arXiv subjects

Ming Chen

Publications and source records attributed to Ming Chen.

At least 19 recordsLinked to original sources

arXiv2026

ADASCALE: An Adaptive Scaling and Placement Framework for Microservices Under Dynamics

Microservice applications are increasingly deployed across cloud--edge environments, where heterogeneous nodes and time-varying inter-node delays amplify the impact of placement decisions. At the same time, these applications face non-stationary traffic, shifts in the mix of root request operations that exercise different call graphs, and heterogeneous communication modes that determine how network latency and queuing propagate to end-to-end (E2E) performance. Existing autoscalers and network-aware schedulers typically handle only a subset of these dynamics, leading to either compute bottlenecks or inflated cross-node latency and thus SLO violations. We propose ADASCALE, an adaptive framework that jointly scales and places microservice replicas under such multi-dimensional dynamics. ADASCALE implements a Monitor--Analyzer--Planner--Executor (MAPE) loop that extracts per-edge and per-service demand from distributed traces and service-mesh metrics, identifies the most critical root operation under a mixed workload, computes SLO-aware replica targets, and then places replicas to minimize a demand-weighted latency objective given the current inter-node latency matrix. To react quickly to networking perturbations, ADASCALE triggers a reactive placement loop, while a steady-state autoscaling loop handles demand shifts. We evaluate ADASCALE on a cloud--edge Kubernetes cluster using the DeathStarBench Social Network application with three root operations under varying load and workload mixes. Across scenarios, ADASCALE consistently meets SLO targets and improves both latency and throughput: compared with NetMARKS_Scale, it achieves up to 1.56x, 1.93x, and 1.34x lower average response time (for compose-post, read-home-timeline, and read-user-timeline) and up to 2.16x, 1.32x, and 1.36x higher throughput, respectively.

cs.NI↗

arXiv2026

AgentFAIR: A Multi-Agent Collaborative Framework for FAIRness Evaluation of Geospatial Datasets

Geospatial datasets support applications from urban planning to climate modeling, yet consistent assessment of FAIR compliance is difficult. Existing evaluators use different rubrics and evidence sources and may fail on JavaScript-rendered pages or repository-specific identifiers. For 50 datasets from 10 repositories, the standard deviation of normalized scores across available tools averages 15.0 percentage points and reaches 30.3 for one dataset. Because these outputs are not equivalent measurements, we use them to characterize disagreement and failure modes, not comparative accuracy. We present AgentFAIR, a multi-agent framework combining structured metadata extraction with 13 sub-principle-specific LLM evaluators. Each produces a 0-3 maturity score, cited evidence, and recommendations; a critic checks evidence and consistency and can request targeted re-evaluation. Mean Findability, Accessibility, Interoperability, and Reusability scores are 79.7%, 70.4%, 45.3%, and 72.0%. Rank correlations with four baseline tools range from 0.31 to 0.61; the FAIR-enough comparison is not statistically significant. On a 10-dataset repeated-run subset, sub-principle agreement averages 89% (standard deviation: 3 percentage points), versus 71% without the critic. A preliminary 15-dataset expert study yields Fleiss' kappa of 0.71 and 82% alignment with expert consensus. API cost is approximately USD 0.054 per dataset. These results support auditability and feasibility, while the limited benchmark, incomplete ablations, and single-model-family validation constrain claims about accuracy and generalization.

cs.AI↗

arXiv2026

Stitching Molecular Worlds Together with Physics-Coupled Diffusion Models

Complex chemical systems often contain multiple components or large molecules, giving rise to substantial chemical and conformational complexity. Modeling the structures of these systems is crucial for mechanistic understanding of chemical processes and rational design, but remains highly challenging for both conventional theoretical approaches and machine learning. Here, we introduce physical-interaction-coupled diffusion models (PICDiff), a framework that couples independently trained diffusion models for subsystems of a complex system through explicit bonded and nonbonded interactions during inference. PICDiff reduces the difficulty of applying generative models to chemically and conformationally complex systems by decomposing them into smaller subsystems that are less complex and more amenable to machine-learning-based modeling. Using peptide-polymer binding and polymer conformation sampling as examples, we demonstrate that PICDiff can quantitatively sample conformations and model the thermodynamics of complex chemical systems. These results show that PICDiff provides a general and practical approach for modeling complex chemical systems by combining learned models of simpler molecular subsystems through physical interactions.

