arXiv subjects

Ke Zhao

Publications and source records attributed to Ke Zhao.

At least 19 recordsLinked to original sources

arXiv2026

Two-block paths in oriented graphs under the Ore-type condition

Stein conjectured that for every positive integer $k$, every oriented graph with minimum semi-degree greater than $k/2$ contains every oriented path of length $k$ [Springer Optim.Appl. 165 (2020), 459--486]. For directed paths this is a classical result of Jackson (1981). The two-block case of the conjecture was established by Chen, Hou and Zhou (2025). In this paper we prove the two-block analogue of Jackson's theorem. For all positive integers $s$ and $r$, let $P(s,r)$ be the oriented path consisting of two directed paths of lengths $s$ and $r$ with a common terminal vertex, and let $Q(s,r)$ be its reverse. We show that for all $K\ge3$ and all $s,r\ge1$ with $s+r\le K$, every oriented graph $D$ with $δ(D)\ge K$ and $d_D^+(u)+d_D^-(v)\ge K-1$ for every ordered pair of distinct vertices $(u,v)\notin A(D)$ contains both $P(s,r)$ and $Q(s,r)$. Our result is the two-block analogue of Jackson's theorem, and it extends the two-block result of Chen, Hou and Zhou. The proof iterates a shift of the terminal vertex of a longest path.

math.CO↗

arXiv2026

On Sequential Entropic Optimal Transport Filter and its Multilevel Variants

We consider the problem of filtering partially observed diffusions associated to discrete time observations. This problem requires the development of advanced numerical methods such as particle filters. In this article we develop a new sequential entropic optimal transport filter (EOTF). The main idea is to sample from successive couplings of the filters. To achieve this, we adopt the approach of an entropic optimal transport (EOT) update implemented through a learned Schrödinger potential, in the spirit of the light Schrödinger bridge methodology \cite{korotin2024light}. Based on this, we develop a multilevel version of this filter (ML-EOTF) in which consecutive discretization levels are coupled at the terminal time by a scaled EOT plan with level-dependent regularization $\eps_l=\eps_0 h_l^κ$ with discretization stepsize $h_l$. Under mild conditions, we show that the level-difference estimator with exact Schrödinger potentials has variance of order $N_l^{-1}\{h_l^β+\eps_l\}$, where $β$ is the strong-error for the discretized SDE. The analysis is then extended to learned potentials, with all approximation and optimization errors summarized by a joint Kullback--Leibler discrepancy whose contribution to the mean squared error is explicitly quantified. Combined with a fixed-time weak-error estimate, this yields the canonical multilevel complexity $\cO(δ^{-2}|\logδ|^2)$ to achieve an MSE of $δ^2$ for Euler--Maruyama discretizations. Numerical experiments validate the results.

stat.CO↗

arXiv2026

On Bridging Mixture Distributions

The construction and the stability of bridges between mixture probability measures are investigated. Given a collection of Markov transitions bridging the components of two mixtures, together with a coupling of the mixture labels, we construct a bridge between the mixtures on an extended state space, and we show that this bridge inherits the entropic optimality of the component bridges. We then turn to Gaussian mixtures bridged by Gaussian Schrödinger bridges, whose parameters are generally unknown and must be estimated. We prove a $2$-Wasserstein continuity theorem between the exact bridge and its plug-in approximation. The analysis rests on a representation of the Riccati fixed point map in inverse coordinates; this map is globally $1$-Lipschitz and requires no matrix inversion. These results are applied to three estimation schemes, with $d$ the dimension and $N$ the number of samples. For Gaussian mixtures estimated by the Expectation-Maximization algorithm, the squared $2$-Wasserstein error is of order $(d\log N/N)^{1/2}+d^2\log N/N$ with probability at least $1-10N^{-1}$. For single Gaussian marginals estimated by their sample moments, it is of order $d^2/N$ in expectation. For the regularized empirical Monge map based on an $ε$-inflation of the sample covariance, the mean squared error is of order $d^2\{(1+ε^{-1})/N+ε^2\}$; as soon as $N$ is a sufficiently large multiple of $d$, it reduces to $d^2/N+d\,ε^2$, up to an exponentially small term. These estimates are illustrated numerically.

math.ST↗

arXiv2026

PrismGPT: Proxy-Guided Learning for Region-Aware Photo Editing with Self-Synthesized Reasoning

