Searcharxiv⌕ Search

arXiv subjects

Jie Song

Publications and source records attributed to Jie Song.

At least 19 recordsLinked to original sources
arXiv2026

OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology Normalization

Biomedical ontology normalization maps free-text expressions to standardized concepts, enabling consistent integration and analysis of biomedical data. This task remains challenging because lexical variation and subtle distinctions among hierarchically related concepts can obscure concept boundaries. We present OntologyAligner, a three-stage framework that combines ontology-aligned retrieval, large language model candidate reranking, and selective hierarchy-guided refinement. We also construct PhenoNormBench, a unified benchmark comprising 13,390 samples from seven Human Phenotype Ontology datasets. OntologyAligner achieved state-of-the-art performance on HPO normalization, with 88.78% Macro Top-1 Accuracy and 86.75% Micro Top-1 Accuracy, exceeding the strongest baseline by 4.85 and 5.07 percentage points, respectively. Ablation analyses showed complementary contributions from all three stages, and sensitivity analyses demonstrated stability across candidate-set sizes and model backbones. Applications to MONDO, MEDIC, and NCBITaxon further established portability to other ontologies. OntologyAligner offers a generalizable framework for accurate mapping of biomedical text to structured ontology concepts. PhenoNormBench and the code are publicly available at https://github.com/zhelishisongjie/OntologyAligner.

cs.AI↗
arXiv2026

Assembling Two Parts in One Hand

A hallmark of human dexterity is the cooperative use of fingers, where different fingers take on distinct yet coordinated roles to accomplish fine manipu- lation, such as capping a pen with the hand that holds it. We study this finger-level coordination through in-hand assembly: mating two rigid objects within a single dexterous hand, with no second arm and no fixture. We present a reinforcement learning formulation to solve this problem in a unified framework, which is driven by a goal relative pose between the two parts. Finger coordination is shaped by a function-based auxiliary reward and regularized toward a single human reference pose, while domain randomization and a fusion of historical proprioception and object observation confer robustness to occlusion-induced estimation noise. The same recipe solves three different assembly tasks (Bottle, Syringe, and Marker). Trained purely in simulation, the policies transfer zero-shot to hardware with a single camera, demonstrating robustness to state-estimation errors caused by oc- clusion. Our experiments also reveal that in-hand assembly places demands on hand morphology and can serve as a benchmark for modern robotic hand systems. Videos and code are available at https://ltbgbird.github.io/in-hand-assembly-page/.

cs.RO↗
arXiv2026

Searching for Type Ia Supernovae in the Dark Energy Spectroscopic Instrument

With the development of large-scale photometric surveys, an increasing number of supernova candidates are being discovered, leading to a rapidly growing demand for supernova spectra. In addition to equipping photometric surveys with follow-up spectroscopic facilities, archival spectra from large multi-object spectroscopic surveys can be mined to provide spectroscopic classifications for candidates and to find supernovae missed by previous surveys. In this work, we combine Principal Component Analysis (PCA), the Local Outlier Factor (LOF) algorithm, and the supernova classification tool SNID to search for Type Ia supernovae among 1,757,303 galaxy spectra from the Dark Energy Spectroscopic Instrument (DESI) Data Release 1 (DR1). We finally obtain 247 Type Ia supernovae and 17 supernovae of other types. Among these, 202 supernovae lack classification records in the Transient Name Server (TNS) and represent newly identified SNe. These results demonstrate the potential of multi-object spectroscopic surveys to supplement supernova samples, particularly for transients missed by traditional photometric surveys.

astro-ph.HE↗
arXiv2026

ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Models

Large Language Models (LLMs) have been increasingly adopted in Text-to-SQL systems, yet SQL errors remain a major obstacle in real-world Text-to-SQL inference pipelines. Existing SQL correction approaches either rely on large-scale, high-quality training data with substantial overhead, or adopt single-path agentic workflows that are brittle to early mistakes and prone to error propagation. To develop a practical SQL correctness system for industrial scenarios, we present a training-free framework that formulates SQL correction as a plan-guided, tree-structured debugging process. By maintaining multiple correction strategies and enabling backtracking, the framework mitigates error accumulation during iterative refinement. We further integrate execution-based verification and clause-level diagnostic tools to support strategy pruning and precise error localization. We evaluate the system on the BIRD-Critic benchmark and observe consistent accuracy gains over strong LLM backbones and representative agent-based baselines, achieving a 9.42% improvement over the previous state-of-the-art method. The framework is also deployed in the Torch Log Service (TLS) of Volcano Engine to support an online Text-to-TLS API. In production, it improves execution accuracy from 36.77% to 53.61% on real user queries with a representative strong LLM backbone (GPT-5). These results demonstrate the effectiveness and stability of our approach in real-world deployments.

cs.AI↗
arXiv2026

Channel-wise Dynamic Knowledge Distillation via Adaptive Sample Generation for Action Recognition

