arXiv subjects

Jie Song

Publications and source records attributed to Jie Song.

At least 37 records · Page 2Linked to original sources

arXiv2026

PAKE: Learning Whole-Body Loco-Manipulation with Partial Kinematic Embeddings

Loco-manipulation has recently shown promising capabilities; however, achieving high-precision control, managing the high-dimensional action space induced by many degrees of freedom (DoFs), and fully exploiting the inherent redundancy of whole-body systems remain challenging. In this paper, we propose a novel whole-body control framework that effectively addresses these challenges by decomposing the complex loco-manipulation problem into partial reference motion generation and low-level imitation control. We introduce a new Kinematic Normalizing Flow (KNF) model, trained on a large-scale kinematic dataset, that generates diverse yet feasible partial reference motions. A high-level controller is then trained to navigate the KNF's latent space to exploit redundant solutions, while a low-level controller ensures physically feasible and accurate motion execution. We validate our approach on the quadrupedal robot equipped with a six-DoF robotic arm. In simulation, experimental results show that our approach significantly outperforms state-of-the-art methods in terms of tracking accuracy and feasible workspace coverage. For hardware deployment, we evaluate the system over 24 episodes across 8 different mobile loco-manipulation tasks. The system achieves end-effector pose-tracking errors of 4.5 cm and 0.14 rad, while maintaining accurate locomotion tracking with linear and angular velocity errors of 0.1 m/s and 0.01 rad/s, respectively, outperforming competitive baselines. Our method represents a practical and powerful solution for accurate and generalized whole-body loco-manipulation in high-DoF robotic systems, with promising potential for diverse downstream robotic tasks.

cs.RO↗

arXiv2026

Mining and searching association relation of scientific papers based on deep learning

There is a complex correlation among the data of scientific papers. The phenomenon reveals the data characteristics, laws, and correlations contained in the data of scientific and technological papers in specific fields, which can realize the analysis of scientific and technological big data and help to design applications to serve scientific researchers. Therefore, the research on mining and searching the association relationship of scientific papers based on deep learning has far-reaching practical significance.

cs.DL↗

arXiv2026

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

Large language model (LLM) agents rely on reusable skills to solve complex tasks, but existing skill creation approaches often treat skills as isolated, static artifacts, limiting reusability, reliability, and long-term improvement. We propose MUSE-Autoskill Agent (Memory-Utilizing Skill Evolution), a skill-centric agent framework that creates, reuses, and refines skills under a unified lifecycle: creation, memory, management, evaluation, and refinement. MUSE creates skills on demand, stores them across tasks, retrieves them through a skill catalog, and accumulates per-skill experience for later reuse and adaptation. Across the main reported settings on SkillsBench and SkillLearnBench, MUSE-Autoskill outperforms Hermes, Codex, and Claude Code. On SkillsBench, its self-created skills surpass human-authored skills on the successfully covered subset (85.24% vs. 81.17%), showing that lifecycle-managed skills can distill agent experience into highly effective reusable assets; MUSE-created skills also transfer to Hermes more effectively than Codex- or Claude-created skills, reaching 51.90% accuracy under transfer. These results highlight the importance of treating skills as long-lived, experience-aware, and testable assets.

cs.AI↗

arXiv2026

Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning

Trajectory representation learning (TRL) aims to encode raw trajectory data into low-dimensional embeddings for downstream tasks such as travel time estimation, mobility prediction, and trajectory similarity analysis. From a behavioral perspective, a trajectory reflects a sequence of route choices within an urban environment. However, most existing TRL methods ignore this underlying decision-making process and instead treat trajectories as static, passive spatiotemporal sequences, thereby limiting the semantic richness of the learned representations. To bridge this gap, we propose CORE, a TRL framework that integrates context-aware route choice semantics into trajectory embeddings. CORE first incorporates a multi-granular Environment Perception Module, which leverages large language models (LLMs) to distill environmental semantics from point of interest (POI) distributions, thereby constructing a context-enriched road network. Building upon this backbone, CORE employs a Route Choice Encoder with a mixture-of-experts (MoE) architecture, which captures route choice patterns by jointly leveraging the context-enriched road network and navigational factors. Finally, a Transformer encoder aggregates the route-choice-aware representations into a global trajectory embedding. Extensive experiments on 4 real-world datasets across 6 downstream tasks demonstrate that CORE consistently outperforms 15 state-of-the-art TRL methods, achieving an average improvement of 9.20\% over the best-performing baseline. Our code is available at https://github.com/caoji2001/CORE.

