arXiv subjects

Ming Chen

Publications and source records attributed to Ming Chen.

At least 37 records · Page 2Linked to original sources

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

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

TraDE: Network and Traffic-aware Adaptive Scheduling for Microservices Under Dynamics

The transition from monolithic architecture to microservices has enhanced flexibility in application design and its scalable execution. This approach typically uses a computing cluster managed by a container orchestration platform to deploy microservices. However, this shift introduces significant challenges, particularly in the efficient scheduling of containerized services. These challenges are compounded by unpredictable scenarios such as dynamic incoming workloads with various execution traffic and variable communication delays among cluster nodes. Existing works often overlook the real-time traffic impacts of dynamic requests on running microservices, as well as the varied communication delays across cluster nodes. Consequently, even optimally deployed microservices could suffer from significant performance degradation over time. To address these issues, we propose a network and traffic-aware adaptive scheduling framework, TraDE, which can adaptively redeploy microservice instances to maintain desired performance amid changing traffic and network conditions within the hosting cluster. We have implemented TraDE as an extension to the Kubernetes platform. Additionally, we deployed realistic microservice applications in a real compute cluster and conducted extensive experiments to assess our framework's performance in various scenarios. The results demonstrate the effectiveness of TraDE in rescheduling running microservices to enhance end-to-end performance while maintaining a high goodput ratio. Compared with the existing method NetMARKS, TraDE outperforms it by reducing the average response time of the application by up to 48.3%, and improving the throughput by up to 1.2-1.5x across workloads while maintaining a goodput ratio of 95.36%, and showing robust adaptive capability to meet QoS targets under sustained workloads and dynamic networking conditions.

cs.NI↗

arXiv2025

LLM-OptiRA: LLM-Driven Optimization of Resource Allocation for Non-Convex Problems in Wireless Communications

Solving non-convex resource allocation problems poses significant challenges in wireless communication systems, often beyond the capability of traditional optimization techniques. To address this issue, we propose LLM-OptiRA, the first framework that leverages large language models (LLMs) to automatically detect and transform non-convex components into solvable forms, enabling fully automated resolution of non-convex resource allocation problems in wireless communication systems. LLM-OptiRA not only simplifies problem-solving by reducing reliance on expert knowledge, but also integrates error correction and feasibility validation mechanisms to ensure robustness. Experimental results show that LLM-OptiRA achieves an execution rate of 96% and a success rate of 80% on GPT-4, significantly outperforming baseline approaches in complex optimization tasks across diverse scenarios.

cs.CL↗

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 $δ(G)\geq (\frac{1}{2}+o(1))n$ and $α_{r-2}(G)=o(n)$ 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↗

arXiv2025

Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-level tracking driven by acoustic or visual cues, without modeling the communicative purpose conveyed by the instructions. This limitation compromises their narrative coherence and character expressiveness. To bridge this gap, we introduce Kling-Avatar, a novel cascaded framework that unifies multimodal instruction understanding with photorealistic portrait generation. Our approach adopts a two-stage pipeline. In the first stage, we design a multimodal large language model (MLLM) director that produces a blueprint video conditioned on diverse instruction signals, thereby governing high-level semantics such as character motion and emotions. In the second stage, guided by blueprint keyframes, we generate multiple sub-clips in parallel using a first-last frame strategy. This global-to-local framework preserves fine-grained details while faithfully encoding the high-level intent behind multimodal instructions. Our parallel architecture also enables fast and stable generation of long-duration videos, making it suitable for real-world applications such as digital human livestreaming and vlogging. To comprehensively evaluate our method, we construct a benchmark of 375 curated samples covering diverse instructions and challenging scenarios. Extensive experiments demonstrate that Kling-Avatar is capable of generating vivid, fluent, long-duration videos at up to 1080p and 48 fps, achieving superior performance in lip synchronization accuracy, emotion and dynamic expressiveness, instruction controllability, identity preservation, and cross-domain generalization. These results establish Kling-Avatar as a new benchmark for semantically grounded, high-fidelity audio-driven avatar synthesis.

cs.CV↗

arXiv2025

DSFT: Inspiring Diffusion Large Language Models to Comprehend Mathematical and Logical Patterns