physics.chem-ph↗

arXiv2026

DeltaDiff: Training-Free, Physics-Guided Machine Learning for Predicting Mutant Protein Structures

Determining mutant protein structures is critical for understanding the mechanistic roles of mutations in biochemical processes. However, experimental characterization and conventional theoretical modeling are often expensive and time-consuming. Recent advances in machine learning provide new opportunities to efficiently predict protein structures from primary sequences. Nevertheless, applying these models to proteins with single-site or few-site mutations remains challenging because mutant sequences are often highly similar to their wild-type counterparts. Here, we introduce DeltaDiff, a physics-guided inference framework for mutant-structure generation that incorporates mutation-aware physical guidance into a baseline diffusion model. We evaluate DeltaDiff on three representative systems: Chignolin T8P, Novispirin G-10, and BBL D162N. All three examples involve nonlocal structural changes, making accurate mutant-structure prediction challenging. DeltaDiff captures key mutation-induced conformational changes without requiring retraining or fine-tuning of the baseline model. These results establish a foundation for efficient mutant-structure prediction at a fraction of the cost of conventional methods, facilitating rational mutant design.

physics.chem-ph↗

arXiv2026

Finite palette endpoints and degree-square Tur\'an problems

We study finite palette extremal problems motivated by uniform Tur\'an densities of $3$-uniform hypergraphs. Given a self-converse tournament $T$ with at least two vertices, we determine the largest possible number of admissible triples in an $m$-color palette that avoids the left and right palettes associated with $T$. The answer is the one-sided degree-square Tur\'an number \[ \operatorname{pal}_T(m) = \operatorname{ex}_2^+(m,T) = \max\left\{ \sum_{v\in V(D)} d_D^+(v)^2: |V(D)|=m,\ D\text{ is }T\text{-free} \right\}. \] Thus this palette problem is reduced to an extremal problem for digraph out-degrees. We then prove a prefix-majorization lemma for convex out-degree moments and apply it to directed cycles. In particular, $\operatorname{ex}_2^+(m,\overrightarrow C_3)=\frac{m(m^2-1)}3$, which gives the sharp $m$-color palette endpoint $\frac13-\frac{1}{3m^2}$ for the directed triangle. Combining this endpoint with the palette characterization of uniform Tur\'an density and the palette separation theorem, we show that for every $m\ge2$ there is a finite $3$-graph $H_m$ such that \[ \frac13-\frac{1}{3m^2}\le \pi_u(H_m)\le \frac13. \] Hence there is a sequence of individual finite $3$-graphs whose uniform Tur\'an densities converge to $1/3$. We also describe the extremal palettes, prove a qualitative edit-distance stability theorem, and compute the Lagrangian of the endpoint palette $\mathcal P_m^\star$. As a consequence, for every $m\ge2$ there is a finite family $\mathcal F_m$ of $3$-graphs with $\pi_u(\mathcal F_m)=\frac13-\frac{1}{3m^2}$, so $1/3$ is an accumulation point of uniform Tur\'an densities of finite forbidden families.

math.CO↗

arXiv2026

Adaptive Management of Microservices in Dynamic Computing Environments: A Taxonomy and Future Directions

Microservice-based cloud applications face changing workloads, evolving request paths, variable network conditions, interference, and failures. These dynamics couple autoscaling, placement, routing, isolation, and remediation. The survey examines dynamics-aware adaptive management for microservices. Its taxonomy covers control locus, modeled dynamics, adaptation strategy, and evaluation evidence; objectives and telemetry are cross-cutting. A synthesis of 84 system entries and 13 evaluation artifacts shows that production dynamics are often partially modeled. Reported gains also depend on evaluation fidelity. Key future directions include cross-layer coordination, telemetry-to-control abstractions, safe learning-based control, and reproducible dynamic evaluation.

cs.DC↗

arXiv2026

LeHome: A Simulation Environment for Deformable Object Manipulation in Household Scenarios