Professional photo finishing relies on both global adjustments and region-specific local edits guided by semantic masks, yet current automated methods handle this workflow only partially. We present PrismGPT, a Vision-Language Model (VLM) framework that produces structured, region-aware editing plans from a single input image without relying on commercial black-box tools. Training a VLM to simultaneously diagnose aesthetic deficiencies at both global and local levels while predicting precise editing parameters is challenging due to the vast combinatorial decision space. We address this through proxy-guided learning: two simpler proxy tasks -- operation decomposition and region-aware aesthetic ranking -- teach the foundational skills the model needs, while a competence-based dynamic scheduler automatically rebalances the multi-task training ratio, progressively shifting emphasis from the proxy tasks to the primary editing task as each skill is mastered. Crucially, all reasoning traces used for supervised fine-tuning are self-synthesized by the same base model, eliminating the need for a stronger external teacher. Experiments on MIT-Adobe FiveK and SPIRE, a new professionally retouched benchmark we introduce, show that PrismGPT achieves state-of-the-art results while using only ~6% of the training data compared to the previous best method.

cs.CV↗

arXiv2026

OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation

Leveraging Large Language Models (LLMs) to automatically formulate and solve optimization problems from natural language has emerged as an efficient paradigm for automated optimization. However, existing methods still exhibit limited generalization: they are sensitive to superficial narrative variations, reuse experience mainly at the case level, and struggle to adapt to shifted or emerging problem types. We propose OptSkills, an archetype-centric skill learning and reasoning agent system for optimization modeling and solving. To improve robust generalization, our system clusters problems by their underlying archetypes rather than surface narratives. To improve in-distribution generalization, it explores diverse modeling paradigms and solver configurations within each cluster, then distills successful trajectories into reusable workflow-level skills. To improve out-of-distribution generalization, it refines existing skills or expands the skill library using newly obtained trajectories. Our system achieves a state-of-the-art micro-averaged accuracy of 68.27% on datasets encompassing diverse problem types and scenarios. In addition, on MIPLIB-NL, a highly challenging large-scale and high-dimensional benchmark, it achieves 26.91% accuracy, outperforming DeepSeek-V3.2-Thinking by 4.53%. After skill learning on Nano-CO, it reaches 72.79% on the OOD NLCO benchmark. Code and skills are available at https://github.com/fujiwaranoM0kou/OptSkills.

cs.AI↗

arXiv2026

Disentangling Representation using Attributes-based Gaussian Estimation for Medical Sound Diagnosis

Deep learning has a powerful capability of feature extraction. However, the lack of fairness and interpretability in deep neural networks poses limitations to their adoption in the medical domain. This paper proposes a disentangled representation learning (DisenRL) framework, named the Attributes-based Gaussian Estimation for Disentangled Representation (AGEDR), which incorporates Attribute Mapping Embedding (AME) modules designed to map attributes into vectors and align them with a subset of the latent vectors in a Variational AutoEncoder (VAE). This part of the latent vector will be disentangled from the remaining latent vectors by minimizing mutual information. A classifier is then trained using the mean parameters of the latent vectors from the VAE. Extensive experiments demonstrate that AGEDR outperforms both conventional classification models and existing disentangled representation learning methods. The ablation experiments also indicate the disentangling capability and fairness of AGEDR. The source code is publicly available at https://github.com/ZhaoKe1024/DisentangledRepr.

cs.AI↗

arXiv2026

MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources

Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large language models (LLMs). Existing approaches typically rely on large-scale supervised datasets, costly reasoning annotations, and expensive intermediate step verification, resulting in substantial training overhead. To address these challenges, we propose MiniOpt, a reinforcement learning framework that learns to solve optimization problems through an "reasoning-to-model-and-solve" paradigm. MiniOpt decomposes optimization reasoning into structured optimization modeling and executable solver generation. Building upon this paradigm, we introduce OptReward, a reward function with hierarchical score structure that jointly evaluates formulation and solution, enabling effective policy learning without expert demonstrations. We further develop an optimization-oriented policy optimization strategy that improves exploration efficiency and stabilizes reinforcement learning for compact models. Extensive experiments show that MiniOpt-3B exhibits strong optimization generalization across various optimization types, problem scenarios, and task domains. For models with fewer than 10B parameters, MiniOpt series achieves the highest average solving accuracy (SA). For models with more than 10B parameters, MiniOpt still shows competitive performance. These results suggest that optimization-oriented reward design and reinforcement learning provide an effective pathway for developing compact optimization-specialized language models with strong optimization generalization capabilities. The code is available at https://github.com/Hsiang-1/MiniOpt.

