Searcharxiv⌕ Search

arXiv subjects

Qian Chen

Publications and source records attributed to Qian Chen.

At least 55 records · Page 3Linked to original sources
arXiv2026

When Should Service Agents Reconsider? Difficulty-Routed Control in Customer-Service Operations

Autonomous customer-service agents are shifting from conversational interfaces toward operational execution roles: they retrieve firm records, apply service policies, and execute backend writes such as refunds, cancellations, exchanges, order modifications, and reservation changes. This shift creates a service-control problem: firms must keep routine service fast and low-friction while preventing operational errors on requests where customer instructions, policy constraints, firm records, and backend writes interact. We propose a difficulty-routed service-control architecture that asks when service agents should reconsider before acting. A lightweight router keeps routine sessions on a low-cost baseline path and routes operationally coupled sessions to an escalated workflow. The escalated path uses conflict-aware communication and write-triggered reconsideration to concentrate deliberation and safeguards before consequential backend writes, rather than applying additional control uniformly across all service sessions. We evaluate the architecture on human-verified retail and airline tasks from $τ^{2}$-bench. In retail, the method improves reliability consistently on service requests with operational conflict. Routing evidence shows that stronger control is directed toward conflicted requests rather than broadly applied to routine ones. Dialogue and tool-use profiles suggest that gains do not come from indiscriminate interaction expansion or broader tool chains; instead, added turns and tool calls support evidence gathering, write separation, and pre-write reconsideration. Case-level evidence shows that the escalated workflow preserves fallback plans, binds retrieved records to the correct action, sequences writes, and decomposes multi-entity requests. Airline results extend the same service-control logic to reservation operations.

cs.AI↗
arXiv2026

Most Properties are Undecidable for Transitive Tense Logics

A logics' property is decidable in a class of logics if there exists an algorithm that decides whether a finitely axiomatizable logic in the class has the property. Many properties are undecidable for bimodal logics but decidable for linear tense logics, which leads to a general question on how the interactions of modalities affect the decidability of properties. In this paper, we study the decidability of properties for transitive tense logics and show that most properties are undecidable in the lattice NExt(K4t) of transitive tense logics, including Kripke completeness, the finite model property, and decidability. Our proof method adapts Chagrov's approach of constructing a reduction from an undecidable problem of Minsky machines to the decision problem for logics' properties, yielding a general scheme of proving the undecidability of these properties.

cs.LO↗
arXiv2026

STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation

Continuous Variational Autoencoders (VAEs) serve as the fundamental continuous tokenizer for modern neural audio generation systems, enabling high-fidelity reconstruction while providing a compact, smooth latent space for downstream generative priors. However, continuous VAEs face a fundamental conflict among compression rate, reconstruction fidelity, and latent space topology, which we formalize as the Rate-Distortion-Regularity Trilemma. This trilemma stems from a topological mismatch: the isotropic Gaussian prior in standard VAEs imposes a flat latent geometry that fails to accommodate audio's hierarchical nature, where low-frequency components are structured and compressible while high-frequency components are stochastic and incompressible, leading to disordered information packing in which crucial semantic features are interleaved with high-entropy noise. To address this challenge, we propose Structured Topology-Aware Regularization (STAR), a general training strategy that reshapes latent space geometry by imposing a growth-based constraint field, routing structural and textural information into channel subspaces with matching capacities. STAR is applicable to any VAE architecture and effectively resolves the trilemma, as demonstrated in CNN-based VAEs. We further present STAR-VAE, which combines STAR with a hybrid CNN-Mamba architecture for local feature extraction and linear-complexity global context modeling, and STAR-Gen, an LLM-based Flow Matching framework that leverages STAR-VAE's structured latent space for high-fidelity generation without vector quantization artifacts. Experiments across diverse audio domains show that STAR-VAE achieves state-of-the-art reconstruction fidelity and enhanced semantic information preservation, while the structured latent space improves both traditional diffusion models and STAR-Gen for text-to-audio generation.

