arXiv subjects

Haoyang Zhang

Publications and source records attributed to Haoyang Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Chronological Thinking in Full-Duplex Spoken Dialogue Language Models

Recent advances in spoken dialogue language models (SDLMs) reflect growing interest in shifting from turn-based to full-duplex systems, where the models continuously perceive user speech streams while generating responses. This simultaneous listening and speaking design enables real-time interaction and the agent can handle dynamic conversational behaviors like user barge-in. However, during the listening phase, existing systems keep the agent idle by repeatedly predicting the silence token, which departs from human behavior: we usually engage in lightweight thinking during conversation rather than remaining absent-minded. Inspired by this, we propose Chronological Thinking, an on-the-fly conversational thinking mechanism that aims to improve response quality in full-duplex SDLMs. Specifically, chronological thinking presents a paradigm shift from conventional LLM thinking approaches, such as Chain-of-Thought, purpose-built for streaming acoustic input. (1) Strictly causal: the agent reasons incrementally while listening, updating internal hypotheses only from past audio with no lookahead. (2) No additional latency: reasoning is amortized during the listening window; once the user stops speaking, the agent halts thinking and begins speaking without further delay. Experiments demonstrate the effectiveness of chronological thinking through both objective metrics and human evaluations show consistent improvements in response quality. Furthermore, chronological thinking robustly handles conversational dynamics and attains competitive performance on full-duplex interaction metrics.

cs.CL↗

arXiv2026

DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action

Recent advances in spoken dialogue language models have shifted from turn-based to full-duplex designs, where the model continuously listens to the user while generating responses. However, existing duplex backbones still lack a native channel for in-conversation planning and tool calling, leaving real-time agentic behaviour either tied to turn boundaries or relegated to an external cascade. We propose DuplexSLA, a native full-duplex Speech-Language-Action foundation model that decodes assistant audio together with a structured action stream on a shared 160 ms chunk timeline. DuplexSLA is built on a dual-stream three-channel formulation: a continuous user audio channel, a discrete assistant audio channel, and a rate-limited textual action channel, all decoded jointly by a single backbone, so that listening, speaking, planning, and tool calling unfold on one shared clock. Two capabilities define the model: (1) semantic-driven turn-taking control, where interruption, pause, and backchannel are handled inside the same backbone instead of by an external semantic VAD; and (2) in-conversation planning and tool calling, where planning text and structured tool calls are emitted on the action channel without halting assistant audio, so that multi-action and backchannel-triggered tool use are interleaved with ongoing speech. To evaluate these capabilities together, we further construct DuplexSLA-Bench, a duplex benchmark covering pause, interrupt, and backchannel turn-taking together with three styles of in-conversation tool calling. Our project page, interactive demos, and the DuplexSLA-Bench evaluation suite are publicly available at https://github.com/hyzhang24/DuplexSLA.

eess.AS↗

arXiv2026

Step-Audio-R1.5 Technical Report

Recent advancements in large audio language models have extended Chain-of-Thought (CoT) reasoning into the auditory domain, enabling models to tackle increasingly complex acoustic and spoken tasks. To elicit and sustain these extended reasoning chains, the prevailing paradigm -- driven by the success of text-based reasoning models -- overwhelmingly relies on Reinforcement Learning with Verified Rewards (RLVR). However, as models are strictly optimized to distill rich, continuous auditory contexts into isolated, verifiable text labels, a fundamental question arises: are we fostering true audio intelligence, or merely reducing a continuous sensory medium into a discrete puzzle? We identify this as the "verifiable reward trap." While RLVR yields remarkable scores on standardized objective benchmarks, it systematically degrades the real-world conversational feel of audio models. By prioritizing isolated correctness over acoustic nuance, RLVR reduces dynamic interactions to mechanical "answering machines," severely compromising prosodic naturalness, emotional continuity, and user immersion, particularly in long-turn dialogues. To bridge the gap between mechanical objective verification and genuine sensory empathy, we introduce Step-Audio-R1.5, marking a paradigm shift toward Reinforcement Learning from Human Feedback (RLHF) in audio reasoning. Comprehensive evaluations demonstrate that Step-Audio-R1.5 not only maintains robust analytical reasoning but profoundly transforms the interactive experience, redefining the boundaries of deeply immersive long-turn spoken dialogue.