Diffusion large language models (dLLMs) have emerged as a new architecture following auto regressive models. Their denoising process offers a powerful generative advantage, but they present significant challenges in learning and understanding numerically sensitive mathematical and order-sensitive logical tasks. Current training methods, including pre-training, fine-tuning, and reinforcement learning, focus primarily on improving general knowledge retention and reasoning abilities, but lack a comprehensive understanding of mathematical and logical patterns. We propose DSFT, a simple yet effective Diffusion SFT strategy, by adjusting the masking strategy and loss function, guiding models to understand mathematical and logical patterns. This strategy can be flexibly combined with pre-training, reinforcement learning, and other training methods. Validated on models such as LLaDA and Dream series, we prove that DSFT on small-scale data can achieve improvements of 5-10% and approximately 2% on mathematical and logical problems, respectively. This inspiring masking approach offers insights for future learning of specific patterns, which can be easily and efficiently combined with other training methods and applied to various dLLMs. Our code is publicly available at https://anonymous.4open.science/r/DSFT-0FFB/

cs.LG↗

arXiv2025

ProTDyn: a foundation Protein language model for Thermodynamics and Dynamics generation

Molecular dynamics (MD) simulation has long been the principal computational tool for exploring protein conformational landscapes and dynamics, but its application is limited by high computational cost. We present ProTDyn, a foundation protein language model that unifies conformational ensemble generation and multi-timescale dynamics modeling within a single framework. Unlike prior approaches that treat these tasks separately, ProTDyn allows flexible independent and identically distributed (i.i.d.) ensemble sampling and dynamic trajectory simulation. Across diverse protein systems, ProTDyn yields thermodynamically consistent ensembles, faithfully reproduces dynamical properties over multiple timescales, and generalizes to proteins beyond its training data. It offers a scalable and efficient alternative to conventional MD simulations.

physics.bio-ph↗

arXiv2025

Embodied Intelligence in Disassembly: Multimodal Perception Cross-validation and Continual Learning in Neuro-Symbolic TAMP

With the rapid development of the new energy vehicle industry, the efficient disassembly and recycling of power batteries have become a critical challenge for the circular economy. In current unstructured disassembly scenarios, the dynamic nature of the environment severely limits the robustness of robotic perception, posing a significant barrier to autonomous disassembly in industrial applications. This paper proposes a continual learning framework based on Neuro-Symbolic task and motion planning (TAMP) to enhance the adaptability of embodied intelligence systems in dynamic environments. Our approach integrates a multimodal perception cross-validation mechanism into a bidirectional reasoning flow: the forward working flow dynamically refines and optimizes action strategies, while the backward learning flow autonomously collects effective data from historical task executions to facilitate continual system learning, enabling self-optimization. Experimental results show that the proposed framework improves the task success rate in dynamic disassembly scenarios from 81.68% to 100%, while reducing the average number of perception misjudgments from 3.389 to 1.128. This research provides a new paradigm for enhancing the robustness and adaptability of embodied intelligence in complex industrial environments.

cs.RO↗

arXiv2025

Decoding RobKiNet: Insights into Efficient Training of Robotic Kinematics Informed Neural Network

In robots task and motion planning (TAMP), it is crucial to sample within the robot's configuration space to meet task-level global constraints and enhance the efficiency of subsequent motion planning. Due to the complexity of joint configuration sampling under multi-level constraints, traditional methods often lack efficiency. This paper introduces the principle of RobKiNet, a kinematics-informed neural network, for end-to-end sampling within the Continuous Feasible Set (CFS) under multiple constraints in configuration space, establishing its Optimization Expectation Model. Comparisons with traditional sampling and learning-based approaches reveal that RobKiNet's kinematic knowledge infusion enhances training efficiency by ensuring stable and accurate gradient optimization.Visualizations and quantitative analyses in a 2-DOF space validate its theoretical efficiency, while its application on a 9-DOF autonomous mobile manipulator robot(AMMR) demonstrates superior whole-body and decoupled control, excelling in battery disassembly tasks. RobKiNet outperforms deep reinforcement learning with a training speed 74.29 times faster and a sampling accuracy of up to 99.25%, achieving a 97.33% task completion rate in real-world scenarios.

cs.RO↗

arXiv2025

Evaluating Multi-Turn Bargain Skills in LLM-Based Seller Agent

In online second-hand marketplaces, multi-turn bargaining is a crucial part of seller-buyer interactions. Large Language Models (LLMs) can act as seller agents, negotiating with buyers on behalf of sellers under given business constraints. A critical ability for such agents is to track and accurately interpret cumulative buyer intents across long negotiations, which directly impacts bargaining effectiveness. We introduce a multi-turn evaluation framework for measuring the bargaining ability of seller agents in e-commerce dialogues. The framework tests whether an agent can extract and track buyer intents. Our contributions are: (1) a large-scale e-commerce bargaining benchmark spanning 622 categories, 9,892 products, and 3,014 tasks; (2) a turn-level evaluation framework grounded in Theory of Mind (ToM) with annotated buyer intents, moving beyond outcome-only metrics; and (3) an automated pipeline that extracts reliable intent from massive dialogue data.