eess.AS↗
arXiv2026

AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation

Unifying speech, sound, and music generation in one model is hindered by tradeoffs between fidelity, end-to-end training, in-context conditioning, and variable-length synthesis that no current paradigm fully resolves. To address this challenge, we present AudioCALM, a universal audio generation framework that extends autoregressive (AR) next-token prediction from discrete tokens to continuous audio latents: a thin flow-matching head replaces the softmax to predict rectified-flow velocities at each position, and a block-causal AR-Flow attention pattern produces arbitrary-length output. Joint training of multiple audio generation tasks faces an asymmetric text--audio mismatch: speech transcripts align to specific time spans and demand tight, time-aligned attention, whereas sound and music captions describe only overall semantics and rely on diffuse, holistic attention; mixing the two disproportionately degrades sound and music generation. We address this asymmetry at two levels: a data reformulation strategy that unifies all three tasks under a single description-style conditioning interface, and a novel architecture Asymmetric Mixture-of-Modality-Experts (A-MoME), which adds a dedicated residual expert for speech while sound and music share the backbone, incurring no inference overhead on non-speech inputs. Experimental results demonstrate that AudioCALM matches modality-specific state-of-the-art and outperforms prior unified baselines on speech, sound, and music generation benchmarks.

eess.AS↗
arXiv2026

Leakage-Aware Benchmarking of LLM Forecasting: Real-Time Nowcasts as the Decision-Time Input for Macro Factor Ranking

Forecasting benchmarks for retrieval-augmented LLMs routinely confound model capability with information leakage: features labeled with a target's timestamp are often not observable at the system's decision time. We study leakage-controlled equity factor ranking with a retrieval-augmented 7B open-source LLM forecaster. At each month-end from 2023-04 to 2026-03, the forecaster observes only decision-time information: lag-shifted FRED macro variables, recent macro-event summaries, and the Cleveland Fed's archived daily CPI nowcast for unreleased current-month inflation. A macro-analog retrieval module selects historical states, a critic LLM compresses them into one tactical rule, and an actor LLM maps the current state and recent rules into scores for seven U.S. equity style factors. The full pipeline obtains a median monthly Spearman rank IC of +0.154, with positive means across three non-overlapping contiguous 12-month subwindows; the mean IC remains statistically underpowered, with a bootstrap 95% confidence interval that includes zero. Non-LLM baselines under the same decision-time constraint demonstrate that a kNN macro-analog model recovers a comparable median IC, indicating that real-time inflation information and macro-similar retrieval explain much of the median signal. The LLM pipeline retains higher mean IC and a stronger long-short allocation sanity check, suggesting that any marginal benefit is concentrated in the extreme rankings that drive long-short portfolio formation. A descriptive audit of the 36 critic rules and per-month case studies appears in the appendix.

q-fin.ST↗
arXiv2026

FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

Although Multimodal Large Language Models (MLLMs) demonstrate strong omni-modal perception, their ability to forecast future events from audio-visual cues remains largely unexplored, as existing benchmarks focus mainly on retrospective understanding. To bridge this gap, we introduce FutureOmni, the first benchmark designed to evaluate omni-modal future forecasting from audio-visual environments. The evaluated models are required to perform cross-modal causal and temporal reasoning, as well as effectively leverage internal knowledge to predict future events. FutureOmni is constructed via a scalable LLM-assisted, human-in-the-loop pipeline and contains 919 videos and 1,034 multiple-choice QA pairs across 8 primary domains. Evaluations on 13 omni-modal and 7 video-only models show that current systems struggle with audio-visual future prediction, particularly in speech-heavy scenarios, with the best accuracy of 64.8% achieved by Gemini 3 Flash. To mitigate this limitation, we curate a 7K-sample instruction-tuning dataset and propose an Omni-Modal Future Forecasting (OFF) training strategy. Evaluations on FutureOmni and popular audio-visual and video-only benchmarks demonstrate that OFF enhances future forecasting and generalization. We publicly release all code (https://github.com/OpenMOSS/FutureOmni) and datasets (https://huggingface.co/datasets/OpenMOSS-Team/FutureOmni).

cs.CL↗
arXiv2026

Collaborative Large and Small Language Models for Accurate and Scalable Data Repair

We study the problem of data repair, a key task in data cleaning that corrects erroneous entries in raw datasets to improve overall data quality. Although recent data-driven methods, especially those based on large language models (LLMs), achieve remarkable performance, we observe that: (i) they directly repair data in the raw and low-quality context, which may compromise learning signals, and (ii) they directly use uncertain model outputs as repairs, potentially introducing unreliable corrections and compromising repair quality. Motivated by the efficiency of small language models (SLMs) and the capabilities of LLMs, and aiming to address the above limitations, we propose LasRepair, a framework that collaborates Large and small language models for data repair. LasRepair employs an LLM as an instructor, which selects a global repair context to guide the SLM. The SLM acts as a corrector, using the selected context to repair erroneous data more efficiently. Moreover, to further improve context quality, we extend LasRepair to LasRepair+, which formulates data repair as an Expectation-Maximisation (EM) procedure that alternates between an E-step for updating the corrector parameters and an M-step for refining the repair context. Furthermore, to mitigate model uncertainty, we propose LasRepair++, which uses column-calibrated model confidence to down-weight unreliable repaired rows when updating the corrector, thereby enhancing repair quality. Theoretical analysis and empirical evaluation demonstrate the superiority of our methods. We theoretically prove the effectiveness of the EM-style procedure and the confidence-based weighting. Experiments on real-world datasets show that LasRepair++~ achieves an average F1-score improvement of 18.1% over the strongest baseline.