eess.AS↗

arXiv2026

The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models

The pursuit of a "unified" discrete token for both speech understanding and generation has led the Speech Language Model (SLM) community to heavily rely on Word Error Rate (WER) -- the core metric for Whisper-style tokenizers -- as the definitive proxy for representation quality. This fosters the assumption that low-WER tokens inherently preserve the information necessary for intelligible acoustic synthesis. We argue this is fundamentally deceptive. While high-frequency tokens succeed in generation tasks due to implicit information leakage, isolating pure semantic information at ultra-low frame rates strips away the finegrained articulation and micro-dynamics essential for ODE-based generation. Empirically validating this requires extreme compression without sacrificing WER -- a methodological bottleneck, as standard fixed-stride downsampling arbitrarily truncates phonetic boundaries. To overcome this, we develop a dynamic compression tokenizer that intelligently aligns representations with semantic boundaries, achieving ultra-low frame rates with exceptionally low WER. Using these isolated "pure" semantic tokens, we expose the WER trap: when conditioning generative models -- even with oracle duration alignments -- the reconstructed speech suffers from severe articulation blur and is rendered acoustically unintelligible. Our findings demonstrate that semantic categorization rewarded by low WER is inherently orthogonal to the continuous phonetic trajectories required for synthesis, shattering the illusion of the unified token and advocating for explicitly decoupled speech representations.

eess.AS↗

arXiv2026

StepAudio 2.5 Technical Report

Unified audio-language modeling has emerged as a prominent trend in modern speech systems, promising to bring the reasoning capabilities of large language models to auditory tasks. However, existing unified foundations often struggle to match the depth of specialized systems across automatic speech recognition (ASR), text-to-speech synthesis (TTS), and realtime spoken interaction. Bridging this gap remains an open challenge. This report presents StepAudio 2.5, a unified audio-language foundation model that matches or exceeds specialized systems across all three capabilities. Rather than treating these tasks as architecturally distinct, we operate on the premise that once text and audio share a multimodal representational space, task specialization becomes a matter of operational regimes: data construction, optimization targets, and decoding constraints. Guided by this insight, we advance the post-training paradigm from standard supervised learning to task-tailored Reinforcement Learning from Human Feedback (RLHF), using it as the primary mechanism to define complex optimization targets. We leverage this RLHF-centric alignment, alongside specialized decoding, to shape a shared backbone into three distinct operational modes. Concretely, the ASR branch advances transcription efficiency via verifiable multi-token decoding; the TTS branch achieves controllable, expressive synthesis through preference-based RLHF and context-rich supervision; and the Realtime branch realizes low-latency, persona-consistent dialogue via generative reward modeling within an RLHF framework. On standard benchmarks, StepAudio 2.5 achieves state-of-the-art results across ASR, TTS, and Realtime, demonstrating that a singular audio-language foundation can successfully internalize the distinct deployment objectives of speech understanding, generation, and live interaction.

eess.AS↗

arXiv2026

A First Measurement Study on Authentication Security in Real-World Remote MCP Servers

