arXiv subjects

Jing Peng

Publications and source records attributed to Jing Peng.

At least 19 recordsLinked to original sources

arXiv2026

Multilingual TASU: Extending Text-Only Alignment to Multilingual Speech Recognition via Simulated CTC Posteriors

Speech Large Language Models (Speech LLMs) achieve strong multilingual ASR when large-scale paired speech-text data is available, yet such resources remain scarce and highly imbalanced across languages. Text-Only Alignment for Speech Understanding (TASU) alleviates this bottleneck by training cross-modal alignment from simulated CTC posteriors without paired audio, but prior work has been limited to English, leaving open whether text-driven alignment can scale to the multilingual setting where data sparsity and cross-lingual phonetic interference amplify the difficulty of learning a shared alignment interface. In this work, we investigate TASU-style posterior alignment as a means of mitigating paired-data scarcity in multilingual ASR. We adopt the native 50,002-way posterior space of a frozen OWSM-CTC frontend as a shared multilingual interface to Qwen2.5-1.5B-Instruct, and systematically compare three supervision sources on eight Multilingual LibriSpeech languages: real audio-derived posteriors, heuristic CTC Posterior Simulation (CPS), and posteriors generated by a learned multilingual simulator. With real posteriors, LoRA adaptation reduces pooled WER from 10.08% (standalone OWSM-CTC) to 8.21%, improving all eight languages. For text-only alignment, the learned simulator substantially outperforms heuristic CPS and attains 10.51% WER with LoRA. Notably, a CPS-initialized model reaches 9.19% WER after only one real-posterior adaptation epoch using merely one-ninth of the complete MLS paired-speech training set, demonstrating that text-first initialization can drastically reduce the amount of paired audio required for competitive multilingual ASR. These findings establish TASU as a viable multilingual alignment framework and highlight text-only simulation as an effective remedy for paired-data scarcity and imbalance across languages.

eess.AS↗

arXiv2026

ETC-Bench: A Multilingual Benchmark for Evaluation-Side Transcript Canonicalization

Written transcripts of the same speech can differ in ways that are not uniquely determined by the speech signal. We formulate evaluation-side transcript canonicalization (ETC), which maps multiple surface forms to a single canonical form when their differences are not determined by speech. To our knowledge, ETC-Bench is the first and most comprehensive multilingual benchmark for evaluation-side transcript canonicalization, covering 181 phenomenon types across 12 languages. Each instance is a minimal pair that shares a sentence context and differs only in a target span exhibiting one phenomenon. To evaluate both canonicalization success and semantic preservation, we propose Semantic-preserving Exact-match Normalization Accuracy (SENA), which combines exact agreement between independently canonicalized pair members with a pair-relative BERTScore constraint against information loss. We further introduce the Taxonomy-guided Agent Canonicalization Skill (TACS), which provides LLM agents with phenomenon descriptions and explicit canonicalization contracts. Experiments with five baseline configurations and three TACS-based agents show that the agents outperform the baseline systems on shared languages. ETC-Bench provides a systematic testbed for evaluation-side transcript canonicalization across languages.

cs.CL↗

arXiv2026

dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model

Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language provides a flexible interface for expressing edit requests, but its ambiguity may leave the intended operation, parameters, or target region underspecified. We study a semi-formal transcript-grounded edit instruction that specifies operation categories and parameters and binds them to transcript spans or boundaries. This semantic timeline avoids explicit timestamp alignment and provides an externally inspectable contract for compositional edits. We instantiate the interface in dots$.$tts$.$edit, a speech editing model built on a continuous autoregressive speech generation architecture. Four representative speech-creation controls cover lexical content, affective expression, pitch and speaking-rate delivery, and temporal phrasing through text, emotion, prosody, and pause editing. Task-specific data pipelines construct operation- and scope-controlled pairs while retaining source-derived context outside each target region. We further introduce doteBench, a bilingual benchmark that measures precise instruction following, local preservation, and audio quality across the four controls and their composition. Experiments show leading overall instruction following and local preservation across its five editing categories, while audio quality remains comparable to existing open-source systems. Across three Seed-TTS-Eval shards, the model shows negligible differences from the base model in zero-shot TTS recognition error rate and speaker similarity.