cs.DB↗
arXiv2026

BareWave: Waveform-Native Flow-Matching Text-to-Speech

Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling. In text-to-speech, however, high-quality systems are still commonly built through an intermediate acoustic representation before waveform synthesis. In this work, we present BareWave, a fully waveform-native framework for direct text-to-wave generation in flow-matching TTS. We consider this setting to raise three training challenges: raw-waveform modeling lacks a strong pretrained representational scaffold, different stages of training benefit from different noise schedules, and data-space perceptual objectives do not automatically share the temporal structure of the velocity-space flow objective. As a result, direct waveform training is hard to optimize efficiently, hard to push toward a strong final operating point with a fixed recipe, and hard to integrate effective perceptual refinement. Guided by this view, we develop a direct text-to-wave training framework that combines training-time representation alignment, staged noise scheduling, and velocity-aware perceptual alignment (VAPA), while preserving a single waveform-native inference path without pretrained components at test time. Experiments on zero-shot voice cloning show that strong intelligibility, speaker similarity, and naturalness can be achieved under a fully waveform-native inference path, supporting waveform-native flow-matching TTS as a practical direction. Project page with audio demos is available at https://barewave.github.io/.

eess.AS↗
arXiv2026

Efficient Asynchronous Federated Evaluation with Strategy Similarity Awareness for Intent-Based Networking in Industrial Internet of Things

Intent-Based Networking (IBN) offers a promising paradigm for intelligent and automated network control in Industrial Internet of Things (IIoT) environments by translating high-level user intents into executable network strategies. However, frequent strategy deployment and rollback are impractical due to tightly coupled workflows and high downtime costs, while node heterogeneity and privacy constraints further complicate centralized strategy evaluation. To address these challenges, we propose a Federated Evaluation Enhanced Intent-Based Networking framework (FEIBN), which leverages large language models (LLMs) to translate user intents into structured strategy tuples and employs federated learning to support distributed strategy evaluation. To improve training efficiency and reduce communication overhead, we design a Strategy Similarity Aware Federated Learning mechanism (SSAFL), which selects nodes relevant to the task based on strategy similarity and resource status, and triggers asynchronous model uploads only when local updates are significant. Experiments demonstrate that the proposed method improves model accuracy, accelerates convergence, and reduces communication cost compared with the baselines.

cs.NI↗
arXiv2026

SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents

Recent AI agents can flexibly invoke skills to solve complex tasks, but their long-term improvement is fundamentally constrained by a lack of systematic skill construction, accumulation, and transfer. In particular, without a unified framework for skill consolidation, agents tend to redundantly construct similar capabilities across different tasks, are unable to effectively transform experience into reusable assets, and struggle to generalize task-specific skills to novel scenarios. To address this limitation, we propose SkillPyramid, a skill consolidation framework that reuses existing skill experience for broader task generalization. Operating on a hierarchical skill topology, SkillPyramid further introduces a self-evolution mechanism that enables agents to compose, validate, and incorporate new skills during task execution. Experiments on ALFWorld, WebShop, and ScienceWorld across four backbone models show that SkillPyramid substantially increases the average reward by 38.0% and reduces execution steps by 27.7%. Overall, our method transforms a skill collection from a static resource pool into a dynamic evolution system.

cs.AI↗
arXiv2026

UniVocal: Unified Speech-Singing Code-Switching Synthesis

We propose UniVocal, a unified framework that implicitly infers vocal modes from text context to pioneer Speech-Singing Code-Switching (SCS) Synthesis - a task where transitions are autonomously driven by textual semantics, akin to seamless human language blending. Unlike single-mode generation or systems relying on switching-control tags, our proposed UniVocal implicitly infers vocal modes solely from text context. To achieve this, we employ a data-efficient two-stage curriculum learning strategy that progressively trains a competitive TTS system to acquire the desired SCS capability. Addressing data scarcity, we introduce a scalable pipeline to synthesize diverse code-switching data that is both semantically and acoustically natural, alongside a new multi-scenario benchmark, SCSBench. To address limitations of semantic tokenizers in capturing acoustic details, we also introduce refined cent token and Chain-of-Thought (CoT) generation for planning prosody before content generation, effectively enhancing empathetic speech generation and singing melody. Experimental results demonstrate that UniVocal achieves state-of-the-art performance on SCSBench while maintaining competitive performance on regular speech and singing tasks. Audio samples are available at https://project-univocal-demo.github.io/demo/. The code and dataset are released at https://github.com/FunAudioLLM/FunResearch/tree/main/UniVocal.

