arXiv subjects

Xu Li

Publications and source records attributed to Xu Li.

At least 19 recordsLinked to original sources

arXiv2026

Qwen-Audio-3.0-ASR Technical Report

In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model scaling, and deep integration with large language models (LLMs). However, bridging the gap between academic benchmark performance and real-world production utility remains a persistent challenge, particularly in handling diverse regional dialects, dynamic entities and hotwords, long-range contextual information, and disfluent spontaneous speech. In this report, we present Qwen-Audio-3.0-ASR, a Mixture-of-Experts (MoE) LLM-based ASR system designed to address these production demands through a unified, instruction-following framework. The model is built upon the Qwen backbone, and is trained on tens of millions of hours of large-scale speech data. Qwen-Audio-3.0-ASR supports transcription across 30 languages and 16 Chinese dialectal varieties spanning eight major dialect regions. Beyond multilingual and dialectal recognition, the model provides production-oriented capabilities including industry-domain entity recognition, hierarchical hotword customization, native single-pass transcription polishing, and long-audio contextual modeling. We further develop a dedicated streaming variant, Qwen-Audio-3.0-ASR-Streaming, for latency-sensitive applications. Extensive evaluations on Chinese, English, multilingual, and real-world industrial test sets demonstrate state-of-the-art or highly competitive recognition performance across a broad range of evaluation conditions, with strong performance relative to leading commercial and proprietary systems including GPT-4o Transcribe and Gemini 3.1 Pro.

cs.CL↗

arXiv2026

MVWeaver: A Hierarchical Music Video Generation Agent with a Learned Song-to-Visual Bridge

Music videos are an important form of audiovisual expression in contemporary culture. They translate and extend the expressive content of songs through deliberate visual design. Existing automatic music video (MV) generation systems can generate visually plausible shots, yet often struggle with long-form coherence and song-grounded visual development. We present MVWeaver, a music video generation agent that integrates hierarchical planning with a learned song-to-visual bridge that translates song understanding into executable shot plans. The MVWeaver architecture comprises a comprehensive song analysis module, a visual planner that constructs hierarchical plans, and downstream image and video generation models that render the planned content. To equip a general-purpose LLM with MV-specific song-to-visual knowledge, we learn a bridge between song analysis and visual planning from real-MV-derived supervision and curate 1,861 real-world song--MV pairs with structured song-side, MV-side, and teacher-inferred song-to-visual rationale annotations. Using these annotations, we perform LoRA-based supervised fine-tuning (SFT) of a large language model to predict song-to-visual bridges that guide hierarchical visual planning. Our experiments demonstrate stronger song-grounded visual translation, richer visual development, and greater conceptual and shot-to-shot coherence, while ablations support the benefits of learned bridge conditioning.

cs.MM↗

arXiv2026

Closing the Verification Loop: Self-Check Captioning for Long-Paragraph Detailed Audio Captioning

Long-paragraph detailed audio captioning, which requires dense and transcript-faithful descriptions of fine-grained audio content, remains unsolved for current audio-visual multimodal language models. We attribute this failure to two structural problems. The first is data poverty, as no public corpus jointly provides long clips, paragraph captions, and verbatim-transcript fidelity. The second is generation-mode failure, evidenced by a 44.8 to 46.4 percentage-point gap between right-audio and shuffled-audio multiple-choice question (MCQ) accuracy. We address both within Self-Check Captioning (SCC), a unified framework that instantiates audio-grounded question answering as the verification primitive at every lifecycle stage. SCC yields three artifacts. Long-paragraph Audio Caption 50k (LACap-50k) is a 50,222-clip audio-visual corpus with 491.5-word captions and a post-hoc automatic speech recognition (ASR) audit. Layer-Curvature Supervised Fine-Tuning (LC-SFT) is the first on-policy supervised fine-tuning method to weight tokens by intermediate-layer evidence, motivated by our identification of Late-Layer Semantic-Entropy Collapse (SEC). SCC-Verifier arbitrates among caption rollouts via audio-grounded self-answering at inference. Across multiple benchmarks, our system attains state-of-the-art among open-source captioners and is competitive with proprietary baselines. We release LACap-50k to fill the resource gap for long-paragraph detailed audio captioning research.