cs.CV↗

arXiv2026

Fast Cross-Scenario Adaptation of CSI Models via Channel Conditional Parameter Generation

Deep learning has shown strong potential for massive multiple-input multiple-output (Massive MIMO) physical-layer tasks, including channel state information (CSI) feedback and channel estimation. However, environmental heterogeneity can severely degrade CSI models in unseen scenarios, while conventional adaptation requires target-domain data and substantial computation. This paper proposes Channel Conditional Parameter Generation (CCPG), an end-to-end pipeline for rapid deployment of CSI models in dynamic wireless environments. CCPG identifies scene-sensitive adaptation bottlenecks through component-freezing experiments and generates only lightweight LoRA weights instead of full model parameters. It compresses high-dimensional channel features into compact latent conditions using cascaded SVD and a Perceiver Resampler. An energy-based canonicalization mechanism mitigates permutation and sign ambiguities in LoRA weights, while a diffusion-based generator incorporates structural information and an asymmetric size-aware loss for topology-aware parameter generation. Experiments on DeepMIMO and WAIR-D for CSI feedback and channel estimation show that CCPG adapts to new scenarios in about 3 seconds with a single forward pass, without target-scenario training or fine-tuning, and achieves cross-domain recovery performance comparable to costly online adaptation. These results demonstrate that CCPG enables efficient deployment of CSI models in large-scale dynamic wireless scenarios for intelligent 6G communications.

cs.AI↗

arXiv2026

TAHOE: Text-to-SQL with Automated Hint Optimization from Experience

Large Language Models (LLMs) have democratized database access through Text-to-SQL, but moving from prototypes to production remains difficult. Real deployments must handle strict SQL dialects, massive schemas, and evolving user preferences, while supervised fine-tuning is costly and rigid and agentic test-time scaling is expensive. We present Tahoe, a system that treats prompt optimization as a dynamic data management problem. Tahoe uses an error-driven hint learning pipeline across Development and Deployment to consolidate debugging traces into a structured Hint Bank. Compiler feedback is distilled into reusable Syntax Hints for dialect-specific rules, while execution and user feedback are converted into Semantic Hints for schema- and user-specific logic. Tahoe further introduces a Strategy Layer that models conflicting user intents as competing strategies under shared natural-language triggers, with recency signals and post-learning attribution statistics that summarize empirical success, harm, inertness, and support. At inference time, Tahoe retrieves relevant hints and guides the LLM through Logic Planning followed by SQL Synthesis. We implement and evaluate the development-phase workflow, leaving deployment-time human-feedback updates for future work. On Spider 2.0-Snow, Tahoe substantially improves Text-to-SQL without updating model parameters. On 113 supervised Spider 2.0-Snow-0212 examples using GPT-5.5, Tahoe raises pass rate from 61.95 percent to 79.42 percent and pass-at-4 from 72.57 percent to 87.61 percent, achieves 100 percent Snowflake syntax pass rate, and reduces average compiler-feedback critic rounds from 2.79 to 0.12 per sampled candidate. The same Hint Bank also transfers to weaker backbones, including a 19.7 percentage-point pass-rate gain on Doubao-2.0-lite.

cs.DB↗

arXiv2026

ProOPF: Benchmarking and Improving LLMs for Professional-Grade Power Systems Optimization Modeling