cs.SD↗
arXiv2026

Detection of CO, H$_2$O, and OH in WASP-18b with JWST/NIRISS using Direct-Extracted Spectra and Cross-Correlation

The James Webb Space Telescope (JWST) has revolutionized the characterization of exoplanetary atmospheres, offering unprecedented sensitivity to probe their chemical and physical properties. Recently, a growing trend has emerged to obtain atmospheric information directly from pixel-level planetary spectra. In this work, we re-analyzed the WASP-18b NIRISS/SOSS dataset by employing a direct extraction method. This new method preserves the spectral information at the native instrumental resolution, thereby enabling the application of cross-correlation techniques and providing atmospheric retrievals with enhanced precision and richer information content. With this methodology, we report detections of CO at $4.4σ$ significance, H$_2$O at $3.4σ$, and OH at $7.8σ$, where CO and OH were previously unseen. Building on these unambiguous detections, our subsequent retrieval analysis significantly improves the constraints on atmospheric abundances. Our results demonstrate that the cross-correlation technique effectively extracts molecular signals from medium-resolution JWST data, enhancing detection sensitivity. By revisiting JWST archival data with cross-correlation and retrieval analysis, we can achieve a more comprehensive survey of planetary atmospheric chemistry, thereby placing precise constraints on key parameters such as planetary metallicity and C/O ratio.

astro-ph.EP↗
arXiv2026

Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset

The emergence of Large Vision-Language Models (LVLMs) has substantially expanded model capabilities beyond text-only understanding, enabling unified inference across both visual and textual modalities and supporting a broader range of real-world applications. To comprehensively evaluate the perception, understanding, reasoning, and cognition capabilities of LVLMs throughout the entire financial business workflow in Chinese contexts, we introduce CFMME, a novel Chinese financial multimodal evaluation benchmark. CFMME comprises 6,052 instances spanning from fundamental academic knowledge to complex real-world applications, covering eight primary financial image modalities and four core multimodal tasks. On CFMME, we conduct a thorough evaluation of representative LVLMs. The results show that the state-of-the-art model attains an overall accuracy of 66.11\% on the question answering task and an average score of 77.18 on the detection, recognition, and information extraction tasks, indicating substantial room for improvement in current LVLMs. In addition, we conduct detailed analyses of error causes, cross-modal capabilities, and multi-orientation settings, yielding valuable insights for future research. We hope that CFMME will spur further progress in LVLMs, especially by improving their performance on multiple multimodal tasks in the financial domain.

cs.CV↗
arXiv2026

Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning

Existing multimodal reasoning approaches predominantly follow two paradigms: converting visual inputs into text prior to reasoning, or performing end-to-end reasoning within a unified vision-language representation space. Despite their empirical progress, both paradigms suffer from fundamental structural limitations. The former relies on static visual-to-text conversion, which tends to compress and lose fine-grained visual details. The latter is prone to linguistic dominance induced by joint optimization and attention mechanisms, leading to systematically weakened faithfulness to visual evidence during reasoning. In this work, we argue that a central challenge is how and when visual evidence is introduced into the reasoning process. Motivated by this insight, we propose CSMR, a multimodal reasoning framework in which a language model controls the reasoning process by deciding when to invoke an independent visual perception module to acquire task-relevant visual evidence. Experiments across multiple multimodal reasoning benchmarks show that CSMR consistently outperforms representative baseline methods in accuracy under a zero-shot setting. Further experimental analysis confirms that these advantages primarily arise from the proposed cognitive scheduling mechanism.