cs.SD↗

arXiv2026

Relative Time Intervals Representation for Word-level Timestamping with Masked Training

Although Speech Large Language Models (SpeechLLMs) excel at speech understanding and generation, their capacity for fine-grained, temporally aligned outputs remains underexplored. Our work addresses this gap by enabling SpeechLLMs to jointly model speech content and temporal structure, effectively transforming them from ``content understanding machines" into ``temporal-aware content understanding machines". Specifically, we replace traditional absolute timestamps with relative timestamps, achieving a more compact vocabulary and stronger generalization capabilities. To efficiently infuse timestamp prediction ability into pre-trained large language models, we introduce a hybrid fine-tuning strategy: full-parameter fine-tuning of the timestamp-augmented embedding layer and language model head, combined with LoRA fine-tuning of the decoder layers. Moreover, we design a masked timestamp training objective, preventing the model from over-relying on ground-truth timestamps, and thereby enhancing robustness against noisy real-world annotations. Extensive experiments demonstrate that our approach achieves significant improvements in timestamp prediction accuracy while maintaining strong speech transcription performance.

cs.AI↗

arXiv2026

ForeSightGuide: An Anticipatory Framework toward Accurate and Low-Redundancy Guidance for the Visually Impaired

Electronic travel aids are pivotal for the independent mobility of the visually impaired. While Vision-Language Models (VLMs) offer rich environmental understanding, they often suffer from excessive false positives in dynamic scenarios, leading to cognitive overload. To address this, we present ForeSightGuide, an anticipatory assistive guidance framework that couples semantic scene understanding with predictive hazard assessment. Unlike reactive systems, ForeSightGuide leverages the reasoning capabilities of VLMs to anticipate obstacle motion, effectively filtering out non-threatening objects to provide concise, actionable guidance. To validate our approach, we introduce a novel dataset captured in complex, dynamic real-world traffic scenes, designed to benchmark predictive capabilities. Extensive experiments on both public benchmarks and our proposed dataset demonstrate that ForeSightGuide achieves state-of-the-art performance. Notably, it significantly mitigates information overload by reducing redundant alerts to 0.299 per guidance output while maintaining a low missed-hazard rate of 0.112, proving its efficacy for safe walking assistance.

cs.CV↗

arXiv2026

Can Large Language Models Explain Flight Safety Events? A Prior-Guided Semantic LLM-based Approach

Improving flight safety with flight data requires not only accurate detection of risk events, but more importantly, clear interpretation of their underlying causes at the level of pilot control behavior. Existing explainable AI techniques, such as feature importance maps, often require considerable domain knowledge to translate them into operationally meaningful explanations. Large Language Models (LLMs), which excel at language reasoning, bring a promising solution to this issue. However, applying LLMs in this domain presents key challenges such as modal inconsistency, limited classification ability, scarcity of task-specific data for fine-tuning, and lack of domain knowledge. To overcome these challenges, we propose FlightLLM, a prior-guided semantic LLM-based approach for interpretable flight safety analysis. Specifically, we first perform feature engineering to address modal inconsistency, combining statistical descriptors with physically meaningful flight indicators. This representation is further processed by a Semantic Discretization module, which converts abstract numerical patterns into qualitative descriptions that are more compatible with language reasoning. In addition, since LLMs are not inherently strong classifiers, CatBoost is incorporated as a statistical expert, and its prediction results are injected into the prompt as prior guidance. A contrastive few-shot learning strategy is further adopted to compensate for limited data. Finally, we design structured prompts to embed aviation-specific knowledge into the inference process. Using hard landing, a representative risk event with complex causal mechanisms, as an anchor point, we evaluate FlightLLM on a dataset of 704 real-world A320 flight samples. Experimental results show that the proposed approach achieves competitive classification performance while generating direct and reasonable explanations for event causes.