cs.SD↗

arXiv2026

EPSBench: Benchmarking LLM Agents for Earnings Forecasting

Quarterly earnings forecasting requires an agent to connect financial evidence to the income-statement line items that produce a company's reported earnings. We introduce EPSBench, a benchmark for studying this ability across 149 firm-quarters from 86 US companies. Agents read a fixed collection of filings, earnings-call transcripts, and news, then estimate company-specific income-statement drivers with cited evidence. A shared accounting calculator converts these estimates into GAAP diluted earnings per share (EPS), providing a common basis for comparing forecast assumptions. We evaluate six models under a common harness, assessing point forecast error relative to date-matched analyst consensus and checking whether their prediction intervals achieve the stated coverage. Three models show no detectable paired difference in point forecast error from consensus, and three have higher error. Across all six models, nominal 80% intervals contain reported EPS in only 37--70% of runs that return an interval, and most misses fall above the upper bound because the forecasts run low. The driver records trace most of the error gap between models to operating-income estimates.

cs.CL↗

arXiv2026

Agentic Data Sampling Framework for Multilingual ASR via Linguistic-Aware Error-Driven Optimization

Multilingual automatic speech recognition (ASR) has achieved rapid progress with large-scale pretrained models and multilingual speech corpora. Previous studies have proved the pivotal role of data sampling in multilingual ASR performance. However, existing sampling strategies largely rely on time-consuming manual, heuristic-based designs. To address this, we propose a linguistic-aware agentic data sampling framework that introduces a data sampling LLM agent into the multilingual ASR training loop. The agent is driven by a linguistically grounded rubric that analyzes ASR errors from phonological, morphological, and syntactic perspectives, and uses the resulting feedback together with training statistics, budget constraints, and algorithm profiles to select domain-level, sample-level, and token-level sampling strategies. This design turns evaluation results into adaptive data-selection decisions rather than treating WER/CER as final endpoints only. We conduct experiments on twelve Common Voice languages using Whisper-medium as the ASR backbone. The results show that our method achieves performance better than full-data training while using less training data and lower computational resources, and substantially accelerates training convergence compared to conventional sampling strategies.

cs.CL↗

arXiv2026

Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents

Forecasting requires large language model (LLM) agents to gather evolving evidence, revise their beliefs, and make calibrated predictions over time. Yet evaluating and improving these capabilities is challenging because real-world events unfold continuously and outcomes may take months to resolve. We introduce Forecast-Dojo, a replayable environment that reconstructs resolved prediction-market events as sequences of dated forecasting steps, enabling reproducible evaluation, longitudinal analysis, and training from agent interactions. It comprises 1,568 Polymarket events split temporally into training and evaluation sets, alongside 18.8 million dated news articles. Across 12 models, research tools consistently improve forecasting performance, and greater capture of new evidence is associated with larger improvements over time. Nevertheless, all models trail historical market forecasts, while carrying a belief notebook across dates reduces research costs without consistently improving forecast quality. We supervise fine-tuned Qwen3-30B-A3B-Thinking-2507 on collected trajectories from Qwen3-235B-A22B-Thinking-2507 to demonstrate the environment's training utility. The student's accuracy is improved from 34.8% to 42.8% on the evaluation set.

cs.AI↗

arXiv2026

SURE-Tagger: Structured Speech Representations for Compositional Evaluation and Targeted Data Selection

Speech conveys linguistic content, speaker characteristics, temporal interactions, paralinguistic cues, and acoustic environments. While recent speech captioning models describe these dimensions in natural language, inconsistent attribute coverage and ambiguous omissions hinder systematic analysis across recordings. We introduce SURE-Tagger, a framework that constructs semi-structured speech representations with explicit attribute values, supplementary descriptions, and abstention under insufficient evidence. By integrating specialist observations through language-model reasoning, SURE-Tagger enables speech conditions to be consistently identified and jointly queried across datasets. We further introduce Tag-Bench, combining real recordings with controlled, agentically synthesized speech scenes and verified attribute annotations. On Tag-Bench, SURE-Tagger achieves the highest scores on 25 of 29 evaluated dimensions for real speech and 24 of 29 for synthetic speech, outperforming caption-based baselines across structural and descriptive attributes. Beyond annotation, we use these representations to construct cross-dataset evaluation subsets and reveal condition-specific ASR errors. Using a separate candidate pool, SURE-Tagger-guided selection reduces the overall ASR error rate of Qwen3-ASR-1.7B by 14.3% relative to the unadapted model under a one-hour fine-tuning budget, while caption-guided and random selection increase error in the same setting. These results demonstrate how structured speech representations can connect rich annotation, compositional evaluation, and targeted model improvement.

eess.AS↗

arXiv2026

In-Context Adapter Generation for Compositional Generalization in Large Audio Language Models

