arXiv subjects

Shuo Ren

Publications and source records attributed to Shuo Ren.

At least 37 records · Page 2Linked to original sources

arXiv2026

AstroVLM: Expert Multi-agent Collaborative Reasoning for Astronomical Imaging Quality Diagnosis

Vision Language Models (VLMs) have been applied to several specific domains and have shown strong problem-solving capabilities. However, astronomical imaging, a quite complex problem involving multidisciplinary knowledge and several subtasks, has not been adequately studied. Due to the complexity of the astronomical imaging process, both world-class astronomical organizations, such as NASA, and expert enthusiasts devote a great deal of time and effort. This is because the processes in astronomical imaging have complex underlying correlations that significantly influence one another, making the quality diagnosis and error localization of astronomical images challenging. To address this problem, we propose AstroVLM, a collaborative multi-agent system for diagnosing the quality of astronomical images. Experiment results show that AstroVLM outperforms all baselines on real-world astronomical imaging quality diagnosis tasks, providing a reference for language models to handle complicated multi-process tasks.

cs.MA↗

arXiv2026

Coherent Spin-Photon Interface of single PL6 Color Centers in Silicon Carbide

The PL6 color center in silicon carbide has recently emerged as a promising platform for quantum information processing, yet its coherent spin--photon interface has remained largely unexplored. Here we present a comprehensive investigation of single PL6 centers, combining spectroscopy with theoretical analysis. The excited-state fine structure is fully resolved using group-theoretical modeling and strain-dependent measurements. Under resonant excitation, we achieve a spin initialization fidelity of $99.69 \pm 0.03\%$ and a readout contrast of $98.31 \pm 1.03\%$. The spin--photon--entangled $A_2$ transition exhibits narrow optical linewidths ($\sim 180$~MHz) and a polarization visibility of $\sim 82\%$. Coherent optical driving enables Rabi frequencies up to $2.895$~GHz, while dynamical decoupling extends the spin coherence time from $0.5$~ms to $5.70$~ms. Our results establish PL6 as a competitive solid-state spin--photon interface hosted in a commercially available semiconductor platform.

quant-ph↗

arXiv2026

Decoherence-protected entangling gates in a silicon carbide quantum node

Solid-state color centers are promising candidates for nodes in quantum network architectures. However, realizing scalable and fully functional quantum nodes, comprising both processor and memory qubits with high-fidelity universal gate operations, remains a central challenge in this field. Here, we demonstrate a fully functional quantum node in silicon carbide, where electron spins act as quantum processors and nuclear spins serve as quantum memory. Specifically, we design a pulse sequence that combines dynamical decoupling with hyperfine interactions to realize decoherence-protected universal gate operations between the processor and memory qubits. Leveraging this gate, we deterministically prepare entangled states within the quantum node, achieving a fidelity of 90%, which exceeds the fault-tolerance threshold of certain quantum network architectures. These results open a pathway toward scalable and fully functional quantum nodes based on silicon carbide.

quant-ph↗

arXiv2026

Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents

As scientific research becomes increasingly complex, innovative tools are needed to manage vast data, facilitate interdisciplinary collaboration, and accelerate discovery. Large language models (LLMs) are now evolving into LLM-based scientific agents that automate critical tasks ranging from hypothesis generation and experiment design to data analysis and simulation. Unlike general-purpose LLMs, these specialized agents integrate domain-specific knowledge, advanced tool sets, and robust validation mechanisms, enabling them to handle complex data types, ensure reproducibility, and drive scientific breakthroughs. This survey provides a focused review of the architectures, design, benchmarks, applications, and ethical considerations surrounding LLM-based scientific agents. We highlight why they differ from general agents and the ways in which they advance research across various scientific fields. By examining their development and challenges, this survey offers a comprehensive roadmap for researchers and practitioners to harness these agents for more efficient, reliable, and ethically sound scientific discovery.

cs.AI↗

arXiv2025

KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning

Recent advances have demonstrated that integrating reinforcement learning with rule-based rewards can significantly enhance the reasoning capabilities of large language models, even without supervised fine-tuning. However, prevalent reinforcement learning algorithms such as GRPO and its variants like DAPO, suffer from a coarse granularity issue when computing the advantage. Specifically, they compute rollout-level advantages that assign identical values to every token within a sequence, failing to capture token-specific contributions and hindering effective learning. To address this limitation, we propose Key-token Advantage Estimation (KTAE) - a novel algorithm that estimates fine-grained, token-level advantages without introducing additional models. KTAE leverages the correctness of sampled rollouts and applies statistical analysis to quantify the importance of individual tokens within a sequence to the final outcome. This quantified token-level importance is then combined with the rollout-level advantage to obtain a more fine-grained token-level advantage estimation. Empirical results show that models trained with GRPO+KTAE and DAPO+KTAE outperform baseline methods across five mathematical reasoning benchmarks. Notably, they achieve higher accuracy with shorter responses and even surpass R1-Distill-Qwen-1.5B using the same base model.