Growing renewable penetration introduces substantial uncertainty into power system operations, necessitating frequent adaptation of dispatch objectives and constraints and challenging expertise-intensive, near-real-time modeling workflows. Large Language Models (LLMs) provide a promising avenue for automating this process by translating natural-language (NL) operational requirements into executable optimization models via semantic reasoning and code synthesis. Yet existing LLM datasets and benchmarks for optimization modeling primarily target coarse-grained cross-domain generalization, offering limited, rigorous evaluation in power-system settings, particularly for Optimal Power Flow (OPF). We therefore introduce \textbf{ProOPF-D} and \textbf{ProOPF-B}, a dataset and benchmark for professional-grade OPF modeling: ProOPF-D contains 12K instances pairing NL requests with parameter adjustments and structural extensions to a canonical OPF, together with executable implementations; ProOPF-B provides 121 expert-annotated test cases with ground-truth code, enabling end-to-end evaluation under both concrete and abstract OPF modeling regimes.

eess.SY↗

arXiv2026

Harnessing Individual Motivation for Collective Efficiency: A Mechanism-Driven Distributed Optimization Method

In industrial scenarios involving multi-agent collective decision-making, centralized decision-making may not be admissible due to restrictive access to individual local information, while the conflicts between participants' self-interest and global performance may also impede collaborative distributed decision-making. This paper proposes a mechanism-driven distributed decision-making method, wherein incentives are employed and designed to motivate participants to collaborate in a distributed fashion even though each participant's decision is driven primarily by self-interest. Focusing on optimization problems with coupled objective functions and coupled constraints, we design a distributed optimization algorithm tailored for this class of problems and provide guarantees for its convergence. Furthermore, we design two incentive mechanisms, the shadow pricing mechanism and the Vickrey-Clarke-Groves mechanism, and demonstrate that participants are willing to engage in distributed collaboration under these mechanisms. The mechanism drives the execution of the distributed algorithm, and the optimal result of distributed computation guides the determination of incentives in the mechanism, both of which are interrelated to form a closed loop. Finally, numerical experiments illustrate the effectiveness of the proposed algorithm and mechanisms.

math.OC↗

arXiv2026

SDSS+JWST Census of Stellar and Nebular Dust Attenuation at $z \sim 0$-7: Mass Dependence and Redshift Evolution

We present the demography of dust attenuation, including its mass dependence and redshift evolution, using spectroscopic samples of 34,182 SDSS galaxies at $z\sim0.1$ and 863 JWST/JADES galaxies at $z\sim1.5$--$7$. We find that, on average, ${\rm Hα}/{\rm Hβ}$ ratios are comparable to the Case B recombination value at $M_\ast \lesssim 10^9 M_\odot$, and increase beyond $M_\ast \sim 10^9 M_\odot$ both at $z\sim0.1$ and $1.5$--$7$. We derive the nebular attenuation $A_{\rm V, nebular}$ from Balmer decrements and the stellar attenuation $A_{\rm V, stellar}$ from rest-frame UV--optical spectra with supplementary \textit{GALEX} data, via comparisons with stellar-population models and multiple attenuation curves in a consistent manner across cosmic time. We find no significant redshift evolution of $A_{\rm V, nebular}$ and $A_{\rm V, stellar}$ at fixed $M_\ast$ over $z\sim0$--$7$, forming a universal extinction relation, and both rise from $0.2$--$0.4$ at $M_\ast \lesssim 10^9 M_\odot$ to $\sim1$ at $M_\ast \sim 10^{11} M_\odot$. Interestingly, at $M_\ast \gtrsim 10^9 M_\odot$, $A_{\rm V, nebular}$ rises more steeply than $A_{\rm V, stellar}$. This correlation holds within an uncertainty of $\sim\pm0.2$ for various combinations of attenuation curves (Calzetti, SMC, and Milky Way). These results indicate that $M_\ast \sim 10^9 M_\odot$ is a transition mass in dust attenuation, whose low-mass behavior reflects dust widely distributed by feedbacks. These mass-dependent extinction results address the long-standing issue of appropriate choice of the stellar-to-nebular color excess ratio, $f\equiv E(B-V)_{\rm stellar}/E(B-V)_{\rm nebular}=1.0$ or $0.44$, and suggest that galaxy $M_\ast$ determines $f$ from $\sim1.0$ to $\sim0.44$ across low- to high-mass galaxies.