Large audio language models (LALMs) have achieved strong performance on standard speech and audio understanding tasks, yet their ability to systematically generalize to novel task compositions remains underexplored. Taking a meta-learning view, we extend Text-to-LoRA (T2L) to LALMs, generating instruction-conditioned LoRA adapters with a Transformer hypernetwork rather than learning a single fixed adapter shared across instructions. To exploit fine-grained task information, we introduce in-context adapter generation (ICAG), a token-level hypernetwork architecture; we call the resulting method T2L-ICAG. We evaluate this approach on two representative LALMs using SIFT-50M for supervised fine-tuning and construct a controlled compositional evaluation suite covering five task classes. Across two LALM backbones, T2L-ICAG consistently improves over static LoRA and also the global embedding-based T2L baseline. Coverage and capacity analyses further show that these gains are larger on structurally out-of-domain tasks and cannot be explained by parameter count alone. These results suggest that generating task-specific adapters from instructions is a promising direction for improving compositional generalization of LALMs.

eess.AS↗

arXiv2026

Bridging the Data Gap: Source-Informed Task-Space Transport for Few-Shot Diffusion

Many deployments require a model to move rapidly from a data-rich source to a related target observed only sparsely. This is especially consequential where target data are difficult to collect, as in healthcare settings with persistent population or acquisition imbalances. Retraining or fine-tuning a high-capacity generator for every target is costly and can be statistically unreliable when target data are scarce. We introduce Meta-Diff, which instead learns a recurring source--target relation once in a compact task space. A shared encoder maps each distribution to a low-dimensional coordinate; a learned relation transports a new source coordinate to its predicted target, and a shared diffusion backbone generates from that prediction without target-specific retraining. Controlled Gaussian-mixture experiments identify when this works: task identity must survive the representation, the relation must generalise across tasks, and the source--target shift must leave useful headroom for transport. On held-out CIFAR-100 validation tasks, correct source $+$ transport achieves 13.9% lower mean SW than transport from the wrong source. With validation-selected adaptation settings in the final-test one-target comparison, its mean SW is 14.7% lower than target-only modelling and 32.7% lower than full fine-tuning; the main route itself uses no target image and assumes the applicable relation is known. On matched CIFAR test episodes, generating from the clean-source coordinate and then applying the known corruption yields lower SW than task-space transport. Office-Home exposes a complementary boundary: transport can align target-domain statistics without reliable object identity. Together, these results recast extreme-few-shot adaptation as reusable transport in task space, while making the conditions for its success and failure directly measurable.

cs.LG↗

arXiv2026

VISH-ASR: Viterbi-Guided Selection of Hotwords for Speech-LLM Contextual ASR

Prompt-based contextual ASR requires selecting a compact hotword subset from large dynamic inventories, yet existing pre-selection methods rely either on discrete ASR hypotheses that may discard acoustic evidence or on separately trained retrieval models. We propose Viterbi-guided Selection of Hotwords (VISH), a training-free, plug-and-play framework that directly verifies candidate-specific acoustic support over frame-level CTC posteriors. VISH formulates pre-selection as constrained posterior search; M-VISH makes large-list verification scalable through frame-synchronous shared-prefix Viterbi search with bounded top-K pruning, while Bi-MVISH exploits complementary backward evidence for robust verification. Across five benchmarks, M-VISH achieves up to 11.7% absolute improvement in Best-F1 over a strong learned-retrieval baseline and reduces candidate-search latency by 75.2% at 2,000 candidates relative to hypothesis-based filtering. These results demonstrate the effectiveness of posterior-level verification for accurate and scalable hotword pre-selection without additional model training.

eess.AS↗

arXiv2026

UniAE-MoE: A Unified Audio Encoder via Mixture of Experts

Large Audio Language Models (LALMs) rely on effective audio encoders for multi-task performance. We introduce UniAE-MoE, a unified audio encoder designed to model cross-domain audio representations and achieve outstanding downstream understanding performance via a Mixture-of-Experts (MoE) architecture. Specifically, we explore mainstream audio encoders and integrate those from Qwen2-Audio and Audio-Flamingo 3, which demonstrate superior downstream capabilities. To facilitate effective model fusion, we improve our encoder using SwiGLU with shared experts to decouple encoder networks, and we further introduce a two-stage instruction-tuning strategy to better adapt the model to diverse downstream tasks. Moreover, we propose the task-specific data scaling (TSDS) technique to enhance UniAE-MoE's understanding capabilities. On the XARES-LLM benchmark, UniAE-MoE attains a score of 0.802, achieving state-of-the-art performance. It also delivers top-tier performance in the official Interspeech 2026 Audio Encoder Capability Challenge, further demonstrating robust generalization across diverse audio tasks. Together, these results validate the effectiveness of UniAE-MoE for unified audio understanding across speech, music, and general audio domains.