cs.AI↗

arXiv2026

ACE-Cap: Active Evidence Acquisition via Agentic Co-Evolution for Long-Paragraph Fine-Grained Audio Captioning

Long-paragraph fine-grained audio captioning requires models to recover diverse acoustic facts while avoiding omissions and unsupported details. However, prevailing captioners remain passive one-shot generators: once a detail is overlooked, they cannot identify the evidence gap, query the audio for targeted information, or decide when sufficient evidence has been collected. We formulate this task as active evidence acquisition and introduce Agentic Co-Evolution for Captioning (ACE-Cap). The framework uses multi-turn interaction between a Composer and an Instruct model to form a closed evidence-acquisition loop. A Captioner first produces an initial description. Conditioned on this description and the interaction history, a text-only Composer asks targeted questions about unresolved acoustic attributes, while an audio-conditioned Instruct model provides grounded answers. The Composer then decides when to terminate and synthesizes the accumulated evidence into a final caption. ACE-Cap trains these roles through a unified gold-to-prediction reward derived from fixed, gold-grounded multiple-choice questions and a frozen caption-only judge. For credit assignment in variable-length interactions, LOOP-GRPO replaces the trajectory-wide scalar advantage with span-aligned signals: leave-one-out contributions of individual questions to the accumulated evidence, a quality-cost utility for stopping, and an evidence-preservation utility for final synthesis. Role-wise warm-up followed by alternating Composer and Instruct optimization keeps each update a well-defined single-policy problem while allowing the roles to co-evolve. ACE-Cap thus turns captioning from passive one-shot generation into an adaptive process that learns what evidence to acquire, when to stop, and how to preserve it in a long-paragraph caption.

cs.SD↗

arXiv2026

SingDance: Compositional Zero-Shot Singing-and-Dancing Video Generation with Role-Aware Audio Conditioning

Generating personalized dance videos from a reference image, text prompt, and audio track requires music-conditioned body motion. Singing-and-dancing adds a second requirement: the visible subject must also articulate the vocals. Existing music-conditioned methods focus primarily on choreography, while speech-driven models generally assume that the visible subject produces the input voice, leaving this combined setting largely underexplored. We introduce SingDance, a unified video diffusion framework that formulates controllable vocal articulation as a semantic role: the visible subject is either the source, who produces the vocal signal, or the listener, who receives it from an off-screen performer. Hard-compact routing selects task-relevant speech, music, and role conditions, which are composed through frame-wise joint audio injection; source and listener retain the same speech pathway. Training uses asymmetric supervision: on-screen speaking and curated off-screen conversational-response videos establish role control, while instrumental and song-based dancing-only videos establish music-conditioned body motion. The target Song/Source configuration is never observed during training. At inference, assigning the source role to a song composes separately learned articulation and song-conditioned dance capabilities, enabling compositional zero-shot singing-and-dancing. Experiments demonstrate strong motion--beat alignment and visual fidelity, reliable paired switching of vocal articulation while preserving music-aligned body motion, and highly competitive lip synchronization with substantially fewer generation-time parameters than the strongest speech-driven baseline evaluated.

cs.SD↗

arXiv2026

How to Identify a Majoron: Effective Field Theories of Spontaneous Lepton Number Breaking

We revisit the traditional Type I, II and III Seesaw mechanisms in the presence of a complex scalar field charged under a global $U(1)$ symmetry that can be identified with lepton number and the Peccei-Quinn symmetry. After symmetry breaking, the radial mode becomes heavy while the angular mode appears as an axion-like particle, traditionally dubbed the Majoron. We construct the effective field theory obtained after integrating out the heavy states and analyse two matching orders: first removing the radial mode and then the Seesaw fields, and vice versa. Both procedures yield the same low-energy Lagrangian containing only Standard Model fields and the Majoron. Because a single vacuum expectation value fixes the mediator masses, the radial mode and every Majoron coupling, these models predict relations among observables rather than their individual size, and it is these relations that are testable. Indeed, the invisible Higgs width is locked to the universal suppression of the Higgs couplings, while the Majoron-lepton coupling is fixed by the measured non-unitarity of the leptonic mixing matrix, and the two independently give comparable lower bounds on the same lepton-number breaking scale, of order $1$-$10$ TeV. Neutrinoless double beta decay with Majoron emission, by contrast, has no sensitivity in this class of models. The framework is thus falsifiable even when the new states lie far beyond experimental reach.