Household environments present one of the most common, impactful yet challenging application domains for robotics. Within household scenarios, manipulating deformable objects is particularly difficult, both in simulation and real-world execution, due to varied categories and shapes, complex dynamics, and diverse material properties, as well as the lack of reliable deformable-object support in existing simulations. We introduce LeHome, a comprehensive simulation environment designed for deformable object manipulation in household scenarios. LeHome covers a wide spectrum of deformable objects, such as garments and food items, offering high-fidelity dynamics and realistic interactions that existing simulators struggle to simulate accurately. Moreover, LeHome supports multiple robotic embodiments and emphasizes low-cost robots as a core focus, enabling end-to-end evaluation of household tasks on resource-constrained hardware. By bridging the gap between realistic deformable object simulation and practical robotic platforms, LeHome provides a scalable testbed for advancing household robotics. Webpage: https://lehome-web.github.io/ .

cs.RO↗

arXiv2026

PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal

Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision.

cs.AI↗

arXiv2026

Tur\'an-type and tiling problems in oriented graphs

Given $a,b,c\in\mathbb N$, let $D_{a,b,c}$ be the tournament on $a+b+c$ vertices obtained by replacing the vertices of the directed triangle $C_3$ with transitive tournaments $TT_a$, $TT_b$, and $TT_c$, respectively. Keevash and Sudakov (2009) showed that every sufficiently large oriented graph $G$ on $n$ vertices with $\delta^{0}(G)\geqslant (1/2-o(1))n$ contains a $C_3$-tiling, equivalently a $D_{1,1,1}$-tiling, covering all but at most three vertices. We generalize this result to arbitrary blow-ups $D_{a,b,c}$. Specifically, for any fixed $a,b,c$, every sufficiently large oriented graph $G$ on $n$ vertices with $\delta^{0}(G)\geqslant (1/2-o(1))n$ contains a $D_{a,b,c}$-tiling covering all but at most $2(a+b+c)-3$ vertices. Moreover, this bound is essentially sharp. We also establish a stronger stability result: if $(a+b+c)\mid n$, then either $G$ contains a $D_{a,b,c}$-factor, or $G$ is close to an extremal graph. Our interest in $D_{a,b,c}$ is also motivated by oriented Tur\'an theory: a seminal theorem of Bollob\'as and H\"aggkvist (1990) shows that a tournament $T$ is Tur\'anable (i.e., contained in every sufficiently large regular tournament) if and only if $T\subseteq D_{s,s,s}$ for some $s$. Complementing our tiling results, we also investigate related semi-degree thresholds for powers of directed cycles and paths. In particular, we present two $n$-vertex constructions that give lower bounds, showing that the minimum semi-degree thresholds for $C^2_l$ with $l\not\equiv 0\pmod 6$ and for $P^2_l$ with $l\geqslant 7$ are at least $4n/9$ and $3n/8$, respectively.

math.CO↗

arXiv2026

A weighted cycle-localization inequality

In 1959, Erd\H{o}s and Gallai showed that every $2$-connected graph $G$ contains a cycle of length at least $\frac{2|E(G)|}{|V(G)|-1}$. This result was subsequently extended to weighted graphs by Bondy and Fan in 1991. A natural local variant of this problem arises by considering, for each edge $e\in E(G)$, the quantity $c(e)$, defined as the length of the longest cycle in $G$ containing $e$ (with $c(e)=2$ if $e$ is a bridge). Zhao and Zhang recently proved that for every graph $G$ on $n$ vertices satisfies $\sum_{e\in E(G)}\frac{1}{c(e)}\le \frac{n-1}{2}.$ In this note, we establish a weighted generalization of this inequality. For a weighted graph $(G,w)$ with positive edge weights, let $C_w(e)$ denote the maximum weight of a cycle containing $e$ (setting $C_w(e)=2w(e)$ if $e$ is a bridge). We prove that $$ \sum_{e\in E(G)}\frac{w(e)}{C_w(e)}\le \frac{n-1}{2}. $$ Our result can be viewed as a weighted local analogue of the Bondy-Fan theorem, thereby establishing a correspondence between the global and local perspectives. Furthermore, we present a broad class of graphs attaining equality and derive necessary conditions for equality.

