arXiv subjects

Chen Zhang

Publications and source records attributed to Chen Zhang.

At least 181 records · Page 10Linked to original sources

arXiv2026

MiMo-V2-Flash Technical Report

We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B active parameters, designed for fast, strong reasoning and agentic capabilities. MiMo-V2-Flash adopts a hybrid attention architecture that interleaves Sliding Window Attention (SWA) with global attention, with a 128-token sliding window under a 5:1 hybrid ratio. The model is pre-trained on 27 trillion tokens with Multi-Token Prediction (MTP), employing a native 32k context length and subsequently extended to 256k. To efficiently scale post-training compute, MiMo-V2-Flash introduces a novel Multi-Teacher On-Policy Distillation (MOPD) paradigm. In this framework, domain-specialized teachers (e.g., trained via large-scale reinforcement learning) provide dense and token-level reward, enabling the student model to perfectly master teacher expertise. MiMo-V2-Flash rivals top-tier open-weight models such as DeepSeek-V3.2 and Kimi-K2, despite using only 1/2 and 1/3 of their total parameters, respectively. During inference, by repurposing MTP as a draft model for speculative decoding, MiMo-V2-Flash achieves up to 3.6 acceptance length and 2.6x decoding speedup with three MTP layers. We open-source both the model weights and the three-layer MTP weights to foster open research and community collaboration.

cs.CL↗

arXiv2026

Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction

Query correction is a critical entry point in modern search pipelines, demanding high accuracy strictly within real-time latency constraints. Chain-of-Thought (CoT) reasoning improves accuracy but incurs prohibitive latency for real-time query correction. A potential solution is to output an answer before reasoning to reduce latency; however, under autoregressive decoding, the early answer is independent of subsequent reasoning, preventing the model from leveraging its reasoning capability to improve accuracy. To address this issue, we propose Sandwich Reasoning (SandwichR), a novel approach that explicitly aligns a fast initial answer with post-hoc reasoning, enabling low-latency query correction without sacrificing reasoning-aware accuracy. SandwichR follows an Answer-Reasoning-Answer paradigm, producing an initial correction, an explicit reasoning process, and a final refined correction. To align the initial answer with post-reasoning insights, we design a consistency-aware reinforcement learning (RL) strategy: a dedicated consistency reward enforces alignment between the initial and final corrections, while margin-based rejection sampling prioritizes borderline samples where reasoning drives the most impactful corrective gains. Additionally, we construct a high-quality query correction dataset, addressing the lack of specialized benchmarks for complex query correction. Experimental results demonstrate that SandwichR achieves SOTA accuracy comparable to standard CoT while delivering a 40-70% latency reduction, resolving the latency-accuracy trade-off in online search.

cs.AI↗

arXiv2026

Efficient Context Scaling with LongCat ZigZag Attention

We introduce LongCat ZigZag Attention (LoZA), which is a sparse attention scheme designed to transform any existing full-attention models into sparse versions with rather limited compute budget. In long-context scenarios, LoZA can achieve significant speed-ups both for prefill-intensive (e.g., retrieval-augmented generation) and decode-intensive (e.g., tool-integrated reasoning) cases. Specifically, by applying LoZA to LongCat-Flash during mid-training, we serve LongCat-Flash-Exp as a long-context foundation model that can swiftly process up to 1 million tokens, enabling efficient long-term reasoning and long-horizon agentic capabilities.

cs.CL↗

arXiv2025

Difference between quark stars and neutron stars in universal relations and their effect on gravitational waves

We calculate the $f$-mode frequency and tidal overlap of quark stars using the full general relativity method. We verify the universal relations obtained from conventional neutron stars in the case of quark stars and explore the cases with different values of parameters of the quark star equation of state. Since quark stars have significantly smaller radii compared to neutron stars in the low mass range, the relation between the tidal defomability and $f$-mode frequency times radius is different for neutron stars and quark stars. This difference has an impact on dynamical tide, which is the lowest-order effect we know of that can distinguish quark stars and neutron stars from the gravitational wave during the inspiral phase. We calculate the tidal dephasing caused by this effect in the post-Newtonian method and find that it can not be detected even by the next-generation gravitational wave detectors.