astro-ph.GA↗

arXiv2026

Robustness Analysis of USmorph: II. Optimizing Feature Extraction, Dimensionality Reduction, and Clustering for Unsupervised Galaxy Morphology Classification

We conduct a systematic robustness analysis of the unsupervised machine learning module within the hybrid framework \texttt{USmorph}. This module automatically discovers morphological structures from large-scale galaxy images, forming the foundation of the complete classification workflow. We evaluate five pre-trained models for feature extraction and identify an ImageNet-pretrained AlexNet as the most effective for capturing discriminative morphological features. UMAP is chosen for dimensionality reduction due to its optimal balance between preserving high-dimensional structure and computational efficiency. To enhance clustering stability, we propose a Bagging-based multi-cluster voting scheme, which significantly improves label consistency and cluster purity. We compare the convergence, scalability, and quality of five clustering algorithms, finding that the Bagging voting scheme has the best performance with the combination of K-means, Birch, and Agg. A bagging clustering number of $K=16$ is used to achieve the optimal balance between classification granularity and manual validation efficiency. Our tests show that: (1) the t-distributed stochastic neighbor embedding (t-SNE) reveals clear, compact cluster boundaries in low-dimensional space with strong feature separability; (2) the morphology classification results align with galaxy evolution theory, showing physically plausible distributions of different types in parameter space. These results demonstrate the technical robustness and scientific credibility of \texttt{USmorph}, establishing it as a reliable method for automated morphological classification in future large-scale surveys such as the China Space Station Telescope (CSST) mission.

astro-ph.GA↗

arXiv2026

Difference Between Half-mass Radius and Half-light Radius of Galaxies at 0.2 $< z <$ 2.5 Revealed by JWST/NIRCam Data

Using JWST observations in CANDELS fields, we measure the half-light radius ($r_{\rm e,light}$) and half-mass radius ($r_{\rm e,mass}$) for 14,333 galaxies with stellar masses $M_* > 10^9 M_\odot$ at redshifts $0.2 < z < 2.5$. To investigate the difference between $r_{\rm e,light}$ and $r_{\rm e,mass}$, we find that $r_{\rm e,light}$ is larger than $r_{\rm e,mass}$ for both quiescent galaxies (QGs) and star-forming galaxies (SFGs). Moreover, the difference between these two radii is clearly correlated with galaxy stellar mass, $r_{\rm e,light}$, and the rest-frame $U - V$ color. When examining the evolution of the $r_{\rm e,mass}/r_{\rm e,light}$ ratio, we observe a significant increase for SFGs at $z > 1.7$. In contrast, no clear increase is observed for QGs at $z > 1$, though a slight decreasing trend is seen between $0.2 < z < 1.0$. By fitting a linear relationship between galaxy size and stellar mass, we find that the slope for $r_{\rm e,light}$ is $\sim$ 0.1 to 0.3 dex larger than that for $r_{\rm e,mass}$. In terms of galaxy size evolution at a fixed stellar mass, the $r_{\rm e,mass}$ of QGs increases by a factor of $\sim$ 3 to 5 from $z \sim 2.5$ to $z \sim 0.2$. In contrast, the $r_{\rm e,mass}$ of SFGs increases by a factor of approximately 2 over the same redshift range, with this growth trend closely following that of their $r_{\rm e,light}$. These results indicate that previous insights into galaxy evolution based on $r_{\rm e,light}$ remain valid when considering $r_{\rm e,mass}$, although the specific slopes show some variations.