cs.SD↗

arXiv2026

Nuclear mass table in deformed relativistic Hartree-Bogoliubov theory in continuum, III: nuclei with $8 \leq Z \leq 120$

The mass table in the deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc) with the PC-PK1 density functional has been established for nuclei with $8 \leq Z \leq 120$, extended from the previous works for even-even nuclei [Zhang et al. (DRHBc mass table collaboration), At. Data Nucl. Data Tables 144, 101488 (2022)] and for even-$Z$ nuclei [Guo et al. (DRHBc mass table collaboration), At. Data Nucl. Data Tables 158, 101661 (2024)]. The calculated binding energies, two- and one-nucleon separation energies, root-mean-square (rms) radii of neutron, proton, matter, and charge distributions, quadrupole deformations, neutron and proton Fermi surfaces, and the blocked neutron (proton) orbitals of odd-$N$ ($Z$) nuclei are tabulated and compared with the available experimental data. A total of 9495 nuclei are predicted to be bound, with an rms deviation of 1.444 MeV from the 2380 mass data. Good agreement with the available experimental pairing gaps, $α$ decay energies, and charge radii is also achieved. The accuracies of the calculated nuclear masses and nucleon separation energies as well as the prediction for drip lines are compared with those obtained by other relativistic and nonrelativistic density functional calculations. It turns out that the DRHBc theory with PC-PK1 provides one of the best microscopic descriptions for nuclear masses. The systematics of nucleon separation energies, pairing gaps, pairing energies, two-nucleon gaps, $α$ decay energies, rms radii, quadrupole deformations, potential energy curves, neutron density distributions, and neutron mean-field potentials are discussed.

nucl-th↗

arXiv2026

Kapture: Capturing Cardiac Dynamics with Koopman-Governed Learning for Efficient Radar-Based Electrocardiogram Recovery

Millimeter-wave (mmWave) radar enables unobtrusive, contactless electrocardiogram (ECG) reconstruction for cardiac monitoring. Time-frequency spectrograms preserve fine cardiac patterns but often require large backbones to separate ECG-relevant features from respiration, motion, multipath, and subject-dependent interference. We propose Kapture, a parameter-efficient Koopman-governed framework that projects radar hidden states into a low-dimensional observable space and identifies a regularized full linear evolution operator from adjacent observable states. The Koopman-predicted observables refine subsequent hidden states for ECG reconstruction. To suppress predictable interference dynamics, a temporal contrastive objective pulls neighboring states together and separates non-neighbors, while reconstruction supervision preserves task relevance. Using approximately 80 minutes of quasi-static radar-ECG recordings containing realistic noise from body movements and other sources, Kapture consistently improves reconstruction across matched backbone widths, with the largest gains under aggressive compression. The compact configuration approaches the full-width reference accuracy with 68.1% fewer parameters and 91.3% fewer profiler-covered floating-point operations (FLOPs), while the full-width configuration delivers the strongest overall reconstruction performance. Our code will be made publicly available after potential publication.

eess.SP↗

arXiv2026

SURE-EVAL: A Systematic and Unified Agentic Framework for Reproducible Evaluation

Audio and speech models are released rapidly, but reported scores often conflate model capability with deployment and evaluation choices. The same checkpoint can produce different predictions under different runtimes, hardware, decoding settings, or fallback policies. Even fixed predictions can receive different scores under different normalization and metric implementations. Existing speech benchmarks standardize selected datasets or scoring procedures, but rarely connect heterogeneous model onboarding, controlled inference, and versioned scoring in one executable workflow. We introduce SURE-EVAL, a Systematic and Unified Agentic framework for Reproducible Evaluation of audio and speech systems. A Tool Agent Workflow converts model releases into isolated, verified callable tools. A Main Agent Workflow commits task-specific inference and scoring protocols, then delegates all score-bearing operations to versioned deterministic programs. Each result retains its runtime, protocol, pipeline nodes, predictions, and audit artifacts. Across 18 public releases covering automatic speech recognition, text-to-speech, voice conversion, speaker diarization, speaker-attributed recognition, and multi-task audio understanding, a Codex-only baseline completes 12 models in one shot, while the same agent with the SURE-EVAL Tool Agent Workflow completes all 18. We also conduct unified evaluations over seven ASR test conditions and two TTS subsets. A protocol analysis of three TTS systems finds absolute differences of 0.02-0.52 points between paper-reported and unified results, with the direction varying by model and language. These results show that reproducible evaluation requires controlling both model execution and output scoring.