gr-qc↗

arXiv2025

Discovering Transmission Dynamics of COVID-19 in China

A comprehensive retrospective analysis of public health interventions, such as large scale testing, quarantining, and contact tracing, can help identify mechanisms most effective in mitigating COVID-19. We investigate China based SARS-CoV-2 transmission patterns (e.g., infection type and likely transmission source) using publicly released tracking data. We collect case reports from local health commissions, the Chinese CDC, and official local government social media, then apply NLP and manual curation to construct transmission/tracking chains. We further analyze tracking data together with Wuhan population mobility data to quantify and visualize temporal and spatial spread dynamics. Results indicate substantial regional differences, with larger cities showing more infections, likely driven by social activities. Most symptomatic individuals (79\%) were hospitalized within 5 days of symptom onset, and those with confirmed-case contact sought admission in under 5 days. Infection sources also shifted over time: early cases were largely linked to travel to (or contact with travelers from) Hubei Province, while later transmission was increasingly associated with social activities.

cs.LG↗

arXiv2025

Embodied Learning of Reward for Musculoskeletal Control with Vision Language Models

Discovering effective reward functions remains a fundamental challenge in motor control of high-dimensional musculoskeletal systems. While humans can describe movement goals explicitly such as "walking forward with an upright posture," the underlying control strategies that realize these goals are largely implicit, making it difficult to directly design rewards from high-level goals and natural language descriptions. We introduce Motion from Vision-Language Representation (MoVLR), a framework that leverages vision-language models (VLMs) to bridge the gap between goal specification and movement control. Rather than relying on handcrafted rewards, MoVLR iteratively explores the reward space through iterative interaction between control optimization and VLM feedback, aligning control policies with physically coordinated behaviors. Our approach transforms language and vision-based assessments into structured guidance for embodied learning, enabling the discovery and refinement of reward functions for high-dimensional musculoskeletal locomotion and manipulation. These results suggest that VLMs can effectively ground abstract motion descriptions in the implicit principles governing physiological motor control.

cs.RO↗

arXiv2025

A fast powerful X-ray transient from possible tidal disruption of a white dwarf

Stars captured by black holes (BHs) can be torn apart by strong tidal forces, producing electromagnetic flares. To date, more than 100 tidal disruption events (TDEs) have been observed, each involving invariably normal gaseous stars whose debris falls onto the BH, sustaining the flares over years. White dwarfs (WDs), which are the most prevalent compact stars and a million times denser--and therefore tougher--than gaseous stars, can only be disrupted by intermediate-mass black holes (IMBHs) of 10^2--10^5 solar masses. WD-TDEs are considered to generate more powerful and short-lived flares, but their evidence has been lacking. Here we report observations of a fast and luminous X-ray transient EP250702a detected by Einstein Probe. Its one-day-long X-ray peak as luminous as 10^(47-49) erg/s showed strong recurrent flares with hard spectra extending to several tens of MeV gamma-rays, as detected by Fermi/GBM and Konus-Wind, indicating relativistic jet emission. The jet's X-ray dropped sharply from 3 x 10^49 erg/s to around 10^44 erg/s within 20 days (10 days in the source rest frame). These characteristics are inconsistent with any known transient phenomena other than a jetted-TDE evolving over an unprecedentedly short timescale, indicating the disruption of a WD by an IMBH. At late times, a new soft component progressively dominates the X-ray spectrum, exhibiting an extreme super-Eddington luminosity, which possibly originates from an accretion disc. WD-TDEs open a new window for investigating the elusive IMBHs and their surrounding stellar environments, and they are prime sources of gravitational waves in the band of space-based interferometers.

astro-ph.HE↗

arXiv2025

FlashFuser: Expanding the Scale of Kernel Fusion for Compute-Intensive Operators via Inter-Core Connection

The scaling of computation throughput continues to outpace improvements in memory bandwidth, making many deep learning workloads memory-bound. Kernel fusion is a key technique to alleviate this problem, but the fusion strategies of existing compilers and frameworks are limited to using local scratchpad memory. When the intermediate results exceed the limited capacity (such as FFN), the fusion fails. Although modern GPUs (like the NVIDIA H100) now incorporate an inter-core connection mechanism known as Distributed Shared Memory(DSM)--providing a larger, high-bandwidth, and low-latency on-chip memory pool--this hardware potential has yet to be exploited by software frameworks. To bridge this gap, we present FlashFuser, the first compiler framework to utilize inter-core connection for kernel fusion on modern GPUs. FlashFuser extends established fusion techniques to the DSM domain through three core contributions. First, we propose a powerful DSM-based communication abstraction that formalizes complex cluster-based data exchange patterns, such as reduce, shuffle and multiply. Second, we introduce a dataflow analyzer that generalizes loop scheduling, resource mapping, and tile selection to the distributed memory hierarchy; it determines the optimal execution order and tile sizes by quantifying data movement across memory levels. Finally, FlashFuser integrates these components into a unified search engine that employs analytical cost modeling and DSM-aware pruning strategies to efficiently discover the optimal execution plan. Our evaluation on an NVIDIA H100 GPU shows that FlashFuser reduces memory access by 58% and delivers kernel speedups of 3.3x against highly-tuned libraries and 4.1x against state-of-the-art compilers, resulting in a 1.24x end-to-end speedup.