cs.LG↗

arXiv2026

Parameter Estimation for Partially Observed Time-Changed SDEs

In this paper we consider the parameter estimation problem associated to partially-observed time changed SDEs, with observations that are given at discrete times. In particular we consider both likelihood and Bayesian estimation. We develop new Markov chain Monte Carlo (MCMC) algorithms which allow an unbiased score-based stochastic approximation method to provide likelihood-type parameter estimators. We also use a variant of this MCMC algorithm to perform multilevel-based Bayesian parameter estimation. We prove that this latter method achieves a mean square error of $\mathcal{O}(ε^2)$ ($ε>0$) with a cost of $\mathcal{O}(ε^{-2}\log(ε)^2)$. Our methodologies are tested numerically on both simulated and real data.

math.NA↗

arXiv2026

Exponentially improved quantum simulation of scalar QFT

Quantum simulations of scalar quantum field theories (QFT) provide important benchmarks for demonstrating quantum advantage. We revisit digitization in the occupation basis, which is typically hindered by unfavorable circuit depth scaling. We present an approach that achieves exponential reductions in circuit depth and significantly mitigates Trotter errors by diagonalizing field operators prior to their decomposition into Pauli strings. Focusing on a scalar QFT in 2+1 dimensions, we show that this method substantially reduces circuit depth and CNOT gate counts for time evolution. Using the Lorentzian energy-energy correlator as a benchmark observable, we find parameter regimes in which occupation-basis digitization converges more rapidly with respect to local truncation than the amplitude-basis approach of Jordan, Lee, and Preskill. These results provide both algorithmic advances and phenomenological benchmarks for studies of light-ray observables on near-term quantum devices.

hep-ph↗

arXiv2026

Edit-aware RAW Reconstruction

Users frequently edit camera images post-capture to achieve their preferred photofinishing style. While editing in the RAW domain provides greater accuracy and flexibility, most edits are performed on the camera's display-referred output (e.g., 8-bit sRGB JPEG) since RAW images are rarely stored. Existing RAW reconstruction methods can recover RAW data from sRGB images, but these approaches are typically optimized for pixel-wise RAW reconstruction fidelity and tend to degrade under diverse rendering styles and editing operations. We introduce a plug-and-play, edit-aware loss function that can be integrated into any existing RAW reconstruction framework to make the recovered RAWs more robust to different rendering styles and edits. Our loss formulation incorporates a modular, differentiable image signal processor (ISP) that simulates realistic photofinishing pipelines with tunable parameters. During training, parameters for each ISP module are randomly sampled from carefully designed distributions that model practical variations in real camera processing. The loss is then computed in sRGB space between ground-truth and reconstructed RAWs rendered through this differentiable ISP. Incorporating our loss improves sRGB reconstruction quality by up to 1.5-2 dB PSNR across various editing conditions. Moreover, when applied to metadata-assisted RAW reconstruction methods, our approach enables fine-tuning for target edits, yielding further gains. Since photographic editing is the primary motivation for RAW reconstruction in consumer imaging, our simple yet effective loss function provides a general mechanism for enhancing edit fidelity and rendering flexibility across existing methods.

cs.CV↗

arXiv2026

PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs

RL post-training with verifiable rewards (RLVR) has become a practical route to eliciting chain-of-thought reasoning in vision--language models (VLMs), but scaling it in the visual domain remains challenging due to costly or noisy supervision and reliance on external verifiers. Puzzle-based RLVR is a promising alternative, yet existing approaches often treat puzzle rewards as flat or sparse, which weakens group-relative learning signal. Existing curriculum strategies are overly restrictive: they rely mainly on reward statistics and do not account for exploration in the solution space, which can lead to collapsed rollout dynamics. Further, RL post-training can induce reasoning--answer inconsistency as training progresses. To address these shortcomings, we present PuzzleCraft, a supervision-free framework that scales vision-centric RLVR using a set of lightweight puzzle environments with built-in verification. PuzzleCraft instantiates three puzzles inspired by classic visual pretext tasks: PatchFit, Rotation, and Jigsaw. We introduce a curriculum that combines difficulty with an exploration signal derived from solution-space dispersion, and use it to downweight collapsed prompt groups. In addition, we introduce a new post-training metric, Reasoning-Answer Consistency (RAC), to measure the degree that the chain-of-though supports the answer, and show our exploration-aware curriculum improves RAC and downstream performance. Across a broad suite of vision-centric benchmarks, PuzzleCraft improves robustness and reasoning consistency, yielding consistent downstream gains on both Qwen2.5-VL and Qwen3-VL backbones. Overall, our results suggest that scalable puzzle-based RLVR benefits from curricula that account for both difficulty and solution-space collapse, together with explicit consistency-enhancing schemes.