hep-ph↗

arXiv2026

AudioMap: Cloze-and-Choice Reinforcement Learning for Time-Aware Dense Audio Captioning

Time-aware dense audio captioning (TDAC) aims to generate multiple fine-grained attributes (dense) of the audio with precise time boundaries (time-aware). Existing methods struggle to achieve these two goals and mainly rely on supervised fine-tuning, yielding sub-optimal performance. While reinforcement learning (RL) shows promise, applying it to TDAC faces two main challenges: (1) existing rewards are too coarse to supervise multi-event, multi-attribute, and multi-relation descriptions in a fine-grained manner; and (2) temporal supervision is difficult for free-form captions, where flexible event-time expressions make reliable event-time correspondence challenging. To address these challenges, we propose AudioMap, a novel RL-based TDAC framework, which shifts to a unified cloze-and-choice reward paradigm. Specifically, we introduce the Evidence Sufficiency Reward (ESR) with an asymmetric hierarchical scoring mechanism to promote fine-grained accuracy and descriptive richness across diverse acoustic dimensions. Furthermore, we design the Event-Conditioned Temporal Reward (ECTR) to structurally bind timestamps to event semantics via temporal IoU, accompanied by a dual-curriculum learning strategy to facilitate the training process. Finally, to support this task, we construct the first time-aware fine-grained audio captioning dataset, AudioMapCap-44K, which contains 44K carefully annotated captions. Extensive experiments across diverse benchmarks show that AudioMap achieves state-of-the-art (SOTA) performance among open-source models and delivers competitive or superior results relative to proprietary models. Project page and release updates are available at https://github.com/ryysayhi/AudioMap.

cs.SD↗

arXiv2026

SonicWeave: Chunk-Routed Mixture-of-Experts for Unified Audio Scene Generation

Text-conditioned general audio generation is moving beyond isolated speech, music, and sound-effect synthesis toward a single model that can compose them into controllable, coherent audio scenes. This unified setting is particularly challenging: heterogeneous components impose conflicting structural requirements on a shared backbone, while a complex mixed scene may contain locally distinct or overlapping content that demands fine-grained adaptation within the same clip. Existing audio mixture-of-experts (MoEs) mainly route at the domain level, while token-wise routing overlooks the local continuity inherent to acoustic signals. We propose SonicWeave, a flow-matching model for unified audio scene generation. At its core is a chunk-routed MoE with a conflict-gated prior-evidence routing mechanism (CPE-MoE). CPE-MoE routes contiguous acoustic chunks by combining a global prior that encodes the structured text condition and diffusion phase with local evidence from the evolving acoustic state. A learned conflict gate favors the prior when local states are unreliable, while allowing local evidence to influence routing when a region departs from the global scene context. SonicWeave supports speech, music, sound effects, singing, and their fine-grained mixtures with a single set of weights. Across TTS, TTA, and TTM benchmarks, SonicWeave consistently improves over controlled Dense and Base-MoE baselines. Complex-scene evaluation further demonstrates improved compositional quality, while routing analyses reveal content-dependent expert specialization across diffusion phases. These results suggest that temporally coherent, prior-evidence routing is an effective conditional-computation strategy for unified audio generation. Project page: https://caiyunrui.github.io/SonicWeave.