cs.DC↗

arXiv2025

Function-on-Function Bayesian Optimization

Bayesian optimization (BO) has been widely used to optimize expensive and gradient-free objective functions across various domains. However, existing BO methods have not addressed the objective where both inputs and outputs are functions, which increasingly arise in complex systems as advanced sensing technologies. To fill this gap, we propose a novel function-on-function Bayesian optimization (FFBO) framework. Specifically, we first introduce a function-on-function Gaussian process (FFGP) model with a separable operator-valued kernel to capture the correlations between function-valued inputs and outputs. Compared to existing Gaussian process models, FFGP is modeled directly in the function space. Based on FFGP, we define a scalar upper confidence bound (UCB) acquisition function using a weighted operator-based scalarization strategy. Then, a scalable functional gradient ascent algorithm (FGA) is developed to efficiently identify the optimal function-valued input. We further analyze the theoretical properties of the proposed method. Extensive experiments on synthetic and real-world data demonstrate the superior performance of FFBO over existing approaches.

stat.ML↗

arXiv2025

DMP-TTS: Disentangled multi-modal Prompting for Controllable Text-to-Speech with Chained Guidance

Controllable text-to-speech (TTS) systems face significant challenges in achieving independent manipulation of speaker timbre and speaking style, often suffering from entanglement between these attributes. We present DMP-TTS, a latent Diffusion Transformer (DiT) framework with explicit disentanglement and multi-modal prompting. A CLAP-based style encoder (Style-CLAP) aligns cues from reference audio and descriptive text in a shared space and is trained with contrastive learning plus multi-task supervision on style attributes. For fine-grained control during inference, we introduce chained classifier-free guidance (cCFG) trained with hierarchical condition dropout, enabling independent adjustment of content, timbre, and style guidance strengths. Additionally, we employ Representation Alignment (REPA) to distill acoustic-semantic features from a pretrained Whisper model into intermediate DiT representations, stabilizing training and accelerating convergence. Experiments show that DMP-TTS delivers stronger style controllability than open-source baselines while maintaining competitive intelligibility and naturalness. Code and demos will be available at https://y61329697.github.io/DMP-TTS/.

cs.SD↗

arXiv2025

Statistic-Augmented, Decoupled MoE Routing and Aggregating in Autonomous Driving

Autonomous driving (AD) scenarios are inherently complex and diverse, posing significant challenges for a single deep learning model to effectively cover all possible conditions, such as varying weather, traffic densities, and road types. Large Model (LM)-Driven Mixture of Experts (MoE) paradigm offers a promising solution, where LM serves as the backbone to extract latent features while MoE serves as the downstream head to dynamically select and aggregate specialized experts to adapt to different scenarios. However, routing and aggregating in MoE face intrinsic challenges, including imprecise expert selection due to flawed routing strategy and inefficient expert aggregation leading to suboptimal prediction. To address these issues, we propose a statistic-augmented, decoupled MoE }outing and Aggregating Mechanism (MoE-RAM) driven by LM. Specifically, on the one hand, MoE-RAM enhances expert routing by incorporating statistical retrieval mechanism to match LM-extracted latent features with cached prototypical features of the most relevant experts; on the other hand, MoE-RAM adaptively reweights experts' outputs in fusion by measuring statistical distances of experts' instant features against LM-extracted latent features. Benefiting from the synergy of the statistic-augmented MoE's routing and aggregating, MoE-RAM ultimately improves the prediction performance. We take the AD semantic segmentation task as an example to assess the proposed MoE-RAM. Extensive experiments on AD datasets demonstrate the superiority of MoE-RAM compared to other MoE baselines and conventional single-model approaches.

