Searcharxiv⌕ Search

arXiv subjects

Yixing Chen

Publications and source records attributed to Yixing Chen.

9 recordsLinked to original sources
arXiv2026

XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment

Robot policy evaluation and deployment remain fragmented by model-specific software dependencies, data representations, and runtime interfaces, so that connecting N policies to M evaluation environments requires O(NM) separate integrations. We present XPolicyLab, a unified standard and open ecosystem that reduces this cost to O(N+M). XPolicyLab specifies common observation, action, and trajectory schemas together with a minimal adapter interface for observation updates, action prediction, batched execution, and episode reset, while a dependency-isolated client/server architecture separates policy inference from environment execution, so that each side retains its native software stack and may run locally or remotely. The ecosystem integrates 42 robot policies and standardizes their installation, debugging, serving, and evaluation workflows. Across these adapters, model-specific code varies by an order of magnitude while the environment-facing loop stays within a few lines of a fixed reference, confirming that the contract confines heterogeneity to the policy side. In a controlled study, conforming to the standard reduces the integration effort of a representative policy from over five hours to two hours, and packaged agent skills reduce it further to thirty minutes. The same adapters serve RoboTwin, RoboDojo simulation, and standardized real-robot evaluation through one interface. XPolicyLab is released as shared infrastructure for reproducible policy comparison and standardized deployment across simulation and physical platforms. Project website: https://xpolicylab.github.io/.

cs.RO↗
arXiv2025

A robust method for identifying Be stars in the LAMOST Data Release 11 based on Deep-learning approach

Be stars are rapidly rotating B-type stars that exhibit Balmer emission lines in their optical spectra. These stars play an important role in studies of stellar evolution and disk structures. In this work, we carried out a systematic search for Be stars based on LAMOST spectroscopic data. Using low-resolution spectra from LAMOST DR11, we constructed a data set and developed a classification model that combines long short-term memory networks and convolutional neural networks , achieving a testing accuracy of 97.86%. The trained model was then applied to spectra with signal-to-noise ratios greater than 10, yielding 55,667 B-type candidates. With the aid of the MKCLASS automated classification tool and manual verification, we finally confirmed 40,223 B-type spectra. By cross-matching with published H{\alpha} emission-line star catalogs, we obtained a sample of 8298 Be stars, including 3787 previously reported Be stars and 4511 newly discovered. Furthermore, by incorporating color information, we classified the Be star sample into Herbig Be stars and Classical Be stars. In total, we identified 3363 Classical Be stars and 35 Herbig Be stars. The B-type and Be star catalogs derived in this study, together with the code used for model training, have been publicly released to facilitate community research.

astro-ph.SR↗
arXiv2025

Multi-Agent Evolve: LLM Self-Improve through Co-evolution

Reinforcement Learning (RL) has demonstrated significant potential in enhancing the reasoning capabilities of large language models (LLMs). However, the success of RL for LLMs heavily relies on human-curated datasets and verifiable rewards, which limit their scalability and generality. Recent Self-Play RL methods, inspired by the success of the paradigm in games and Go, aim to enhance LLM reasoning capabilities without human-annotated data. However, their methods primarily depend on a grounded environment for feedback (e.g., a Python interpreter or a game engine); extending them to general domains remains challenging. To address these challenges, we propose Multi-Agent Evolve (MAE), a framework that enables LLMs to self-evolve in solving diverse tasks, including mathematics, reasoning, and general knowledge Q&A. The core design of MAE is based on a triplet of interacting agents (Proposer, Solver, Judge) that are instantiated from a single LLM, and applies reinforcement learning to optimize their behaviors. The Proposer generates questions, the Solver attempts solutions, and the Judge evaluates both while co-evolving. Experiments on Qwen2.5-3B-Instruct demonstrate that MAE achieves an average improvement of 4.54% on multiple benchmarks. These results highlight MAE as a scalable, data-efficient method for enhancing the general reasoning abilities of LLMs with minimal reliance on human-curated supervision.

cs.AI↗
arXiv2025

ArtGS:3D Gaussian Splatting for Interactive Visual-Physical Modeling and Manipulation of Articulated Objects

Articulated object manipulation remains a critical challenge in robotics due to the complex kinematic constraints and the limited physical reasoning of existing methods. In this work, we introduce ArtGS, a novel framework that extends 3D Gaussian Splatting (3DGS) by integrating visual-physical modeling for articulated object understanding and interaction. ArtGS begins with multi-view RGB-D reconstruction, followed by reasoning with a vision-language model (VLM) to extract semantic and structural information, particularly the articulated bones. Through dynamic, differentiable 3DGS-based rendering, ArtGS optimizes the parameters of the articulated bones, ensuring physically consistent motion constraints and enhancing the manipulation policy. By leveraging dynamic Gaussian splatting, cross-embodiment adaptability, and closed-loop optimization, ArtGS establishes a new framework for efficient, scalable, and generalizable articulated object modeling and manipulation. Experiments conducted in both simulation and real-world environments demonstrate that ArtGS significantly outperforms previous methods in joint estimation accuracy and manipulation success rates across a variety of articulated objects. Additional images and videos are available on the project website: https://sites.google.com/view/artgs/home

cs.RO↗
arXiv2025

KETA: Kinematic-Phrases-Enhanced Text-to-Motion Generation via Fine-grained Alignment

