, noted saturation points, applied codes to excerpts for a subset of participants (n = 20), and synthesized data into themes. Outputs and performance metrics were compared directly. LLMs using the RISEN framework developed deductive parent codes similar to human codes, but humans excelled in inductive child code development and theme synthesis. Knowledge-based LLMs reached coding saturation with fewer transcripts (10-15) than the out-of-the-box model (15-20) and humans (90-99). The out-of-the-box LLM identified a comparable number of excerpts to human researchers, showing strong inter-rater reliability (K = 0.84), though the knowledge-based LLM produced fewer excerpts. Human excerpts were longer and involved multiple codes per excerpt, while LLMs typically applied one code. Overall, LLM-based thematic analysis proved more cost-effective but lacked the depth of human analysis. LLMs can transform qualitative analysis in mental healthcare and clinical research when combined with human oversight to balance participant perspectives and research resources.

cs.HC↗

arXiv2025

Turán problems for suspension of a balanced tree

The Turán number $\ex(n,H)$ is the maximum number of edges that an $n$-vertex $H$-free graph can have. The suspension $\widehat{H}$ is obtained from $H$ by adding a new vertex which is adjacent to all vertices of $H$ and a tree is balanced if the sizes of its two color classes differ at most $1$. In this paper, we obtain a sharp bound of $\ex(n,\widehat{T})$ when $n\ge 4(4k)^6$ based on the Erdős-Sós conjecture. We also show the bound is sharp for infinitely many $n$ and characterize all extremal graphs. In particular, if $T$ satisfies some conditions such as $T$ contains a matching covering all vertices in one color class, then the bound is sharp for all $n$. This is a new class of graphs whose decomposition family does not contain a linear forest but we still can determine its Turán number.

math.CO↗

arXiv2025

A Non-contrast Head CT Foundation Model for Comprehensive Neuro-Trauma Triage

Recent advancements in AI and medical imaging offer transformative potential in emergency head CT interpretation for reducing assessment times and improving accuracy in the face of an increasing request of such scans and a global shortage in radiologists. This study introduces a 3D foundation model for detecting diverse neuro-trauma findings with high accuracy and efficiency. Using large language models (LLMs) for automatic labeling, we generated comprehensive multi-label annotations for critical conditions. Our approach involved pretraining neural networks for hemorrhage subtype segmentation and brain anatomy parcellation, which were integrated into a pretrained comprehensive neuro-trauma detection network through multimodal fine-tuning. Performance evaluation against expert annotations and comparison with CT-CLIP demonstrated strong triage accuracy across major neuro-trauma findings, such as hemorrhage and midline shift, as well as less frequent critical conditions such as cerebral edema and arterial hyperdensity. The integration of neuro-specific features significantly enhanced diagnostic capabilities, achieving an average AUC of 0.861 for 16 neuro-trauma conditions. This work advances foundation models in medical imaging, serving as a benchmark for future AI-assisted neuro-trauma diagnostics in emergency radiology.

eess.IV↗

arXiv2024

Heuristically Adaptive Diffusion-Model Evolutionary Strategy

Diffusion Models represent a significant advancement in generative modeling, employing a dual-phase process that first degrades domain-specific information via Gaussian noise and restores it through a trainable model. This framework enables pure noise-to-data generation and modular reconstruction of, images or videos. Concurrently, evolutionary algorithms employ optimization methods inspired by biological principles to refine sets of numerical parameters encoding potential solutions to rugged objective functions. Our research reveals a fundamental connection between diffusion models and evolutionary algorithms through their shared underlying generative mechanisms: both methods generate high-quality samples via iterative refinement on random initial distributions. By employing deep learning-based diffusion models as generative models across diverse evolutionary tasks and iteratively refining diffusion models with heuristically acquired databases, we can iteratively sample potentially better-adapted offspring parameters, integrating them into successive generations of the diffusion model. This approach achieves efficient convergence toward high-fitness parameters while maintaining explorative diversity. Diffusion models introduce enhanced memory capabilities into evolutionary algorithms, retaining historical information across generations and leveraging subtle data correlations to generate refined samples. We elevate evolutionary algorithms from procedures with shallow heuristics to frameworks with deep memory. By deploying classifier-free guidance for conditional sampling at the parameter level, we achieve precise control over evolutionary search dynamics to further specific genotypical, phenotypical, or population-wide traits. Our framework marks a major heuristic and algorithmic transition, offering increased flexibility, precision, and control in evolutionary optimization processes.