astro-ph.GA↗

arXiv2026

Learning Dynamic Pick-and-Place for a Legged Manipulator

Legged manipulators extend robotic capabilities beyond static manipulation by integrating agile locomotion with versatile arm control. However, achieving precise manipulation while maintaining coordinated locomotion remains a major challenge. This work presents a hierarchical reinforcement learning framework for dynamic pick-and-place tasks using a quadruped equipped with a 6-DOF robotic arm. The framework incorporates an explicit mass estimation module enabling adaptive whole-body control for objects with varying weights. In simulation, the system achieves an 86.05% success rate with payloads up to 2.3 kg. The approach is further validated through real-world experiments across six representative scenarios with controlled variations in object physical properties (size and mass) and task heights. Specifically, within a wide vertical workspace ranging from ground level to 1.1~m-high tabletops, the system demonstrates an average success rate of 73.3% for payloads up to 1.3 kg, with an average execution time of 4.06 s. Unlike prior works that handle lightweight objects and execute pick-and-place motions with slow, piecewise motions, the proposed framework exploits concurrent locomotion and manipulation for dynamic, continuous execution. These results demonstrate the potential of quadrupedal mobile manipulators for adaptive, whole-body pick-and-place with heavier payloads and extended workspaces.

cs.RO↗

arXiv2026

OptArgus: A Multi-Agent System to Detect Hallucinations in LLM-based Optimization Modeling

Large language models (LLMs) are increasingly used to translate natural-language optimization problems into mathematical formulations and solver code, but matching the reference objective value is not a reliable test of correctness: an artifact may agree numerically while still changing the underlying optimization semantics. We formulate this issue as \emph{optimization-modeling hallucination detection}, namely structural consistency auditing over the problem description, symbolic model, and solver implementation. We develop, to our knowledge, the first fine-grained hallucination taxonomy specifically for optimization modeling, spanning objective, variable, constraint, and implementation failures. We use this taxonomy to design OptArgus, a multi-agent detector with conductor routing, specialist auditors, and evidence consolidation. To evaluate this setting, we introduce a three-part benchmark suite with $484$ clean artifacts, $1266$ controlled injected artifacts, and $6292$ natural LLM-generated artifacts. Against a matched single-agent baseline, OptArgus produces fewer false alarms on clean artifacts, more accurate top-ranked localization on controlled single-error cases, and stronger detection on natural model outputs. Together, these contributions turn optimization-modeling hallucination detection into a concrete empirical problem and suggest that modular, taxonomy-grounded auditing is a practical route to more reliable optimization modeling.

cs.AI↗

arXiv2026

Dissecting the superradiant phase transition in the anisotropic Rabi model: Pattern competition and cavity-QED simulation

In this manuscript, we analyze the mechanism of the superradiant phase transition in the anisotropic Rabi model under the classical oscillator limit using the pattern picture. By expanding the anisotropic Rabi model Hamiltonian in operator space, we obtained three patterns, and we find that the phase transition arises from the competition between patterns. The difficulty in achieving the classical oscillator limit motivates our investigation into the quantum phase transition within a parametrically-driven Jaynes-Cummings model. This parametrically-driven Jaynes-Cummings model can reproduce the dynamics of an ultrastrong-coupling anisotropic Rabi model in a squeezed-light frame. According to the eigenenergies and eigenstates of the normal and superradiant phases of this equivalent anisotropic Rabi model, we find that the excitation energy of the normal phase and the superradiant phase vanishes at the critical point. The photon number becomes infinite beyond the critical point. These results indicate that the system undergoes a superradiant phase transition at the critical point.

quant-ph↗

arXiv2026

Sampling-Aware Quantization for Diffusion Models

Diffusion models have recently emerged as the dominant approach in visual generation tasks. However, the lengthy denoising chains and the computationally intensive noise estimation networks hinder their applicability in low-latency and resource-limited environments. Previous research has endeavored to address these limitations in a decoupled manner, utilizing either advanced samplers or efficient model quantization techniques. In this study, we uncover that quantization-induced noise disrupts directional estimation at each sampling step, further distorting the precise directional estimations of higher-order samplers when solving the sampling equations through discretized numerical methods, thereby altering the optimal sampling trajectory. To attain dual acceleration with high fidelity, we propose a sampling-aware quantization strategy, wherein a Mixed-Order Trajectory Alignment technique is devised to impose a more stringent constraint on the error bounds at each sampling step, facilitating a more linear probability flow. Extensive experiments on sparse-step fast sampling across multiple datasets demonstrate that our approach preserves the rapid convergence characteristics of high-speed samplers while maintaining superior generation quality. Code is publicly available at: https://github.com/TaylorJocelyn/Sampling-aware-Quantization.

