arXiv subjects

Yanxin Chen

Publications and source records attributed to Yanxin Chen.

11 recordsLinked to original sources

arXiv2026

LLM4LLM: Bridging Kernel Benchmarks and Real Deployment via Closed-Loop Agentic Optimization

Large language models have become increasingly capable agents for low-level code and kernel optimization, but isolated kernel benchmarks provide only a proxy for the deployment behavior that matters in language-model inference. We identify a benchmark-to-deployment gap: candidate kernels that appear correct and fast in standalone harnesses can exhibit different performance, safety, or phase behavior after integration into a real inference workload. We introduce LLM4LLM, a deployment-aware closed-loop optimization framework that starts from a target inference script, extracts phase-aware optimization tasks, searches with an experience-guided episodic agent, and accepts patches through in-model validation. Across ten language-model inference workloads on A100 and H100 GPUs, LLM4LLM improves end-to-end latency for every evaluated model, achieving 3.91$\times$/6.98$\times$ geometric-mean speedups on A100/H100; as supporting kernel-level evidence, it also attains up to 2.745$\times$ GeoMean speedup on KernelBench Level 2.

cs.AI↗

arXiv2026

MOSS-VL Technical Report

We present MOSS-VL, an open vision-language model family that treats real-time interaction -- perceiving while it speaks -- as a first-class capability. It is co-designed across the stack: the language decoder attends to vision only through gated cross-attention, so the model can naturally see incoming frames while generating; a synthesized interaction corpus supervises when to speak, when to stay silent, and when to revise; and a staged curriculum concentrates all real-time-specific training in one light final stage over a strong offline foundation. Offline, MOSS-VL-Instruct is competitive at comparable scale and leads temporal-reasoning video sets. Across four streaming benchmarks, MOSS-VL-Realtime posts the best average on three (second on the fourth) among open-source streaming models, sweeping the three subsets that squarely test proactive behavior -- 66.0 vs. 37.5 for the best baseline on OmniMMI Proactive Alerting. With 11.3B parameters but visual tokens outside the decoded sequence, MOSS-VL widens its time-to-first-token advantage over same-backbone Qwen3-VL-8B from 2.8x to 5.1x as visual context grows. We release all five checkpoints, the training curriculum, and the real-time inference code at https://github.com/OpenMOSS/MOSS-VL.

cs.CV↗

arXiv2026

MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention

Video understanding is shifting from the offline paradigm -- taking a fully recorded video as input and producing a single answer after it ends -- toward real-time interaction, in which the model perceives new frames while still replying, revises its answer as new evidence appears, and remains silent when there is nothing to say. We present MOSS-Video-Preview to validate this paradigm. Our central claim is that perception must not be blocked by generation; its natural realization is a two-channel architecture. We argue that a cross-attention backbone is better suited to real-time vision-language fusion than the prevailing decoder-only design: visual features enter through a side channel rather than joining the autoregressive sequence, so perception and generation run on separate, non-blocking pathways -- reducing the frequency of visual processing and exposing a clean channel-wise interface for independent compression. We complement this with a data synthesis pipeline that converts dense captions into real-time understanding QA whose answers are revised to match what the model has perceived so far, and we specialize an offline model on these data to elicit real-time behavior. Our model trails the strong Qwen2.5-VL-7B baseline overall -- a gap we attribute primarily to data and scale rather than the architecture -- yet attains competitive offline video and multimodal understanding, remains robust on the spatial and fine-grained temporal reasoning central to real-time use, and acquires behaviors that offline models lack: continuous perception, answer revision, and timely silence. On a single H200 with 256 frames per video, it achieves about a 5x speedup in time to first token and 2.7x higher decoding throughput, with negligible degradation in offline ability. Our study of paradigm, architecture, and data outlines a viable path toward real-time video understanding.