Knowledge Distillation (KD) offers a promising yet underexplored path for compressing large action recognition models. However, existing KD methods suffer from two key limitations: 1) reliance on fixed input samples leads to suboptimal feature alignment between the frozen teacher (larger model) and the learnable student (smaller model), and 2) applying a uniform distillation strength for all channels fails to account for their varying importance in capturing distinct knowledge (e.g., motion tempo or magnitude) across training epochs. This motivates us to develop an Adaptive Sample-aware Channel-wise Dynamic (ASCD) KD approach, which operates in two stages. First, we use an adaptive sample generation module to create updated samples by incorporating semantics from sample gradients, which are derived by minimizing a feature loss weighted by channel centroid frequency differences at each layer. Meanwhile, crucial motion-related details are preserved by applying a Gaussian mask to frequency features. Second, we employ a channel-wise dynamic distillation module to train student on these generated samples, guided by sample gradients and feature frequencies. For efficiency, samples are updated periodically rather than per epoch. Extensive experiments on three video benchmarks (UCF101, Kinetics-400, Something-Something-v2) and two image datasets (CIFAR-100, ImageNet) demonstrate the state-of-the-art performance of our method. Code is available at https://github.com/mlvccn/ASCD_KD_Action.

cs.CV↗
arXiv2026

CoEvoKG: Co-Evolving Knowledge Graphs with Self-Evolving Search Agents

Large language models can improve with reinforcement learning for search agents, yet existing self play agents repeatedly generate tasks while discarding the knowledge gained during successful searches. We introduce CoEvoKG, a framework that turns a knowledge graph into both a source of verifiable training tasks and a persistent evidence memory for agent evolution. CoEvoKG jointly trains a task generator and a search agent: the generator creates multihop questions from entity chains sampled from the knowledge graph, while the agent learns from rewards for answer correctness and search trajectories whose entity paths are supported by graph evidence. When a search succeeds, CoEvoKG verifies and deduplicates the retrieved evidence, then writes it back to the corresponding graph nodes and edges. Future rounds reuse this enriched graph for task generation and reward computation, closing the loop between model self evolution and knowledge accumulation. Experiments on six QA benchmarks (NQ, TriviaQA, PopQA, HotpotQA, 2WikiMultiHopQA, and Bamboogle) with three backbone models show that CoEvoKG improves macro average accuracy over the corresponding base models by +11.2, +10.1, and +11.6 points on Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct, and Llama-3.1-8B-Instruct, respectively. Under matched training budgets, CoEvoKG further improves over competitive self play baselines and RL baselines for search agents by +2.6 to +3.7 macro average points across the three backbones. Code is available at https://github.com/lazzy1225/CoEvoKG.

cs.AI↗
arXiv2026

Geometry-guided Emotion Modulation for Controllable and Photorealistic Emotional Talking Face Generation

Audio-driven emotional talking face generation aims to synthesize realistic videos with expressive facial dynamics. However, existing methods struggle to balance controllability and visual fidelity. Although implicit representations capture rich semantics, they lack structural guidance, often resulting in averaged emotional expressions. In contrast, explicit geometric methods offer better control over facial expressions but tend to sacrifice high-frequency texture details. To address it, we propose GemTalk, a diffusion-based framework that combines the semantic richness of implicit representations with the structural precision of explicit geometric priors. We introduce a Vision-guided Audio Emotion Projection (V-AEP) module to extract implicit emotional lip and expression features. At the same time, a Diffusion-based Geometric Priors Generator (D-GPG) generates identity-aware blendshape coefficients as explicit structural priors. Crucially, our Geometry-guided Emotion Modulation (GEM) module leverages these geometric priors to recalibrate the magnitude of implicit features, enabling precise, continuous control over emotional expressions, especially emotion intensity, without sacrificing visual quality. Extensive experiments show GemTalk achieves superior performance in photo-realism, and facial emotional dynamics.

cs.CV↗
arXiv2026

UniCross: Unified Cross-Skill Dexterous Manipulation Synthesis

Many dexterous manipulation tasks require the object to remain securely held throughout the interaction. From the perspective of hand-object relational motion, such manipulation comprises four canonical skills: grasping, relocation, in-hand rotation, and in-hand translation. Human hands flexibly compose these skills to accomplish complex tasks. Existing approaches, however, model these skills separately with skill-specific action constraints, objectives, or even dedicated hand morphologies, which breaks the compatibility and continuity required for long-horizon composition. In this work, we present a unified framework that models all four skills in a single formulation that shares the same state and action spaces and a common objective structure. This formulation enables straightforward distillation of a single cross-skill policy that performs strongly on every skill, generalizes to unseen objects, stays robust to disturbances, and chains skills seamlessly into long-horizon manipulation. The framework also transfers effectively across different hand morphologies. Overall, our results suggest that different dexterous manipulation skills can be viewed as instantiations of a shared task formulation, revealing the intrinsic consistency across different behaviors.

cs.RO↗
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

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

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

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, ${\rm H\alpha}/{\rm H\beta}$ 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↗