cs.AI↗

arXiv2025

MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation

Recently, interactive digital human video generation has attracted widespread attention and achieved remarkable progress. However, building such a practical system that can interact with diverse input signals in real time remains challenging to existing methods, which often struggle with heavy computational cost and limited controllability. In this work, we introduce an autoregressive video generation framework that enables interactive multimodal control and low-latency extrapolation in a streaming manner. With minimal modifications to a standard large language model (LLM), our framework accepts multimodal condition encodings including audio, pose, and text, and outputs spatially and semantically coherent representations to guide the denoising process of a diffusion head. To support this, we construct a large-scale dialogue dataset of approximately 20,000 hours from multiple sources, providing rich conversational scenarios for training. We further introduce a deep compression autoencoder with up to 64$\times$ reduction ratio, which effectively alleviates the long-horizon inference burden of the autoregressive model. Extensive experiments on duplex conversation, multilingual human synthesis, and interactive world model highlight the advantages of our approach in low latency, high efficiency, and fine-grained multimodal controllability.

cs.CV↗

arXiv2025

A Steel Surface Defect Detection Method Based on Lightweight Convolution Optimization

Surface defect detection of steel, especially the recognition of multi-scale defects, has always been a major challenge in industrial manufacturing. Steel surfaces not only have defects of various sizes and shapes, which limit the accuracy of traditional image processing and detection methods in complex environments. However, traditional defect detection methods face issues of insufficient accuracy and high miss-detection rates when dealing with small target defects. To address this issue, this study proposes a detection framework based on deep learning, specifically YOLOv9s, combined with the C3Ghost module, SCConv module, and CARAFE upsampling operator, to improve detection accuracy and model performance. First, the SCConv module is used to reduce feature redundancy and optimize feature representation by reconstructing the spatial and channel dimensions. Second, the C3Ghost module is introduced to enhance the model's feature extraction ability by reducing redundant computations and parameter volume, thereby improving model efficiency. Finally, the CARAFE upsampling operator, which can more finely reorganize feature maps in a content-aware manner, optimizes the upsampling process and ensures detailed restoration of high-resolution defect regions. Experimental results demonstrate that the proposed model achieves higher accuracy and robustness in steel surface defect detection tasks compared to other methods, effectively addressing defect detection problems.

eess.IV↗

arXiv2025

Constructing Generalized Sample Transition Probabilities with Biased Simulations

In molecular dynamics (MD) simulations, accessing transition probabilities between states is crucial for understanding kinetic information, such as reaction paths and rates. However, standard MD simulations are hindered by the capacity to visit the states of interest, prompting the use of enhanced sampling to accelerate the process. Unfortunately, biased simulations alter the inherent probability distributions, making kinetic computations using techniques such as diffusion maps challenging. Here, we use a coarse-grained Markov chain to estimate the intrinsic pairwise transition probabilities between states sampled from a biased distribution. Our method, which we call the generalized sample transition probability (GSTP), can recover transition probabilities without relying on an underlying stochastic process and specifying the form of the kernel function, which is necessary for the diffusion map method. The proposed algorithm is validated on model systems such as a harmonic oscillator, alanine dipeptide in vacuum, and met-enkephalin in solvent. The results demonstrate that GSTP effectively recovers the unbiased eigenvalues and eigenstates from biased data. GSTP provides a general framework for analyzing kinetic information in complex systems, where biased simulations are necessary to access longer timescales.

physics.chem-ph↗

arXiv2025

Delay-Doppler Diversity Analysis of ODDM Modulation in Satellite Communication Systems

Orthogonal delay-Doppler division multiplexing (ODDM) modulation offers a promising solution to the problem of severe Doppler effects in low earth orbit (LEO) satellites communications. It has been suggested in the recent literature that ODDM modulation can extract full delay-Doppler (DD) diversity, yet a rigorous analysis has not been presented. In this paper, we present a formal analysis of the DD diversity achieved by ODDM modulation along with supporting simulations. Specifically, the analysis and simulations reveal that the asymptotic DD diversity order of ODDM modulation is one, and this order is achieved at lower bit error rate (BER) values for increased frame sizes. We also present low-complexity detector for ODDM modulation based on the Orthogonal approximate message passing (OAMP) algorithm, and show that this detector extracts full DD diversity with the reduced complexity.

cs.IT↗