cs.AI↗

arXiv2025

Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questions

In visual question answering (VQA) context, users often pose ambiguous questions to visual language models (VLMs) due to varying expression habits. Existing research addresses such ambiguities primarily by rephrasing questions. These approaches neglect the inherently interactive nature of user interactions with VLMs, where ambiguities can be clarified through user feedback. However, research on interactive clarification faces two major challenges: (1) Benchmarks are absent to assess VLMs' capacity for resolving ambiguities through interaction; (2) VLMs are trained to prefer answering rather than asking, preventing them from seeking clarification. To overcome these challenges, we introduce \textbf{ClearVQA} benchmark, which targets three common categories of ambiguity in VQA context, and encompasses various VQA scenarios.

cs.CV↗

arXiv2025

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (\textbf{VRMs}). owever, such transfer faces critical challenges: Effective "slow thinking" in VRMs requires \textbf{visual reflection}, the ability to check the reasoning process based on visual information. Through quantitative analysis, we observe that current VRMs exhibit limited visual reflection, as their attention to visual information diminishes rapidly with longer generated responses. To address this challenge, we propose a new VRM \textbf{Reflection-V}, which enhances visual reflection based on reasoning data construction for cold-start and reward design for reinforcement learning (RL). Firstly, we construct vision-centered reasoning data by leveraging an agent that interacts between VLMs and reasoning LLMs, enabling cold-start learning of visual reflection patterns. Secondly, a visual attention based reward model is employed during RL to encourage reasoning based on visual information. Therefore, \textbf{Reflection-V} demonstrates significant improvements across multiple visual reasoning benchmarks. Furthermore, \textbf{Reflection-V} maintains a stronger and more consistent reliance on visual information during visual reasoning, indicating effective enhancement in visual reflection capabilities.

cs.CV↗

arXiv2025

Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture

Spatial understanding is essential for Multimodal Large Language Models (MLLMs) to support perception, reasoning, and planning in embodied environments. Despite recent progress, existing studies reveal that MLLMs still struggle with spatial understanding. However, existing research lacks a comprehensive and systematic evaluation of these limitations, often restricted to isolated scenarios, such as single-view or video. In this work, we present a systematic analysis of spatial understanding from both data and architectural perspectives across three representative scenarios: single-view, multi-view, and video. We propose a benchmark named MulSeT (Multi-view Spatial Understanding Tasks), and design a series of experiments to analyze the spatial reasoning capabilities of MLLMs. From the data perspective, the performance of spatial understanding converges quickly as the training data increases, and the upper bound is relatively low, especially for tasks that require spatial imagination. This indicates that merely expanding training data is insufficient to achieve satisfactory performance. From the architectural perspective, we find that spatial understanding relies more heavily on the positional encoding within the visual encoder than within the language model, in both cascaded and native MLLMs. Moreover, we explore reasoning injection and envision future improvements through architectural design to optimize spatial understanding. These insights shed light on the limitations of current MLLMs and suggest new directions for improving spatial reasoning capabilities through data scaling and architectural tuning.

cs.CV↗

arXiv2024

Robust single divacancy defects near stacking faults in 4H-SiC under resonant excitation

Color centers in silicon carbide (SiC) have demonstrated significant promise for quantum information processing. However, the undesirable ionization process that occurs during optical manipulation frequently causes fluctuations in the charge state and performance of these defects, thereby restricting the effectiveness of spin-photon interfaces. Recent predictions indicate that divacancy defects near stacking faults possess the capability to stabilize their neutral charge states, thereby providing robustness against photoionization effects. In this work, we present a comprehensive protocol for the scalable and targeted fabrication of single divacancy arrays in 4H-SiC using a high-resolution focused helium ion beam. Through photoluminescence emission (PLE) experiments, we demonstrate long-term emission stability with minimal linewidth shift ($\sim$ 50 MHz over 3 hours) for the single c-axis divacancies within stacking faults. By measuring the ionization rate for different polytypes of divacancies, we found that the divacancies within stacking faults are more robust against resonant excitation. Additionally, angle-resolved PLE spectra reveal their two resonant-transition lines with mutually orthogonal polarizations. Notably, the PLE linewidths are approximately 7 times narrower and the spin-coherent times are 6 times longer compared to divacancies generated via carbon-ion implantation. These findings highlight the immense potential of SiC divacancies for on-chip quantum photonics and the construction of efficient spin-to-photon interfaces, indicating a significant step forward in the development of quantum technologies.