cs.CV↗

arXiv2026

Pre/Absence: Prompting Cultural Awareness and Understanding for Lost Architectural Heritage in Virtual Reality

Lost architectural heritage presents interpretive challenges due to vanished structures and fragmented historical records. Using Hanyuan Hall of the Tang dynasty's Daming Palace as a case study, we conducted a formative investigation with archaeologists, heritage administrators, and visitors to identify key issues in current interpretation practices. We found that these practices often compress complex cultural layers into factual summaries and rely on linear narratives that overlook the continuing reinterpretations following a site's disappearance. In response, we designed Pre/Absence, a virtual reality experience grounded in the presence-absence dialectic to interweave tangible and vanished aspects of heritage within a spatiotemporal narrative. A mixed-method study with 28 participants compared Pre/Absence to a paper-based experience. Both improved users' factual understanding, but the VR experience more strongly enhanced cultural awareness, evoked emotional engagement with loss, and encouraged critical reflection on the evolving social and political meanings of heritage. The findings suggest that VR can move beyond static reconstruction to engage users as co-constructors of cultural meaning, providing a nuanced framework for critical heritage narrative design in human-computer interaction.

cs.HC↗

arXiv2025

Evaluating Large Language Models in Crisis Detection: A Real-World Benchmark from Psychological Support Hotlines

Psychological support hotlines serve as critical lifelines for crisis intervention but encounter significant challenges due to rising demand and limited resources. Large language models (LLMs) offer potential support in crisis assessments, yet their effectiveness in emotionally sensitive, real-world clinical settings remains underexplored. We introduce PsyCrisisBench, a comprehensive benchmark of 540 annotated transcripts from the Hangzhou Psychological Assistance Hotline, assessing four key tasks: mood status recognition, suicidal ideation detection, suicide plan identification, and risk assessment. 64 LLMs across 15 model families (including closed-source such as GPT, Claude, Gemini and open-source such as Llama, Qwen, DeepSeek) were evaluated using zero-shot, few-shot, and fine-tuning paradigms. LLMs showed strong results in suicidal ideation detection (F1=0.880), suicide plan identification (F1=0.779), and risk assessment (F1=0.907), with notable gains from few-shot prompting and fine-tuning. Compared to trained human operators, LLMs achieved comparable or superior performance on suicide plan identification and risk assessment, while humans retained advantages on mood status recognition and suicidal ideation detection. Mood status recognition remained challenging (max F1=0.709), likely due to missing vocal cues and semantic ambiguity. Notably, a fine-tuned 1.5B-parameter model (Qwen2.5-1.5B) outperformed larger models on mood and suicidal ideation tasks. LLMs demonstrate performance broadly comparable to trained human operators in text-based crisis assessment, with complementary strengths across task types. PsyCrisisBench provides a robust, real-world evaluation framework to guide future model development and ethical deployment in clinical mental health.

cs.CL↗

arXiv2025

Scalable Quantum State Preparation via Large-Language-Model-Driven Discovery

Efficient quantum state preparation remains a central challenge in first-principles quantum simulations of dynamics in quantum field theories, where the Hilbert space is intrinsically infinite-dimensional. Here, we introduce a large language model (LLM)-assisted framework for quantum-circuit design that systematically scales state-preparation circuits to large lattice volumes. Applied to a 1+1d XY spin chain, the LLM autonomously discovers a compact 4-parameter circuit that captures boundary-induced symmetry breaking with sub-percent energy deviation, enabling successful validation on the \texttt{Zuchongzhi} quantum processor. Guided by this insight, we extend the framework to 2+1d quantum field theories, where scalable variational ansätze have remained elusive. For a scalar field theory, the search yields a symmetry-preserving, 3-parameter shallow-depth ansatz whose optimized parameters converge to size-independent constants for lattices $n \ge 4$, providing, to our knowledge, the first scalable ansatz for this class of 2+1d models. Our results establish a practical route toward AI-assisted, human-guided discovery in quantum simulation.

quant-ph↗

arXiv2025

Relief of EGFR/FOS-downregulated miR-103a by loganin alleviates NF-kappaB-triggered inflammation and gut barrier disruption in colitis