cs.RO↗

arXiv2025

FedDSR: Federated Deep Supervision and Regularization Towards Autonomous Driving

Federated Learning (FL) enables collaborative training of autonomous driving (AD) models across distributed vehicles while preserving data privacy. However, FL encounters critical challenges such as poor generalization and slow convergence due to non-independent and identically distributed (non-IID) data from diverse driving environments. To overcome these obstacles, we introduce Federated Deep Supervision and Regularization (FedDSR), a paradigm that incorporates multi-access intermediate layer supervision and regularization within federated AD system. Specifically, FedDSR comprises following integral strategies: (I) to select multiple intermediate layers based on predefined architecture-agnostic standards. (II) to compute mutual information (MI) and negative entropy (NE) on those selected layers to serve as intermediate loss and regularizer. These terms are integrated into the output-layer loss to form a unified optimization objective, enabling comprehensive optimization across the network hierarchy. (III) to aggregate models from vehicles trained based on aforementioned rules of (I) and (II) to generate the global model on central server. By guiding and penalizing the learning of feature representations at intermediate stages, FedDSR enhances the model generalization and accelerates model convergence for federated AD. We then take the semantic segmentation task as an example to assess FedDSR and apply FedDSR to multiple model architectures and FL algorithms. Extensive experiments demonstrate that FedDSR achieves up to 8.93% improvement in mIoU and 28.57% reduction in training rounds, compared to other FL baselines, making it highly suitable for practical deployment in federated AD ecosystems.

cs.RO↗

arXiv2025

M3-TTS: Multi-modal DiT Alignment & Mel-latent for Zero-shot High-fidelity Speech Synthesis

Non-autoregressive (NAR) text-to-speech synthesis relies on length alignment between text sequences and audio representations, constraining naturalness and expressiveness. Existing methods depend on duration modeling or pseudo-alignment strategies that severely limit naturalness and computational efficiency. We propose M3-TTS, a concise and efficient NAR TTS paradigm based on multi-modal diffusion transformer (MM-DiT) architecture. M3-TTS employs joint diffusion transformer layers for cross-modal alignment, achieving stable monotonic alignment between variable-length text-speech sequences without pseudo-alignment requirements. Single diffusion transformer layers further enhance acoustic detail modeling. The framework integrates a mel-vae codec that provides 3* training acceleration. Experimental results on Seed-TTS and AISHELL-3 benchmarks demonstrate that M3-TTS achieves state-of-the-art NAR performance with the lowest word error rates (1.36\% English, 1.31\% Chinese) while maintaining competitive naturalness scores. Code and demos will be available at https://wwwwxp.github.io/M3-TTS.

cs.SD↗

arXiv2025

Ultrafast Optical Evidence of Coexisting Density Waves in Bilayer Nickelate La$_3$Ni$_2$O$_7$

Utilizing ultrafast optical pump-probe spectroscopy, we investigate the coexistence and competition of electronic orders in the bilayer nickelate La$_3$Ni$_2$O$_7$. Our results reveal two coexisting density waves that can be selectively manipulated with light. We directly identify a spin-density wave (SDW) with electronic nematicity emerging below $T_{\rm SDW}$ $\approx$ 140 K by measuring its spin dynamics, and discover a distinct, nonmagnetic charge order appearing below $T_{\rm DW}$ $\approx$ 115 K. The central finding is the demonstration of differential optical control: the charge order is fragile, completely suppressed by a pump fluence of approximately 40 $μ$J/cm$^2$, while the SDW is remarkably robust, persisting to 200 $μ$J/cm$^2$. This work establishes a clear hierarchy in the stability of competing electronic orders and provides a powerful method for disentangling their interplay in quantum materials.

cond-mat.str-el↗

arXiv2025

HyperST: Hierarchical Hyperbolic Learning for Spatial Transcriptomics Prediction

Spatial Transcriptomics (ST) merges the benefits of pathology images and gene expression, linking molecular profiles with tissue structure to analyze spot-level function comprehensively. Predicting gene expression from histology images is a cost-effective alternative to expensive ST technologies. However, existing methods mainly focus on spot-level image-to-gene matching but fail to leverage the full hierarchical structure of ST data, especially on the gene expression side, leading to incomplete image-gene alignment. Moreover, a challenge arises from the inherent information asymmetry: gene expression profiles contain more molecular details that may lack salient visual correlates in histological images, demanding a sophisticated representation learning approach to bridge this modality gap. We propose HyperST, a framework for ST prediction that learns multi-level image-gene representations by modeling the data's inherent hierarchy within hyperbolic space, a natural geometric setting for such structures. First, we design a Multi-Level Representation Extractors to capture both spot-level and niche-level representations from each modality, providing context-aware information beyond individual spot-level image-gene pairs. Second, a Hierarchical Hyperbolic Alignment module is introduced to unify these representations, performing spatial alignment while hierarchically structuring image and gene embeddings. This alignment strategy enriches the image representations with molecular semantics, significantly improving cross-modal prediction. HyperST achieves state-of-the-art performance on four public datasets from different tissues, paving the way for more scalable and accurate spatial transcriptomics prediction.