quant-ph↗

arXiv2023

SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data

How to boost speech pre-training with textual data is an unsolved problem due to the fact that speech and text are very different modalities with distinct characteristics. In this paper, we propose a cross-modal Speech and Language Model (SpeechLM) to explicitly align speech and text pre-training with a pre-defined unified discrete representation. Specifically, we introduce two alternative discrete tokenizers to bridge the speech and text modalities, including phoneme-unit and hidden-unit tokenizers, which can be trained using a small amount of paired speech-text data. Based on the trained tokenizers, we convert the unlabeled speech and text data into tokens of phoneme units or hidden units. The pre-training objective is designed to unify the speech and the text into the same discrete semantic space with a unified Transformer network. We evaluate SpeechLM on various spoken language processing tasks including speech recognition, speech translation, and universal representation evaluation framework SUPERB, demonstrating significant improvements on content-related tasks. Code and models are available at https://aka.ms/SpeechLM.

cs.CL↗

arXiv2023

An Efficient Solution Space Exploring and Descent Method for Packing Equal Spheres in a Sphere

The problem of packing equal spheres in a spherical container is a classic global optimization problem, which has attracted enormous studies in academia and found various applications in industry. This problem is computationally challenging, and many efforts focus on small-scale instances with the number of spherical items less than 200 in the literature. In this work, we propose an efficient local search heuristic algorithm named solution space exploring and descent for solving this problem, which can quantify the solution's quality to determine the number of exploring actions and quickly discover a high-quality solution. Besides, we propose an adaptive neighbor object maintenance method to speed up the convergence of the continuous optimization process and reduce the time consumption. Computational experiments on a large number of benchmark instances with $5 \leq n \leq 400$ spherical items show that our algorithm significantly outperforms the state-of-the-art algorithm. In particular, it improves the 274 best-known results and matches the 84 best-known results out of the 396 well-known benchmark instances.

cs.CG↗

arXiv2022

Infinitely many sign-changing solutions for the nonlinear Schrödinger-Poisson system with $p$-Laplacian

In this paper, we consider the following Schrödinger-Poisson system with $p$-laplacian \begin{equation} \begin{cases} -Δ_{p}u+V(x)|u|^{p-2}u+ϕ|u|^{p-2}u=f(u)\qquad&x\in\mathbb{R}^{3},\newline -Δϕ=|u|^{p}&x\in\mathbb{R}^{3}. \end{cases}\notag \end{equation} We investigate the existence of multiple sign-changing solutions. By using the method of invariant sets of descending flow, we prove that this system has infinitely many sign-changing solutions. This system is new one coupled by Schrödinger equation of $p$-laplacian with a Poisson equation. Our results complement the study made by Zhaoli Liu, Zhiqiang Wang, Jianjun Zhang (Annali di Matematica Pura ed Applicata, 195(3):775-794(2016)).

math.AP↗

arXiv2022

TESSP: Text-Enhanced Self-Supervised Speech Pre-training

Self-supervised speech pre-training empowers the model with the contextual structure inherent in the speech signal while self-supervised text pre-training empowers the model with linguistic information. Both of them are beneficial for downstream speech tasks such as ASR. However, the distinct pre-training objectives make it challenging to jointly optimize the speech and text representation in the same model. To solve this problem, we propose Text-Enhanced Self-Supervised Speech Pre-training (TESSP), aiming to incorporate the linguistic information into speech pre-training. Our model consists of three parts, i.e., a speech encoder, a text encoder and a shared encoder. The model takes unsupervised speech and text data as the input and leverages the common HuBERT and MLM losses respectively. We also propose phoneme up-sampling and representation swapping to enable joint modeling of the speech and text information. Specifically, to fix the length mismatching problem between speech and text data, we phonemize the text sequence and up-sample the phonemes with the alignment information extracted from a small set of supervised data. Moreover, to close the gap between the learned speech and text representations, we swap the text representation with the speech representation extracted by the respective private encoders according to the alignment information. Experiments on the Librispeech dataset shows the proposed TESSP model achieves more than 10% improvement compared with WavLM on the test-clean and test-other sets. We also evaluate our model on the SUPERB benchmark, showing our model has better performance on Phoneme Recognition, Acoustic Speech Recognition and Speech Translation compared with WavLM.