Due to the ever-rising global incidence rate of inflammatory bowel disease (IBD) and the lack of effective clinical treatment drugs, elucidating the detailed pathogenesis, seeking novel targets, and developing promising drugs are the top priority for IBD treatment. Here, we demonstrate that the levels of microRNA (miR)-103a were significantly downregulated in the inflamed mucosa of ulcerative colitis (UC) patients, along with elevated inflammatory cytokines (IL-1beta/TNF-alpha) and reduced tight junction protein (Occludin/ZO-1) levels, as compared with healthy control objects. Consistently, miR-103a deficient intestinal epithelial cells Caco-2 showed serious inflammatory responses and increased permeability, and DSS induced more severe colitis in miR-103a-/- mice than wild-type ones. Mechanistic studies unraveled that c-FOS suppressed miR-103a transcription via binding to its promoter, then miR-103a-targeted NF-kappaB activation contributes to inflammatory responses and barrier disruption by targeting TAB2 and TAK1. Notably, the traditional Chinese medicine Cornus officinalis (CO) and its core active ingredient loganin potently mitigated inflammation and barrier disruption in UC by specifically blocking the EGFR/RAS/ERK/c-FOS signaling axis, these effects mainly attributed to modulated miR-103a levels as the therapeutic activities of them were almost completely shielded in miR-103a KO mice. Taken together, this work reveals that loganin relieves EGFR/c-FOS axis-suppressed epithelial miR-103a expression, thereby inhibiting NF-kappaB pathway activation, suppressing inflammatory responses, and preserving tight junction integrity in UC. Thus, our data enrich mechanistic insights and promising targets for UC treatment.

q-bio.BM↗

arXiv2024

Rethinking the Intermediate Features in Adversarial Attacks: Misleading Robotic Models via Adversarial Distillation

Language-conditioned robotic learning has significantly enhanced robot adaptability by enabling a single model to execute diverse tasks in response to verbal commands. Despite these advancements, security vulnerabilities within this domain remain largely unexplored. This paper addresses this gap by proposing a novel adversarial prompt attack tailored to language-conditioned robotic models. Our approach involves crafting a universal adversarial prefix that induces the model to perform unintended actions when added to any original prompt. We demonstrate that existing adversarial techniques exhibit limited effectiveness when directly transferred to the robotic domain due to the inherent robustness of discretized robotic action spaces. To overcome this challenge, we propose to optimize adversarial prefixes based on continuous action representations, circumventing the discretization process. Additionally, we identify the beneficial impact of intermediate features on adversarial attacks and leverage the negative gradient of intermediate self-attention features to further enhance attack efficacy. Extensive experiments on VIMA models across 13 robot manipulation tasks validate the superiority of our method over existing approaches and demonstrate its transferability across different model variants.

cs.LG↗

arXiv2024

Report on Methods and Applications for Crafting 3D Humans

This paper presents an in-depth exploration of 3D human model and avatar generation technology, propelled by the rapid advancements in large-scale models and artificial intelligence. The paper reviews the comprehensive process of 3D human model generation, from scanning to rendering, and highlights the pivotal role these models play in entertainment, VR, AR, healthcare, and education. We underscore the significance of diffusion models in generating high-fidelity images and videos. It emphasizes the indispensable nature of 3D human models in enhancing user experiences and functionalities across various fields. Furthermore, this paper anticipates the potential of integrating large-scale models with deep learning to revolutionize 3D content generation, offering insights into the future prospects of the technology. It concludes by emphasizing the importance of continuous innovation in the field, suggesting that ongoing advancements will significantly expand the capabilities and applications of 3D human models and avatars.

cs.GR↗

arXiv2024

Challenges and Opportunities in 3D Content Generation

This paper explores the burgeoning field of 3D content generation within the landscape of Artificial Intelligence Generated Content (AIGC) and large-scale models. It investigates innovative methods like Text-to-3D and Image-to-3D, which translate text or images into 3D objects, reshaping our understanding of virtual and real-world simulations. Despite significant advancements in text and image generation, automatic 3D content generation remains nascent. This paper emphasizes the urgency for further research in this area. By leveraging pre-trained diffusion models, which have demonstrated prowess in high-fidelity image generation, this paper aims to summary 3D content creation, addressing challenges such as data scarcity and computational resource limitations. Additionally, this paper discusses the challenges and proposes solutions for using pre-trained diffusion models in 3D content generation. By synthesizing relevant research and outlining future directions, this study contributes to advancing the field of 3D content generation amidst the proliferation of large-scale AIGC models.

cs.GR↗