cs.CV↗

arXiv2026

MDS and NMDS Codes from the Extended Twisted Generalized Reed-Solomon Codes

This paper contributes to maximum distance separable (MDS) and near MDS (NMDS) properties of the extended generalized twisted Reed-Solomon (TGRS) codes. Firstly, a family of extended TGRS (ETGRS) are constructed by appending three columns to the generator matrix of original TGRS codes. Secondly, the necessary and sufficient conditions for these codes to be MDS or almost MDS (AMDS) codes are derived. Then, by analyzing the AMDS properties of their dual codes, the necessary and sufffcient conditions for them to be NMDS codes are established. Furthermore, some examples are given to verify the main results. Finally, we determine the non-generalized Reed-Solomon (non-GRS) characteristics of them via the Schur product method.

cs.IT↗

arXiv2026

Self-Orthogonal Twisted Generalized Reed-Solomon Codes and Their Application to Quantum Error-Correcting Codes

In this paper, two classes of twisted generalized Reed-Solomon (TGRS) codes with multi-twists are studied. Firstly, some sufficient and necessary conditions for these codes to be self-orthogonal and self-dual are established. Then several explicit constructions of self-orthogonal and self-dual codes are presented, from which quantum stabilizer codes are further derived. Finally, some corresponding examples are given, especially that some of these codes are MDS, AMDS or NMDS and that some of the resulting quantum stabilizer codes are optimal, achieving the quantum Singleton bound.

cs.IT↗

arXiv2025

"I Don't Think RAI Applies to My Model'' -- Engaging Non-champions with Sticky Stories for Responsible AI Work

Responsible AI (RAI) tools -- checklists, templates, and governance processes -- often engage RAI champions, individuals intrinsically motivated to advocate ethical practices, but fail to reach non-champions, who frequently dismiss them as bureaucratic tasks. To explore this gap, we shadowed meetings and interviewed data scientists at an organization, finding that practitioners perceived RAI as irrelevant to their work. Building on these insights and theoretical foundations, we derived design principles for engaging non-champions, and introduced sticky stories -- narratives of unexpected ML harms designed to be concrete, severe, surprising, diverse, and relevant, unlike widely circulated media to which practitioners are desensitized. Using a compound AI system, we generated and evaluated sticky stories through human and LLM assessments at scale, confirming they embodied the intended qualities. In a study with 29 practitioners, we found that, compared to regular stories, sticky stories significantly increased time spent on harm identification, broadened the range of harms recognized, and fostered deeper reflection.

cs.HC↗

arXiv2025

Examining density wave correlations in high pressure $\rm{La_3Ni_2O_7}$ through variational Monte Carlo

$\rm La_3Ni_2O_7$, a nickelate compound with a reported superconducting transition temperature of $\rm 80~K$, has attracted significant attention in recent years. Density-wave phenomena arising from strong electron correlations are widely regarded as key to unraveling the superconductivity mechanism, but the ordering and stability of these density waves remain a subject of contention in existing theoretical studies. In this work, we employ the variational Monte Carlo (VMC) method to thoroughly examine the nature of density waves as functions of Coulomb repulsion and exchange interactions in bilayer two-orbital model proposed for the high pressure phase of $\rm La_3Ni_2O_7$. We analyse the spin and charge correlation functions in a wide range of parameter space, and delineate a schematic phase diagram that separates different density-wave ground states. Our results provide useful insights into the understanding of electron correlations in $\rm La_3Ni_2O_7$, and highlight the potential of VMC to elucidate its superconducting mechanism.