eess.AS↗

arXiv2026

Making AI Scientists Auditable from Evidence to Claim

AI research systems can report improved results without establishing that the tested implementation matches the method described in their conclusions. We introduce Xcientist, a research harness that connects literature review, component-based idea generation, experiment validation and reporting. An evidence graph retains source passages, methods, baselines and evaluation conditions; component records track design revisions; and validation contracts specify the implementation, comparisons and artifacts required at each stage. We define claim drift as an unresolved mismatch between an accepted claim and its attributed sources, code or experiments. A retrospective audit across agent memory, traffic forecasting and physics-informed learning found audit claim drift rates of 3.6--16.7\% for Xcientist, lower than those of each of three comparison systems in all nine task-by-relation comparisons. This measure includes both confirmed mismatches and unverifiable claims; most of the difference arose from fewer unverifiable records. The case studies also document performance gains, unsuccessful revisions and limits on component attribution. This technical report describes the system, its implementation and the records needed to check how a proposed idea became a tested method and a final claim.

cs.AI↗

arXiv2026

Backbone-Adaptive Evidence Routing for Robust Pairwise LLM Judging

Pairwise language-model judges can gather evidence through direct comparison, reasoning, or reference-based verification, but no single protocol is best across benchmarks and judge backbones. We introduce Backbone-Adaptive Evidence Routing (BAER), which adapts the evidence mechanism while preserving candidate symmetry: swapping the two responses may reverse the preference but cannot change its strength. BAER separates each expert's signed preference from candidate-invariant reliability and builds three symmetric heads: evidence stacking, reliability-based expert routing, and candidate-blind reference verification. Development data select one head for each benchmark--backbone condition, and that choice is frozen before testing. Across four benchmarks and two 8B judge backbones, BAER achieves the highest test accuracy among the compared methods in all eight conditions, with full prediction coverage and gains of 0.87--7.32 points over the strongest external baseline. The results show that adapting how evidence is gathered is more reliable than fixing one judging protocol everywhere.

cs.AI↗

arXiv2026

Discrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs

Large Audio Language Models (LALMs) utilize either continuous features or discrete tokens, yet the optimal representation paradigm for general audio understanding remains debated. Existing benchmarks often focus on narrow domains or evaluate encoders outside LALM contexts. To address these gaps, we systematically evaluate continuous and discrete representations across speech, sound and music. Utilizing our UniARC framework with dual evaluation strategies across model scales from SmolLM2-135M to Llama-3-8B, we analyze the dynamic relationships of data volume, model capacity, and computational efficiency. Our results reveal the pivotal role of semantic constraints in tokenization for audio understanding and demonstrate that scaling backbones fail to compensate for information loss in audio representation, especially in data-limited tasks. These findings offer practical guidance for balancing semantic density, fidelity, and efficiency in future LALMs.

cs.SD↗

arXiv2026

LoSATok: Low-Dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation

Audio tokenizers are fundamental to unifying audio understanding and generation. Understanding requires high-level semantics, while generation demands semantic and acoustic details. Existing unified tokenizers jointly encode both in high-dimensional continuous latents, which increases the modeling burden of Diffusion Transformers (DiTs) for generation. We propose LoSATok, a low-dimensional audio tokenizer for cross-domain audio understanding and generation. Motivated by the observation that 1280-dimensional semantic encoder features are compressible, we introduce a Semantic Bottleneck that compresses them into 128 dimensions, regularized by the proposed time-relation loss for temporal feature consistency. We further design a dual-level semantic supervision method that leverages both high- and low-dimensional semantic signals, enabling the tokenizer to jointly capture semantics and acoustic details within a compact latent space. Experiments on speech, music, and general audio show that SemBo preserves strong low-dimensional semantic capacity and LoSATok retains competitive understanding performance compared with several semantic representations, while consistently improving DiT modeling performance on speech, music, and audio generation. These results demonstrate that LoSATok's low-dimensional representations can effectively support audio understanding and generation. Our code is provided at https://github.com/wxzyd123/LoSATok.

eess.AS↗