cs.AI↗
arXiv2026

TrimCaching: Parameter-sharing Edge Caching for AI Model Downloading

Next-generation mobile networks are expected to facilitate fast AI model downloading to end users. By caching models on edge servers, mobile networks can deliver models to end users with low latency, resulting in a paradigm of edge model caching. In this paper, we develop a novel model placement framework, called parameter-sharing model caching (TrimCaching). TrimCaching exploits the key observation that a wide range of AI models, such as convolutional neural networks or large language models, can share a significant proportion of parameter blocks containing reusable knowledge, thereby improving storage efficiency. To this end, we formulate a parameter-sharing model placement problem to maximize the cache hit ratio in multi-edge wireless networks by balancing the fundamental tradeoff between storage efficiency and service latency. We show that the formulated problem is a submodular maximization problem with submodular constraints, for which no polynomial-time approximation algorithm exists. To tackle this challenge, we study an important special case, where a small fixed number of parameter blocks are shared across models, which often holds in practice. In such a case, a polynomial-time algorithm with a $\left(1-ε\right)/2$-approximation guarantee is developed. Subsequently, we address the original problem for the general case by developing a greedy algorithm. Simulation results demonstrate that the proposed TrimCaching framework significantly improves the cache hit ratio compared with state-of-the-art content caching without exploiting shared parameters in AI models.

cs.NI↗
arXiv2026

SpaceMoE: Towards Orbital General Intelligence with Distributed Mixture-of-Experts Inference

As satellite networks evolve to support increasingly diverse services and artificial general intelligence (AGI), large language models (LLMs) are emerging as a critical foundation for future space systems. However, deploying LLMs on satellites is hindered by stringent constraints on onboard memory, computation, and energy. In this context, the mixture-of-experts (MoE) architecture emerges as a promising solution, leveraging sparse expert activation to enable scalable model inference. By harnessing the architectural advantages of MoE, this article provides a comprehensive overview of SpaceMoE, a new paradigm for distributed MoE inference in satellite networks. We first review recent industrial progress and emerging standardization trends that motivate the evolution toward space AGI systems. Then, we introduce the fundamentals and architectural evolution of SpaceMoE. Subsequently, we discuss three fundamental design problems in SpaceMoE, namely expert placement, expert selection, and hidden-state transmission and routing, highlighting how satellite-specific factors such as dynamic topology, battery degradation, and thermal limits fundamentally reshape their solutions. Finally, we outline promising research directions for realizing scalable, efficient, and sustainable on-orbit MoE inference in future satellite networks.

cs.NI↗
arXiv2026

3DTMDet: A Dual-Path Synergy Network of Transformer and SSM for 3D Object Detection in Point Clouds

A fundamental challenge in point cloud object detection lies in the conflict between the extreme sparsity of distant points and the need for remote context understanding. The existing methods typically use 1D serialization to expand the receptive field, which inevitably discards already scarce local geometric details and reduces detection of distant and small objects. To address this issue, we propose 3DTMDet, a novel detection network that synergistically combines state space models (Mamba) with Transformers. The core idea is to utilize SSM's linear complexity and advantages in long sequence modeling to effectively capture global interactions between sparse and distant points, while using Transformer modules with local attention to encode fine-grained geometric structures in local point sets, preserving accurate shape information. We propose the 3D Hybrid Mamba Transformer (3DHMT) block, which uses an SSM-Attention-SSM pipeline to balance global context understanding and local detail preservation, effectively alleviating the tension between receptive field enlargement and geometric preservation in remote detection. In addition, we introduced a voxel generation block inspired by LiDAR physics, which diffuses features along the sensor observation direction to reconstruct the complete object structure of occlusion and distant areas. Extensive experiments conducted on the KITTI and ONCE datasets have shown that 3DTMDet outperforms state-of-the-art detectors. The code is available at https://github.com/QiuBingwen/3DTMDet.

cs.CV↗
arXiv2026

Psychological Mechanisms of Generative AI Discontinuance Intention among Chinese K-12 Teachers

This study examines the psychological mechanisms underlying Chinese K-12 teachers' discontinuance intention toward generative AI. Drawing on the Cognition-Affect-Conation framework, the study investigates how cognitive evaluations of generative AI shape affective responses and subsequently influence behavioural intention. Survey data from 256 Chinese K-12 teachers were analysed using structural equation modelling and fuzzy-set qualitative comparative analysis. The results showed that privacy concern, algorithmic opacity, and information hallucination increased AI anxiety, which in turn strengthened discontinuance intention. Conversely, perceived intelligence, perceived personalisation, and perceived interactivity enhanced satisfaction, which reduced discontinuance intention. The configurational analysis further identified multiple pathways leading to high discontinuance intention, highlighting the combined roles of technological risks, AI anxiety, weak affordance perceptions, and low satisfaction. These findings extend research on post-adoption generative AI use in education and suggest that sustainable integration requires both reducing technological uncertainty and enhancing teachers' positive user experiences.

cs.HC↗