Motion synthesis plays a vital role in various fields of artificial intelligence. Among the various conditions of motion generation, text can describe motion details elaborately and is easy to acquire, making text-to-motion(T2M) generation important. State-of-the-art T2M techniques mainly leverage diffusion models to generate motions with text prompts as guidance, tackling the many-to-many nature of T2M tasks. However, existing T2M approaches face challenges, given the gap between the natural language domain and the physical domain, making it difficult to generate motions fully consistent with the texts. We leverage kinematic phrases(KP), an intermediate representation that bridges these two modalities, to solve this. Our proposed method, KETA, decomposes the given text into several decomposed texts via a language model. It trains an aligner to align decomposed texts with the KP segments extracted from the generated motions. Thus, it's possible to restrict the behaviors for diffusion-based T2M models. During the training stage, we deploy the text-KP alignment loss as an auxiliary goal to supervise the models. During the inference stage, we refine our generated motions for multiple rounds in our decoder structure, where we compute the text-KP distance as the guidance signal in each new round. Experiments demonstrate that KETA achieves up to 1.19x, 2.34x better R precision and FID value on both backbones of the base model, motion diffusion model. Compared to a wide range of T2M generation models. KETA achieves either the best or the second-best performance.

cs.CV↗
arXiv2023

From Stars to Insights: Exploration and Implementation of Unified Sentiment Analysis with Distant Supervision

Sentiment analysis is integral to understanding the voice of the customer and informing businesses' strategic decisions. Conventional sentiment analysis involves three separate tasks: aspect-category detection, aspect-category sentiment analysis, and rating prediction. However, independently tackling these tasks can overlook their interdependencies and often requires expensive, fine-grained annotations. This paper introduces unified sentiment analysis, a novel learning paradigm that integrates the three aforementioned tasks into a coherent framework. To achieve this, we propose the Distantly Supervised Pyramid Network (DSPN), which employs a pyramid structure to capture sentiment at word, aspect, and document levels in a hierarchical manner. Evaluations on multi-aspect review datasets in English and Chinese show that DSPN, using only star rating labels for supervision, demonstrates significant efficiency advantages while performing comparably well to a variety of benchmark models. Additionally, DSPN's pyramid structure enables the interpretability of its outputs. Our findings validate DSPN's effectiveness and efficiency, establishing a robust, resource-efficient, unified framework for sentiment analysis.

cs.CL↗
arXiv2022

Charge gradients around dendritic voids cause nanoscale inhomogeneities in liquid water

Water is the matrix of life and is generally considered a homogeneous, uniform, liquid. Recent experiments report that water is instead a two-state liquid. However, subsequently, these findings were contested. The structure of water and whether we should think of it as uniform therefore remains an open question. Here, we report femtosecond elastic second harmonic scattering (fs-ESHS) of liquid water in comparison to an isotropic liquid (CCl4) and show that water is indeed a non-uniform liquid, The coherent fs-ESHS intensity was interpreted, using molecular dynamics simulations, as arising from charge density fluctuations and consequentially enhanced nanoscale polarizabilities around transient voids having an average lifetime of 300 fs. Although voids were also present in CCl4, they were not characterized by hydrogen bond defects and did not show strong polarizability fluctuations, leading to fs-ESHS of an isotropic liquid. The voids increased in number at higher temperatures above room temperature, in agreement with the fs-ESHS results. The measured nanoscale-femtosecond inhomogeneities therefore do not necessarily relate to the proposed two state model of water, but instead underscore the elusive nature of liquid water, and undoubtedly have an impact on any type of transition that occurs in liquid water.

physics.chem-ph↗
arXiv2021

Urban Building Energy Modeling (UBEM) Tools: A State-of-the-Art Review of bottom-up physics-based approaches

Regulations corroborate the importance of retrofitting existing building stocks or constructing new energy efficient district. There is, thus, a need for modeling tools to evaluate energy scenarios to better manage and design cities, and numerous methodologies and tools have been developed. Among them, Urban Building Energy Modeling (UBEM) tools allow the energy simulation of buildings at large scales. Choosing an appropriate UBEM tool, balancing the level of complexity, accuracy, usability, and computing needs, remains a challenge for users. The review focuses on the main bottom-up physics-based UBEM tools, comparing them from a user-oriented perspective. Five categories are used: (i) the required inputs, (ii) the reported outputs, (iii) the exploited workflow, (iv) the applicability of each tool, and (v) the potential users. Moreover, a critical discussion is proposed focusing on interests and trends in research and development. The results highlighted major differences between UBEM tools that must be considered to choose the proper one for an application. Barriers of adoption of UBEM tools include the needs of a standardized ontology, a common three dimensional city model, a standard procedure to collect data, and a standard set of test cases. This feeds into future development of UBEM tools to support cities' sustainability goals.

cs.CY↗