math.CO↗

arXiv2026

CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support

Large language models (LLMs) show significant potential for clinical decision support (CDS), yet their black-box nature -- characterized by untraceable reasoning and probabilistic hallucinations -- poses severe challenges in acupuncture, a field demanding rigorous interpretability and safety. To address this, we propose CORE-Acu, a neuro-symbolic framework for acupuncture clinical decision support that integrates Structured Chain-of-Thought (S-CoT) with knowledge graph (KG) safety verification. First, we construct the first acupuncture Structured Reasoning Trace dataset and a schema-constrained fine-tuning framework. By enforcing an explicit causal chain from pattern identification to treatment principles, treatment plans, and acupoint selection, we transform implicit Traditional Chinese Medicine (TCM) reasoning into interpretable generation constraints, mitigating the opacity of LLM-based CDS. Furthermore, we construct a TCM safety knowledge graph and establish a ``Generate--Verify--Revise'' closed-loop inference system based on a Symbolic Veto Mechanism, employing deterministic rules to intercept hallucinations and enforce hard safety boundaries. Finally, we introduce the Lexicon-Matched Entity-Reweighted Loss (LMERL), which corrects terminology drift caused by the frequency--importance mismatch in general optimization by adaptively amplifying gradient contributions of high-risk entities during fine-tuning. Experiments on 1,000 held-out cases demonstrate CORE-Acu's superior entity fidelity and reasoning quality. Crucially, CORE-Acu achieved 0/1,000 observed safety violations (95\% CI: 0--0.37\%), whereas GPT-4o exhibited an 8.5\% violation rate under identical rules. These results establish CORE-Acu as a robust neuro-symbolic framework for acupuncture clinical decision support, guaranteeing both reasoning auditability and strict safety compliance.

cs.AI↗

arXiv2026

SurgAtt-Tracker: Online Surgical Attention Tracking via Temporal Proposal Reranking and Motion-Aware Refinement

Accurate and stable field-of-view (FoV) guidance is critical for safe and efficient minimally invasive surgery, yet existing approaches often conflate visual attention estimation with downstream camera control or rely on direct object-centric assumptions. In this work, we formulate surgical attention tracking as a spatio-temporal learning problem and model surgeon focus as a dense attention heatmap, enabling continuous and interpretable frame-wise FoV guidance. We propose SurgAtt-Tracker, a holistic framework that robustly tracks surgical attention by exploiting temporal coherence through proposal-level reranking and motion-aware refinement, rather than direct regression. To support systematic training and evaluation, we introduce SurgAtt-1.16M, a large-scale benchmark with a clinically grounded annotation protocol that enables comprehensive heatmap-based attention analysis across procedures and institutions. Extensive experiments on multiple surgical datasets demonstrate that SurgAtt-Tracker consistently achieves state-of-the-art performance and strong robustness under occlusion, multi-instrument interference, and cross-domain settings. Beyond attention tracking, our approach provides a frame-wise FoV guidance signal that can directly support downstream robotic FoV planning and automatic camera control.

cs.CV↗

arXiv2026

SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm

The long-standing tension between Pre- and Post-Norm remains an open problem in Transformer architecture, reflecting a fundamental trade-off between training stability and representational capacity. Prior attempts to combine their strengths have made progress, but often show limited robustness across training settings, restricting their broader applicability. We revisit this dilemma, showing that single-stream architectures struggle to reconcile Pre-Norm's stable identity-gradient propagation with Post-Norm's normalization of the main residual path. To address this structural tension, we propose SiameseNorm, a simple yet effective two-stream architecture that remains compatible with Pre-Norm training recipes. SiameseNorm couples Pre-Norm-like and Post-Norm-like streams through shared residual blocks, allowing each residual block to receive optimization signals from both pathways with negligible overhead. Extensive experiments on 400M and 1.3B dense language models, 15B MoE models, Vision Transformers, and Diffusion Transformers show that SiameseNorm consistently improves performance while maintaining strong training stability across architectures and modalities. Code is available at https://github.com/Qwen-Applications/SiameseNorm.

cs.LG↗

arXiv2026

On a weaker notion of cross $t$-intersecting families

We prove that if two families $\mathcal{F} \subseteq \binom{[n]}{k}$ and $\mathcal{F}' \subseteq \binom{[n]}{k'}$ satisfy $\sum_{1 \leq i, j \leq \ell} \lvert F_i \cap F_j' \rvert \geq \ell^2t - \ell +1$ for every choice of distinct $F_1, \ldots, F_\ell \in \mathcal{F}$ and $F_1', \ldots, F_\ell' \in \mathcal{F}'$, then $\lvert \mathcal{F} \rvert \cdot \lvert \mathcal{F}' \rvert \leq \binom{n-t}{k-t} \binom{n-t}{k'-t}$, provided that $n$ is sufficiently large. This extends a celebrated theorem of Pyber for large $n$, which determines the tight upper bound for the product of the sizes of cross $1$-intersecting families.