The Model Context Protocol (MCP) is emerging as a common interface connecting large language models (LLMs) with external services. Remote deployments are becoming increasingly important as agents connect to user-linked online services, such as social, productivity, and financial services. In such deployments, the authentication boundary between MCP clients and remote servers becomes security-critical, yet remains underexplored. We present the first measurement study of authentication security in real-world remote MCP servers. We identify 7,973 live remote MCP servers, finding that 40.55% expose tools without authentication. Among authenticated servers, OAuth is the dominant authorization mechanism for reaching remote services, and OAuth deployments in the MCP ecosystem commonly exhibit three characteristics: open client environments, dynamic client registration, and delegated authorization. These characteristics distinguish MCP deployments from traditional OAuth and introduce new attack surfaces. Guided by this observation, we derive a taxonomy of authentication flaws comprising three MCP-specific categories and conventional OAuth misconfigurations, for a total of four categories and nine concrete flaw types. To evaluate these flaws at scale, we implement a semi-automated detection framework that combines passive traffic inspection with active dynamic probing. Applying it to 119 testable real-world OAuth-enabled MCP servers, we find that each server exhibits at least one flaw, with a total of 325 flaws identified, among which dynamic client registration flaws affect 96.6% of tested servers. Many of these flaws can lead to sensitive information leakage and account takeover. Through responsible disclosure, we obtained 9 CVE IDs. Our findings expose pervasive authentication weaknesses in the MCP ecosystem and underscore the urgent need for hardened OAuth-based remote deployments.

cs.CR↗

arXiv2026

UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation

Manually annotating accurate 3D hand poses is extremely time-consuming and labor-intensive. Existing self-supervised hand pose estimation methods leverage the discrepancy between input images and rendered outputs, or multi-view consistency constraints, as the driving force to optimize networks and progressively refine pose accuracy. However, these methods are highly susceptible to noisy pseudo-labels and overlook the importance of fully exploiting fine-grained spatial correlations, which undermines the stability of model training. To address these issues, we propose UST-Hand, a self-supervised learning framework that estimates uncertainty distribution of hand pose and constructs a probabilistic point cloud feature space, which enables the complex spatiotemporal relationship modeling. UST-Hand employs a conditional normalizing flow model to capture hand pose distributions and samples diverse hypotheses, facilitating robust learning under noisy pseudo-labels supervision with enhanced stability. These multi-hypothesis are mapped to a unified probabilistic 3D point cloud space for multi-view and temporal feature interaction, comprehensively exploring hand motion patterns and fine-grained spatial correlations. Extensive experiments on three challenging datasets demonstrate that UST-Hand achieves state-of-the-art performance, outperforming existing self-supervised methods by up to 37.8% in Mean Per Vertex Position Error (MPVPE).

cs.CV↗

arXiv2026

Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation

Omni-modal language models are intended to jointly understand audio, visual inputs, and language, but benchmark gains can be inflated when visual evidence alone is enough to answer a query. We study whether current omni-modal benchmarks separate visual shortcuts from genuine audio-visual-language evidence integration, and how post-training behaves under a visually debiased evaluation setting. We audit nine omni-modal benchmarks with visual-only probing, remove visually solvable queries, and retain full subsets when filtering is undefined or would make comparisons unstable. This yields OmniClean, a cleaned evaluation view with 8,551 retained queries from 16,968 audited queries. On OmniClean, we evaluate OmniBoost, a three-stage post-training recipe based on Qwen2.5-Omni-3B: mixed bi-modal SFT, mixed-modality RLVR, and SFT on self-distilled data. Balanced bi-modal SFT gives limited and uneven gains, RLVR provides the first broad improvement, and self-distillation reshapes the benchmark profile. After SFT on self-distilled data, the 3B model reaches performance comparable to, and in aggregate slightly above, Qwen3-Omni-30B-A3B-Instruct without using a stronger omni-modal teacher. These results show that omni-modal progress is easier to interpret when evaluation controls visual leakage, and that small omni-modal models can benefit from staged post-training with self-distilled omni-query supervision. Project page: https://cheliu-computation.github.io/omni/