cs.SD↗

arXiv2022

RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction

Bilingual lexicon induction induces the word translations by aligning independently trained word embeddings in two languages. Existing approaches generally focus on minimizing the distances between words in the aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates. In addition, the mapping function is globally shared by all words, whose performance might be hindered by the deviations in the distributions of different languages. In this work, we propose a novel ranking-oriented induction model RAPO to learn personalized mapping function for each word. RAPO is capable of enjoying the merits from the unique characteristics of a single word and the cross-language isomorphism simultaneously. Extensive experimental results on public datasets including both rich-resource and low-resource languages demonstrate the superiority of our proposal. Our code is publicly available in \url{https://github.com/Jlfj345wf/RAPO}.

cs.CL↗

arXiv2022

WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing

Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contains multi-faceted information including speaker identity, paralinguistics, spoken content, etc., learning universal representations for all speech tasks is challenging. To tackle the problem, we propose a new pre-trained model, WavLM, to solve full-stack downstream speech tasks. WavLM jointly learns masked speech prediction and denoising in pre-training. By this means, WavLM does not only keep the speech content modeling capability by the masked speech prediction, but also improves the potential to non-ASR tasks by the speech denoising. In addition, WavLM employs gated relative position bias for the Transformer structure to better capture the sequence ordering of input speech. We also scale up the training dataset from 60k hours to 94k hours. WavLM Large achieves state-of-the-art performance on the SUPERB benchmark, and brings significant improvements for various speech processing tasks on their representative benchmarks. The code and pre-trained models are available at https://aka.ms/wavlm.

cs.CL↗

arXiv2022

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text modality based on the output of the decoder. Leveraging large-scale unlabeled speech and text data, we pre-train SpeechT5 to learn a unified-modal representation, hoping to improve the modeling capability for both speech and text. To align the textual and speech information into this unified semantic space, we propose a cross-modal vector quantization approach that randomly mixes up speech/text states with latent units as the interface between encoder and decoder. Extensive evaluations show the superiority of the proposed SpeechT5 framework on a wide variety of spoken language processing tasks, including automatic speech recognition, speech synthesis, speech translation, voice conversion, speech enhancement, and speaker identification. We release our code and model at https://github.com/microsoft/SpeechT5.

eess.AS↗

arXiv2022

Speech Pre-training with Acoustic Piece

Previous speech pre-training methods, such as wav2vec2.0 and HuBERT, pre-train a Transformer encoder to learn deep representations from audio data, with objectives predicting either elements from latent vector quantized space or pre-generated labels (known as target codes) with offline clustering. However, those training signals (quantized elements or codes) are independent across different tokens without considering their relations. According to our observation and analysis, the target codes share obvious patterns aligned with phonemized text data. Based on that, we propose to leverage those patterns to better pre-train the model considering the relations among the codes. The patterns we extracted, called "acoustic piece"s, are from the sentence piece result of HuBERT codes. With the acoustic piece as the training signal, we can implicitly bridge the input audio and natural language, which benefits audio-to-text tasks, such as automatic speech recognition (ASR). Simple but effective, our method "HuBERT-AP" significantly outperforms strong baselines on the LibriSpeech ASR task.

cs.SD↗

arXiv2021

Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding

The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text encoder for leveraging extensive text data and thus capture more context-aware linguistic information. However, this approach brings a mismatch problem between the speech encoder and the text encoder due to the different units used for modeling. In this paper, we propose an embedding aligner and modality switch training to better align the speech and text latent spaces. The embedding aligner is a shared linear projection between text encoder and speech encoder trained by masked language modeling (MLM) loss and connectionist temporal classification (CTC), respectively. The modality switch training randomly swaps speech and text embeddings based on the forced alignment result to learn a joint representation space. Experimental results show that our proposed approach achieves a relative 14% to 19% word error rate (WER) reduction on Librispeech ASR task. We further verify its effectiveness on spoken language understanding (SLU), i.e., an absolute 2.5% to 2.8% F1 score improvement on SNIPS slot filling task.

cs.SD↗