cs.CV↗

arXiv2026

Evolutionary Negative Module Pruning for Better LoRA Merging

Merging multiple Low-Rank Adaptation (LoRA) experts into a single backbone is a promising approach for efficient multi-task deployment. While existing methods strive to alleviate interference via weight interpolation or subspace alignment, they rest upon the implicit assumption that all LoRA matrices contribute constructively to the merged model. In this paper, we uncover a critical bottleneck in current merging paradigms: the existence of $\textit{negative modules}$ -- specific LoRA layers that inherently degrade global performance upon merging. We propose $\textbf{E}$volutionary $\textbf{N}$egative $\textbf{M}$odule $\textbf{P}$runing ($\textbf{ENMP}$), a plug-and-play LoRA pruning method to locate and exclude these detrimental modules prior to merging. By leveraging an evolutionary search strategy, ENMP effectively navigates the discrete, non-differentiable landscape of module selection to identify optimal pruning configurations. Extensive evaluations demonstrate that ENMP consistently boosts the performance of existing merging algorithms, achieving a new state-of-the-art across both language and vision domains. Code is available at https://github.com/CaoAnda/ENMP-LoRAMerging.

cs.AI↗

arXiv2026

Discovery of low-redshift analogues to "Little Red Dots" in DESI: A later evolutionary stage of compact LRDs?

The James Webb Space Telescope (JWST) has recently discovered a population of compact, red sources at z > 4 known as "Little Red Dots" (LRDs). They are characterized by their V-shaped continuum spectra and prominent broad Balmer emission lines. As their underlying physical nature remains debated and direct study at high-redshift is challenging; therefore, we seek to identify and characterize LRD analogues in the low-redshift universe to constrain their properties and potential evolutionary pathways. We identified five candidates at z = 0.2-0.4 from the Dark Energy Spectroscopic Instrument (DESI) that exhibit spectral energy distributions (SEDs) and broad Balmer emission lines closely resembling their high-redshift counterparts. However, we find significant differences: our low-redshift sample occupies a different region on the Baldwin, Phillips \& Terlevich (BPT) diagram, and their stellar masses are significantly higher, suggesting a more substantial host galaxy contribution. These sources are not necessarily direct local analogues of high-redshift LRDs, but may represent later evolutionary stages of compact, rapidly accreting systems, or systems with related observational properties arising under different physical conditions. This sample provides a valuable laboratory for detailed follow-up studies to elucidate the nature of LRD-like phenomena.

astro-ph.GA↗

arXiv2026

Variance-Reduced Gradient Estimator for Nonconvex Zeroth-Order Distributed Optimization

This paper investigates distributed zeroth-order optimization for smooth nonconvex problems, targeting the trade-off between convergence rate and sampling cost per zeroth-order gradient estimation in current algorithms that use either the $2$-point or $2d$-point gradient estimators. We propose a novel variance-reduced gradient estimator that either randomly renovates a single orthogonal direction of the true gradient or calculates the gradient estimation across all dimensions for variance correction, based on a Bernoulli distribution. Integrating this estimator with gradient tracking mechanism allows us to address the trade-off. We show that the oracle complexity of our proposed algorithm is upper bounded by $O(d/ε)$ for smooth nonconvex functions and by $O(dκ\ln (1/ε))$ for smooth and gradient dominated nonconvex functions, where $d$ denotes the problem dimension and $κ$ is the condition number. Numerical simulations comparing our algorithm with existing methods confirm the effectiveness and efficiency of the proposed gradient estimator.

math.OC↗