cs.MM↗

arXiv2026

Two-Phonon Resonance Drives Multicomponent Mechanical Cat States

Using quadratic optomechanical coupling to prepare high-purity mechanical cat states is not feasible as its strength is several orders weaker than linear optomechanical coupling. Here, using only linear coupling in a multimode system, we achieve strong interaction between photons and two phonons, enabling the deterministic generation of high-purity multicomponent mechanical cats. Mediated by an auxiliary supermode, when other two optical supermodes satisfy the two-phonon resonance condition, the process whereby the annihilation of a high-frequency photon accompanied by the creation of a low-frequency photon and two phonons is strongly enhanced. Such resonant two-phonon process drives multiple rotations and interferences of mechanical coherent states, deterministically generating a multicomponent mechanical cat immune to both mechanical and optical losses. Our work provides an universal strategy for enhancing high-order phonon nonlinearities, paving the way for quantum state engineering, quantum precision measurement and fault-tolerant quantum computation.

quant-ph↗

arXiv2026

Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models

Real-time Spoken Language Models (SLMs) struggle to leverage Chain-of-Thought (CoT) reasoning due to the prohibitive latency of generating the entire thought process sequentially. Enabling SLMs to think while speaking, similar to humans, is attracting increasing attention. We present, for the first time, Mind-Paced Speaking (MPS), a brain-inspired framework that enables high-fidelity, real-time reasoning. Similar to how humans utilize distinct brain regions for thinking and responding, we propose a novel dual-brain approach, employing a "Formulation Brain" for high-level reasoning to pace and guide a separate "Articulation Brain" for fluent speech generation. This division of labor eliminates mode-switching, preserving the integrity of the reasoning process. Experiments show that MPS significantly outperforms existing think-while-speaking methods and achieves reasoning performance comparable to models that pre-compute the full CoT before speaking, while drastically reducing latency. Under a zero-latency configuration, the proposed method achieves an accuracy of 92.8% on the mathematical reasoning task Spoken-MQA and attains a score of 82.5 on the speech conversation task URO-Bench. MPS is the methodology underlying our released Step-Audio R1.1 system, effectively bridging the gap between high-quality reasoning and real-time interaction.

cs.CL↗

arXiv2026

Unraveling Intrinsic Thermal Conductivity in Layered Conductive MOF Single Crystals

Layered conductive metal-organic frameworks (LCMOFs) show great promise in energy and electronics due to their high electrical conductivity and tunable pore structures. They are considered ideal "phonon-glass, electron-crystal" materials. However, their intrinsic thermal transport properties, particularly the thermal conductivity in the single-crystalline state, have never been explored before. The applicability of the Wiedemann-Franz law to such complex porous materials is a key scientific question to describe their thermoelectric relationship. We investigated single crystals of three LCMOFs (Cu3HHTP2, Co9HHTP4, Nd3HHTP2) using the microfabricated suspended device. Results showed ultralow thermal conductivities (0.075-0.194 W m-1 K-1) along the π-π stacking direction. Crucially, Nd3HHTP2 exhibited a high electrical conductivity of 398 S cm-1, yet its thermal conductivity (0.148 W m-1 K-1) was comparable to the other two LCMOFs with significantly lower electrical conductivities. Structural characterization revealed that the incommensurate modulation, and in-plane correlated disorder within the Nd3HHTP2 structure are the potential causes of strong phonon scattering and the observed ultralow thermal conductivity.

cond-mat.mtrl-sci↗

arXiv2026

OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognition

Online micro gesture recognition from hand skeletons is critical for VR/AR interaction but faces challenges due to limited public datasets and task-specific algorithms. Micro gestures involve subtle motion patterns, which make constructing datasets with precise skeletons and frame-level annotations difficult. To this end, we develop a multi-view self-supervised pipeline to automatically generate skeleton data, complemented by heuristic rules and expert refinement for semi-automatic annotation. Based on this pipeline, we introduce OMG-Bench, the first large-scale public benchmark for skeleton-based online micro gesture recognition. It features 40 fine-grained gesture classes with 13,948 instances across 1,272 sequences, characterized by subtle motions, rapid dynamics, and continuous execution. To tackle these challenges, we propose Hierarchical Memory-Augmented Transformer (HMATr), an end-to-end framework that unifies gesture detection and classification by leveraging hierarchical memory banks which store frame-level details and window-level semantics to preserve historical context. In addition, it employs learnable position-aware queries initialized from the memory to implicitly encode gesture positions and semantics. Experiments show that HMATr outperforms state-of-the-art methods by 7.6% in detection rate, establishing a strong baseline for online micro gesture recognition. Project page: https://omg-bench.github.io/