cs.SD↗

arXiv2026

Criticality and reduced dynamical resilience in PM2.5 pollution systems

Concentration-based metrics underpin air-quality assessment, while dynamical persistence and recovery describe how rapidly high-PM2.5 episodes dissipate and how strongly they retain memory. Here we introduce a finite-memory multiplicative reversion (FMMR) process that links the lognormal concentration backbone of PM2.5 variability with event recurrence, temporal memory, variance amplification and local dynamical resilience. Across station observations and reanalysis data, elevated PM2.5 regimes show a coherent set of critical signatures: stronger memory, rising autocorrelation, broader upper tails, amplified variance, reduced resilience and more clustered exceedance events. Together, these co-occurring signals reveal dynamical criticality in PM2.5 pollution systems, with critical slowing down expressed as a loss of restoring capacity under high-pollution conditions. A gridded comparison across populated and emission-influenced regions further shows that areas with similar PM2.5 burden can differ in recovery capacity, while eastern China has shifted toward higher resilience during recent air-quality improvements and India and West Africa occupy lower-resilience states. By identifying where pollution burden and recovery capacity diverge, these findings establish dynamical persistence and resilience as complementary dimensions of PM2.5 risk and provide a quantitative basis for resilience-oriented air-quality assessment.

physics.soc-ph↗

arXiv2026

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference

Large Vision-Language Models (LVLMs) typically require processing hundreds to thousands of visual tokens, leading to substantial inference overhead. Existing visual token pruning methods either operate before the LLM using text-agnostic heuristics or prune inside the LLM at the cost of efficiency and noisy cross-modal attention. To address these limitations, we propose CRISP, a pre-LLM yet text-driven visual token pruning framework that preserves both instruction-relevant evidence and essential scene context. CRISP works in a two-stage pipeline: Stage 1 first identifies text-aligned visual tokens, and Stage 2 enhances contextual completeness through semantic diversity. Extensive experiments on LLaVA-1.5 and LLaVA-NeXT demonstrate that CRISP achieves superior performance retention under aggressive pruning ratios, maintaining up to 99.5% accuracy while reducing inference cost and latency by more than 2 times. CRISP serves as a practical solution for efficient LVLM inference, especially in resource-constrained scenarios.

cs.CV↗

arXiv2026

Surface code logical operations on a superconducting quantum processor

Fault-tolerant quantum computation requires logical operations that manipulate encoded information while preserving quantum error-correction protection. In planar surface-code architectures, code deformation and lattice surgery provide a local, measurement-based route to such operations. Here we experimentally realize key elements of patch-based surface-code logical processing on a 107-qubit superconducting quantum processor. We first implement a reusable primitive layer comprising merge and split, patch expansion and shrinkage, and deformations mediated by domain walls and twist defects. We then compose these primitives to realize logical state routing, the logical controlled-NOT gate, and the single-qubit Hadamard and phase gates, which together form a Clifford-generating set. All operations are implemented on distance-three rotated surface-code patches with multi-round syndrome extraction and neural-network decoding, without post-selection. Our results advance superconducting surface-code experiments from protected logical memory to active, patch-based fault-tolerant logical operations.

quant-ph↗

arXiv2026

FlexiSLM: A Spoken Language Model with Dynamic and Controllable Frame Rates

Spoken language models (SLMs) extend LLMs to speech input and output. Existing SLMs represent speech at fixed frame rates (e.g., 25 or 12.5 Hz), ignoring the time-varying information density of speech and offering limited flexibility to trade off quality for speed at inference time. Recent audio tokenizer research has proposed dynamic-frame-rate speech coding, which exploits this non-uniformity and enables two new capabilities: very low average frame rates and frame-rate controllability. However, this technique has not yet been applied to SLMs. We introduce FlexiSLM, the first SLM with dynamic and controllable frame rates. FlexiSLM uses the pretrained FlexiCodec to obtain dynamic speech output tokens. The main contributions of this work are threefold: (1) integrating and validating this dynamic-rate representation within a multi-task, speech-to-speech SLM architecture; (2) extending it to frame compression on the input side; and (3) introducing direct frame-rate conditioning to enable accurate and controllable SLM inference. FlexiSLM outperforms fixed-frame-rate 7B models including Qwen2.5-Omni and Kimi-Audio at its 12.5 Hz and 6.25 Hz operating points. We further verify that FlexiSLM can be accurately steered down to 4.0 Hz; at 6.25 Hz, it roughly halves inference time relative to 12.5 Hz while retaining strong speech-to-speech quality. Audio samples are available at: https://flexislm.github.io. Code and data are available at: https://github.com/AmphionTeam/FlexiSLM.