cs.NE↗

arXiv2024

Disproofs of four Gallai-Ramsey-type conjectures

As a significant variation of Ramsey numbers, the Gallai-Ramsey number $GR_k(H)$ refers to the smallest positive integer $r$ such that, by coloring the edges of $K_r$ with at most $k$ colors, there exists either a monochromatic subgraph isomorphic to $H$ or a rainbow triangle. Mao, Wang, Magnant, and Schiermeyer [Discrete Math., 2023], Song, Wei, Zhang, and Zhao [Discrete Math., 2020], and Zhao and Wei [Discrete Appl. Math., 2021] each proposed one conjecture on the Gallai-Ramsey numbers for fans, wheels, and kipases, respectively. We establish new lower bounds that disprove all three conjectures. Su and Liu [Graphs Combin., 2022] studied the Gallai-Ramsey-full property of graphs and conjectured that a graph is Ramsey-full if and only if it is Gallai-Ramsey-full. We present two classes of graphs that are Ramsey-full, but neither is Gallai-Ramsey-full.

math.CO↗

arXiv2024

Improved bound on the number of edges of diameter-$k$-critical graphs

A graph is diameter-$k$-critical if its diameter equals $k$ and the deletion of any edge increases its diameter. The Murty-Simon Conjecture states that for any diameter-2-critical graph $G$ of order $n$, $e(G) \leq \lfloor \frac{n^2}{4}\rfloor$, with equality if and only if $G \cong K_{\lfloor \frac{n}{2}\rfloor,\lceil \frac{n}{2}\rceil}$. Füredi (JGT,1992) proved that this conjecture is true for sufficiently large $n$. Over two decades later, Loh and Ma (JCT-B, 2016) proved that $e(G) \leq \frac{n^2}{6}+o(n^2)$ for diameter-3-critical graphs $G$, and $e(G) \leq \frac{3n^2}{k}$ for diameter-$k$-critical graphs $G$ with $k \geq 4$. In this paper, we improve the bound for diameter-$k$-critical graphs to $ \frac{n^2}{2k}+o(n^2)$.

math.CO↗

arXiv2024

A Systematic Review on Long-Tailed Learning

Long-tailed data is a special type of multi-class imbalanced data with a very large amount of minority/tail classes that have a very significant combined influence. Long-tailed learning aims to build high-performance models on datasets with long-tailed distributions, which can identify all the classes with high accuracy, in particular the minority/tail classes. It is a cutting-edge research direction that has attracted a remarkable amount of research effort in the past few years. In this paper, we present a comprehensive survey of latest advances in long-tailed visual learning. We first propose a new taxonomy for long-tailed learning, which consists of eight different dimensions, including data balancing, neural architecture, feature enrichment, logits adjustment, loss function, bells and whistles, network optimization, and post hoc processing techniques. Based on our proposed taxonomy, we present a systematic review of long-tailed learning methods, discussing their commonalities and alignable differences. We also analyze the differences between imbalance learning and long-tailed learning approaches. Finally, we discuss prospects and future directions in this field.

cs.LG↗

arXiv2024

Pushing the Limit of Range Resolution Beyond Bandwidth Constraint with Triangle FMCW

This paper proposes a novel signal processing technique that doubles the range resolution of FMCW~(Frequency Modulated Continuous Wave) sensing without increasing the required bandwidth. The proposed design overcomes the resolution limit imposed by bandwidth by exploiting the phase consistency observed in the special frequency variation of the beat signal derived from triangle FMCW. Through this approach, the resolution is doubled while maintaining high spectrum SNR. A system model for signal processing is presented, and the energy distribution of the derived beat spectrum is analyzed. The effectiveness of the proposed technique is validated through model-based simulations.

eess.SP↗