math.CO↗

arXiv2025

Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning

Decoding-based regression, which reformulates regression as a sequence generation task, has emerged as a promising paradigm of applying large language models for numerical prediction. However, its progress is hindered by the misalignment between discrete token-level objectives (e.g., cross-entropy) and continuous numerical values. Existing approaches relying on token-level constraints often fail to capture the global magnitude of the target value, limiting their precision and generalization. In this paper, we propose to unlock the potential of decoding-based regression via Reinforcement Learning (RL). We formulate the generation process as a Markov Decision Process, utilizing sequence-level rewards to enforce global numerical coherence. Extensive experiments on tabular regression and code metric regression demonstrate that our method (specifically with ReMax and GRPO) consistently outperforms both state-of-the-art token-level baselines and traditional regression heads, showing the superiority of introducing sequence-level signals. Our analysis further reveals that RL significantly enhances sampling efficiency and predictive precision, establishing decoding-based regression as a robust and accurate paradigm for general-purpose numerical prediction.

cs.LG↗

arXiv2025

Reasoning in Diffusion Large Language Models is Concentrated in Dynamic Confusion Zones

Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for downstream alignment. Existing trajectory-based RL methods uniformly allocate policy gradients across denoising steps, implicitly treating all steps as equally important. We challenge this assumption by analyzing trajectories with several step-level metrics: entropy-based uncertainty, Confidence-Margin (CM) uncertainty, and Rate of Entropy Change (RoEC). These reveal structured "zones of confusion": transient spikes in uncertainty and instability that strongly predict final success or failure, while most steps remain stable. We propose Adaptive Trajectory Policy Optimization (ATPO), a lightweight step-selection strategy that dynamically reallocates gradient updates to these high-leverage steps without changing the RL objective, rewards, or compute budget. Using a hybrid RoEC+CM rule, ATPO delivers substantial gains in reasoning accuracy and training stability across benchmarks, showing that exploiting trajectory dynamics is key to advancing dLLM RL.

cs.LG↗

arXiv2025

AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms

Dynamically configuring algorithm hyperparameters is a fundamental challenge in computational intelligence. While learning-based methods offer automation, they suffer from prohibitive sample complexity and poor generalization. We introduce AutoEP, a novel framework that bypasses training entirely by leveraging Large Language Models (LLMs) as zero-shot reasoning engines for algorithm control. AutoEP's core innovation lies in a tight synergy between two components: (1) an online Exploratory Landscape Analysis (ELA) module that provides real-time, quantitative feedback on the search dynamics, and (2) a multi-LLM reasoning chain that interprets this feedback to generate adaptive hyperparameter strategies. This approach grounds high-level reasoning in empirical data, mitigating hallucination. Evaluated on three distinct metaheuristics across diverse combinatorial optimization benchmarks, AutoEP consistently outperforms state-of-the-art tuners, including neural evolution and other LLM-based methods. Notably, our framework enables open-source models like Qwen3-30B to match the performance of GPT-4, demonstrating a powerful and accessible new paradigm for automated hyperparameter design. Our code is available at https://github.com/YiZheZhang12/AutoEP.

cs.AI↗

arXiv2025

Clique-factors in graphs with low $K_{\ell}$-independence number

Given $r\in \mathbb{N}$ with $r\geq 4$, we show that there exists $n_0\in \mathbb{N}$ such that for every $n\geq n_0$, every $n$-vertex graph $G$ with $\delta(G)\geq (\frac{1}{2}+o(1))n$ and $\alpha_{r-2}(G)=o(n)$ contains a $K_{r}$-factor. This resolves the first open case of a question proposed by Nenadov and Pehova, and reiterated by Knierm and Su. We further introduce two lower bound constructions that, along with some known results, fully resolve a question presented by Balogh, Molla, and Sharifzadeh.

math.CO↗