cs.SD↗

arXiv2026

ParkingTransformer: LLM-Enhanced End-to-End Trajectory Planning for Autonomous Parking

End-to-end autonomous parking has emerged as a critical task within the realm of autonomous driving. However, existing methods suffer from black-box characteristics, lacking high-level semantic understanding and interpretability, which impedes the realization of seamless long-distance autonomous parking from the road to the target spot. To address these limitations, we propose ParkingTransformer, a novel framework that leverages multi-view perception and the scene understanding capability of Large Language Models (LLMs). By combining trajectory queries with LLMs implicit state features, our method interacts directly with historical information and raw sensor data to output planning trajectories, eliminating the need for dense Bird's-View (BEV) representations. To compensate for the inadequate spatial reasoning ability of LLMs, we introduce 3D positional encoding to explicitly inject spatial geometric awareness. Furthermore, a fixed-window streaming mechanism is designed for historical information processing, significantly improving long-term temporal processing efficiency and inference speed. Additionally, a coarse-to-fine decoding strategy is employed to progressively enhance trajectory precision. Extensive closed-loop experiments are conducted on the CARLA simulator and real-world vehicle platforms. The results demonstrate that our method achieves a driving score of 61.32 in CARLA simulator and an average success rate of 88.70% in real-world experiments, validating the feasibility and effectiveness of the proposed algorithms.

cs.RO↗

arXiv2026

An Ontology-Guided Multi-Anchor Graph Retrieval Framework for Traffic Legal Liability Determination

Traffic law liability determination is critical for assigning legal penalties, requiring the simultaneous identification of interdependent statutory provisions across multiple legal dimensions. However, existing retrieval-augmented generation methods suffer from a multi-dimensional retrieval bottleneck: single axis architectures compress complex legal queries into a single pathway, causing interdependent statutory dimensions to be overlooked. To address this, we propose OMAGR, an ontology-guided framework that decomposes queries into ontology-aligned anchors and executes parallel graph retrieval across each dimension, ensuring independent retrieval across dimensions before fusion. To evaluate the proposed method, we created the TrafficLaw-QA dataset, an expert-validated benchmark dataset containing 200 questions and 527 legal provisions. Results show that TrafficOmni-RAG outperforms baselines on Context Precision and Faithfulness metrics. The findings demonstrate that parallel multi-anchor retrieval effectively resolves the multi-dimensional retrieval bottleneck, offering a promising direction for traffic law liability determination research.

cs.CL↗

arXiv2026

Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts

Generating novel, feasible, and high-quality research ideas is an important yet challenging task in scientific discovery. Recent Large Language Model (LLM)-based methods often ground idea generation with retrieved literature, but the retrieved evidence is usually provided as flat text, such as titles, abstracts, or summaries. Such flat contexts may contain redundant or weakly relevant information, while making cross-paper relations among problems, methods, mechanisms, and findings difficult to identify and trace. To address this challenge, we propose Graph2Idea, a knowledge graph-guided framework for retrieval-augmented scientific idea generation.Graph2Idea first retrieves papers according to the input topic, transforms them into structured knowledge triples, and dynamically constructs a target-centered knowledge graph to make literature relations explicit. It then extracts compact graph-derived contexts that retain target-relevant relational evidence while reducing noisy textual input. Based on these contexts, a two-stage generation process first identifies promising research directions and then guides the LLM to synthesize candidate ideas from graph-grounded evidence. Experiments on a scientific idea generation benchmark show that Graph2Idea outperforms representative baselines under the automatic evaluation protocol. Compared with the strongest baseline scores, it improves Novelty from 0.45 to 0.52, Quality from 0.24 to 0.29, and Feasibility from 0.22 to 0.28. These results suggest that graph-structured evidence helps LLMs generate research ideas through more explicit, compact, and traceable recombination of prior scientific knowledge.

cs.AI↗