cs.CV↗

arXiv2025

InstructAudio: Unified speech and music generation with natural language instruction

Text-to-speech (TTS) and text-to-music (TTM) models face significant limitations in instruction-based control. TTS systems usually depend on reference audio for timbre, offer only limited text-level attribute control, and rarely support dialogue generation. TTM systems are constrained by input conditioning requirements that depend on expert knowledge annotations. The high heterogeneity of these input control conditions makes them difficult to joint modeling with speech synthesis. Despite sharing common acoustic modeling characteristics, these two tasks have long been developed independently, leaving open the challenge of achieving unified modeling through natural language instructions. We introduce InstructAudio, a unified framework that enables instruction-based (natural language descriptions) control of acoustic attributes including timbre (gender, age), paralinguistic (emotion, style, accent), and musical (genre, instrument, rhythm, atmosphere). It supports expressive speech, music, and dialogue generation in English and Chinese. The model employs joint and single diffusion transformer layers with a standardized instruction-phoneme input format, trained on 50K hours of speech and 20K hours of music data, enabling multi-task learning and cross-modal alignment. Fig. 1 visualizes performance comparisons with mainstream TTS and TTM models, demonstrating that InstructAudio achieves optimal results on most metrics. To our best knowledge, InstructAudio represents the first instruction-controlled framework unifying speech and music generation. Audio samples are available at: https://qiangchunyu.github.io/InstructAudio/

eess.AS↗

arXiv2025

CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection

Detecting trajectory anomalies is a vital task in modern Intelligent Transportation Systems (ITS), enabling the identification of unsafe, inefficient, or irregular travel behaviours. While deep learning has emerged as the dominant approach, several key challenges remain unresolved. First, sub-trajectory anomaly detection, capable of pinpointing the precise segments where anomalies occur, remains underexplored compared to whole-trajectory analysis. Second, many existing methods depend on carefully tuned thresholds, limiting their adaptability in real-world applications. Moreover, the irregular sampling of trajectory data and the presence of noise in training sets further degrade model performance, making it difficult to learn reliable representations of normal routes. To address these challenges, we propose a contrastive reinforcement learning framework for online trajectory anomaly detection, CroTad. Our method is threshold-free and robust to noisy, irregularly sampled data. By incorporating contrastive learning, CroTad learns to extract diverse normal travel patterns for different itineraries and effectively distinguish anomalous behaviours at both sub-trajectory and point levels. The detection module leverages deep reinforcement learning to perform online, real-time anomaly scoring, enabling timely and fine-grained identification of abnormal segments. Extensive experiments on two real-world datasets demonstrate the effectiveness and robustness of our framework across various evaluation scenarios.

cs.LG↗

arXiv2025

ELPO: Ensemble Learning Based Prompt Optimization for Large Language Models

The remarkable performance of Large Language Models (LLMs) highly relies on crafted prompts. However, manual prompt engineering is a laborious process, creating a core bottleneck for practical application of LLMs. This phenomenon has led to the emergence of a new research area known as Automatic Prompt Optimization (APO), which develops rapidly in recent years. Existing APO methods such as those based on evolutionary algorithms or trial-and-error approaches realize an efficient and accurate prompt optimization to some extent. However, those researches focus on a single model or algorithm for the generation strategy and optimization process, which limits their performance when handling complex tasks. To address this, we propose a novel framework called Ensemble Learning based Prompt Optimization (ELPO) to achieve more accurate and robust results. Motivated by the idea of ensemble learning, ELPO conducts voting mechanism and introduces shared generation strategies along with different search methods for searching superior prompts. Moreover, ELPO creatively presents more efficient algorithms for the prompt generation and search process. Experimental results demonstrate that ELPO outperforms state-of-the-art prompt optimization methods across different tasks, e.g., improving F1 score by 7.6 on ArSarcasm dataset.

cs.CL↗