cs.CV↗

arXiv2026

Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives

Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that blurs the phonetic boundaries. Although the constituent languages may be individually high-resource, the scarcity of annotated code-switching data further compounds these challenges. In this paper, we systematically analyze CS-ASR from both model-centric and data-centric perspectives. By comparing state-of-the-art algorithmic methods, including language-specific processing and auxiliary language-aware multi-task learning, we discuss their varying effectiveness across datasets with different linguistic characteristics. On the data side, we first investigate TTS as a data augmentation method. By varying the textual characteristics and speaker accents, we analyze the impact of language confusion and accent bias on CS-ASR. To further mitigate data scarcity and enhance textual diversity, we propose a prompting strategy by simplifying the equivalence constraint theory (SECT) to guide large language models (LLMs) in generating linguistically valid code-switching text. The proposed SECT outperforms existing methods in ASR performance and linguistic quality assessments, generating code-switching text that more closely resembles real-world code-switching text. When used to generate speech-text pairs via TTS, SECT proves effective in improving CS-ASR performance. Our analysis of both model- and data-centric methods underscores that effective CS-ASR requires strategies to be carefully aligned with the specific linguistic characteristics of the code-switching data.

eess.AS↗

arXiv2026

Dr.Occ: Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for Autonomous Driving

3D semantic occupancy prediction is crucial for autonomous driving perception, offering comprehensive geometric scene understanding and semantic recognition. However, existing methods struggle with geometric misalignment in view transformation due to the lack of pixel-level accurate depth estimation, and severe spatial class imbalance where semantic categories exhibit strong spatial anisotropy. To address these challenges, we propose Dr. Occ, a depth- and region-guided occupancy prediction framework. Specifically, we introduce a depth-guided 2D-to-3D View Transformer (D$^2$-VFormer) that effectively leverages high-quality dense depth cues from MoGe-2 to construct reliable geometric priors, thereby enabling precise geometric alignment of voxel features. Moreover, inspired by the Mixture-of-Experts (MoE) framework, we propose a region-guided Expert Transformer (R/R$^2$-EFormer) that adaptively allocates region-specific experts to focus on different spatial regions, effectively addressing spatial semantic variations. Thus, the two components make complementary contributions: depth guidance ensures geometric alignment, while region experts enhance semantic learning. Experiments on the Occ3D--nuScenes benchmark demonstrate that Dr. Occ improves the strong baseline BEVDet4D by 7.43% mIoU and 3.09% IoU under the full vision-only setting.

cs.CV↗

arXiv2026

CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System

Large language models are enabling language-conditioned agents in interactive environments, but highly cooperative tasks often impose two simultaneous constraints: sub-second real-time coordination and sustained multi-episode adaptation under a strict online token budget. Existing approaches either rely on frequent in-episode reasoning that induces latency and timing jitter, or deliver post-episode improvements through unstructured text that is difficult to compile into reliable low-cost execution. We propose CoWork-X, an active co-evolution framework that casts peer collaboration as a closed-loop optimization problem across episodes, inspired by fast--slow memory separation. CoWork-X instantiates a Skill-Agent that executes via HTN (hierarchical task network)-based skill retrieval from a structured, interpretable, and compositional skill library, and a post-episode Co-Optimizer that performs patch-style skill consolidation with explicit budget constraints and drift regularization. Experiments in challenging Overcooked-AI-like realtime collaboration benchmarks demonstrate that CoWork-X achieves stable, cumulative performance gains while steadily reducing online latency and token usage.