cond-mat.supr-con↗

arXiv2025

MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation

Knowledge distillation as an efficient knowledge transfer technique, has achieved remarkable success in unimodal scenarios. However, in cross-modal settings, conventional distillation methods encounter significant challenges due to data and statistical heterogeneities, failing to leverage the complementary prior knowledge embedded in cross-modal teacher models. This paper empirically reveals two critical issues in existing approaches: distillation path selection and knowledge drift. To address these limitations, we propose MST-Distill, a novel cross-modal knowledge distillation framework featuring a mixture of specialized teachers. Our approach employs a diverse ensemble of teacher models across both cross-modal and multimodal configurations, integrated with an instance-level routing network that facilitates adaptive and dynamic distillation. This architecture effectively transcends the constraints of traditional methods that rely on monotonous and static teacher models. Additionally, we introduce a plug-in masking module, independently trained to suppress modality-specific discrepancies and reconstruct teacher representations, thereby mitigating knowledge drift and enhancing transfer effectiveness. Extensive experiments across five diverse multimodal datasets, spanning visual, audio, and text, demonstrate that our method significantly outperforms existing state-of-the-art knowledge distillation methods in cross-modal distillation tasks. The source code is available at https://github.com/Gray-OREO/MST-Distill.

cs.CV↗

arXiv2024

Research on the Application of Large Language Models in Automatic Question Generation: A Case Study of ChatGLM in the Context of High School Information Technology Curriculum

This study investigates the application effectiveness of the Large Language Model (LLMs) ChatGLM in the automated generation of high school information technology exam questions. Through meticulously designed prompt engineering strategies, the model is guided to generate diverse questions, which are then comprehensively evaluated by domain experts. The evaluation dimensions include the Hitting(the degree of alignment with teaching content), Fitting (the degree of embodiment of core competencies), Clarity (the explicitness of question descriptions), and Willing to use (the teacher's willingness to use the question in teaching). The results indicate that ChatGLM outperforms human-generated questions in terms of clarity and teachers' willingness to use, although there is no significant difference in hit rate and fit. This finding suggests that ChatGLM has the potential to enhance the efficiency of question generation and alleviate the burden on teachers, providing a new perspective for the future development of educational assessment systems. Future research could explore further optimizations to the ChatGLM model to maintain high fit and hit rates while improving the clarity of questions and teachers' willingness to use them.

cs.CY↗

arXiv2024

Application of Large Language Models in Automated Question Generation: A Case Study on ChatGLM's Structured Questions for National Teacher Certification Exams

This study delves into the application potential of the large language models (LLMs) ChatGLM in the automatic generation of structured questions for National Teacher Certification Exams (NTCE). Through meticulously designed prompt engineering, we guided ChatGLM to generate a series of simulated questions and conducted a comprehensive comparison with questions recollected from past examinees. To ensure the objectivity and professionalism of the evaluation, we invited experts in the field of education to assess these questions and their scoring criteria. The research results indicate that the questions generated by ChatGLM exhibit a high level of rationality, scientificity, and practicality similar to those of the real exam questions across most evaluation criteria, demonstrating the model's accuracy and reliability in question generation. Nevertheless, the study also reveals limitations in the model's consideration of various rating criteria when generating questions, suggesting the need for further optimization and adjustment. This research not only validates the application potential of ChatGLM in the field of educational assessment but also provides crucial empirical support for the development of more efficient and intelligent educational automated generation systems in the future.

cs.CY↗

arXiv2024

Wearable Device-Based Real-Time Monitoring of Physiological Signals: Evaluating Cognitive Load Across Different Tasks

This study employs cutting-edge wearable monitoring technology to conduct high-precision, high-temporal-resolution (1-second interval) cognitive load assessment on electroencephalogram (EEG) data from the FP1 channel and heart rate variability (HRV) data of secondary vocational students. By jointly analyzing these two critical physiological indicators, the research delves into their application value in assessing cognitive load among secondary vocational students and their utility across various tasks. The study designed two experiments to validate the efficacy of the proposed approach: Initially, a random forest classification model, developed using the N-BACK task, enabled the precise decoding of physiological signal characteristics in secondary vocational students under different levels of cognitive load, achieving a classification accuracy of 97%. Subsequently, this classification model was applied in a cross-task experiment involving the National Computer Rank Examination (Level-1), demonstrating the method's significant applicability and cross-task transferability in diverse learning contexts. Conducted with high portability, this research holds substantial theoretical and practical significance for optimizing teaching resource allocation in secondary vocational education, as well as for cognitive load assessment methods and monitoring. Currently, the research findings are undergoing trial implementation in the school.

cs.HC↗