cs.CL↗

arXiv2026

Analysis of Full Order Observer Based Control for Spacecraft Orbit Maneuver Trajectory Under Solar Radiation Pressure

This study investigates the application of modern control theory to improve the precision of spacecraft orbit maneuvers in low Earth orbit under the influence of solar radiation pressure. A full order observer based feedback control framework is developed to estimate system states and compensate for external disturbances during the trajectory correction phase following main engine cut off. The maneuver trajectory is generated using Lambert guidance, while the observer based controller ensures accurate tracking of the target orbit despite SRP perturbations. The effectiveness of the proposed design is assessed through stability, observability, and controllability analyses. Stability is validated by step-response simulations and eigenvalue distributions of the system dynamics. Observability is demonstrated through state matrix rank analysis, confirming complete state estimation. Controllability is verified using state feedback rank conditions and corresponding control performance plots. Comparative simulations highlight that, in contrast to uncontrolled or conventional control cases, the observer based controller achieves improved trajectory accuracy and robust disturbance rejection with moderate control effort. These findings indicate that observer-based feedback control offers a reliable and scalable solution for precision orbital maneuvering in LEO missions subject to environmental disturbances.

eess.SY↗

arXiv2026

DepFlow: Disentangled Speech Generation to Mitigate Semantic Bias in Depression Detection

Speech is a scalable and non-invasive biomarker for early mental health screening. However, widely used depression datasets like DAIC-WOZ exhibit strong coupling between linguistic sentiment and diagnostic labels, encouraging models to learn semantic shortcuts. As a result, model robustness may be compromised in real-world scenarios, such as Camouflaged Depression, where individuals maintain socially positive or neutral language despite underlying depressive states. To mitigate this semantic bias, we propose DepFlow, a three-stage depression-conditioned text-to-speech framework. First, a Depression Acoustic Encoder learns speaker- and content-invariant depression embeddings through adversarial training, achieving effective disentanglement while preserving depression discriminability (ROC-AUC: 0.693). Second, a flow-matching TTS model with FiLM modulation injects these embeddings into synthesis, enabling control over depressive severity while preserving content and speaker identity. Third, a prototype-based severity mapping mechanism provides smooth and interpretable manipulation across the depression continuum. Using DepFlow, we construct a Camouflage Depression-oriented Augmentation (CDoA) dataset that pairs depressed acoustic patterns with positive/neutral content from a sentiment-stratified text bank, creating acoustic-semantic mismatches underrepresented in natural data. Evaluated across three depression detection architectures, CDoA improves macro-F1 by 9%, 12%, and 5%, respectively, consistently outperforming conventional augmentation strategies in depression Detection. Beyond enhancing robustness, DepFlow provides a controllable synthesis platform for conversational systems and simulation-based evaluation, where real clinical data remains limited by ethical and coverage constraints.

cs.CL↗

arXiv2025

A Mass-Independent Damping Timescale in Black Hole Accretion Systems

The scaling laws reveal the underlying structural similarities shared by astrophysical systems across vastly different scales. In black hole accretion systems, the scaling relations between the characteristic damping timescales (CDTs) of light curves and black hole mass offer valuable insights into the underlying physical structure of accretion disks. Here, we investigate the long-term hard X-ray CDTs of 106 black hole and neutron star accretion systems using light curves from the \textit{Swift} Burst Alert Telescope 157-month catalog. Unexpectedly, for the first time, we discover a mass-independent CDT in these black hole accretion systems, in contrast to well-established scaling laws. This puzzling phenomenon can be attributed to conductive timescales arising from disk--corona interactions, instead of the intrinsic accretion disk processes characterized by scaling laws, and it may further modulate jet emission in blazars. This result demonstrates thermal conduction as a key mechanism driving hard X-ray variability and offers new observational evidence for the disk--corona--jet connection.

astro-ph.HE↗