Search arXiv⌕ Search

arXiv subjects

Bowen Zhang

Publications and source records attributed to Bowen Zhang.

At least 19 recordsLinked to original sources
arXiv2026

Cross-Lingual F5-TTS 2: A Simplified Framework for Language-Agnostic Voice Cloning

Zero-shot text-to-speech (TTS) can clone a speaker's voice from a short audio prompt, yet most TTS systems still require the audio prompt transcript during inference. This dependency prevents cross-lingual voice cloning when the audio prompt transcript is unavailable, particularly for unseen languages. Cross-Lingual F5-TTS removes this dependency and enables transcript-free cross-lingual voice cloning, but it prepares its training data with forced alignment. Forced alignment is sensitive to boundary errors, and its cost grows as more languages are covered. Its speaking rate predictor is also unreliable at estimating duration when the audio prompt begins or ends with silence. In this paper, we present Cross-Lingual F5-TTS 2, a simplified framework for transcript-free cross-lingual voice cloning without forced alignment. Instead of using forced alignment to segment real utterances, we build same-speaker prompt and target pairs using a pretrained F5-TTS model and fine-tune the same model on these constructed pairs. This simplifies data preparation and preserves the acoustic modeling capability of the pretrained model, enabling adaptation with only a short fine-tuning stage. We further make the syllable-level speaking rate predictor robust to leading and trailing silence through silence-aware augmentation. Experiments show that Cross-Lingual F5-TTS 2 reaches higher speaker similarity than F5-TTS and Cross-Lingual F5-TTS while maintaining intelligibility. All related resources are publicly available.

cs.SD↗
arXiv2026

AI-based Interference Mitigation for Power-domain Spectrum Sharing among LEO Satellites

Low-earth orbits (LEO) satellites have recently gained wide attention for their potential to provide high-data-rate services in desert, sea, and rural areas. Currently such systems operate in the Ku band on the down-link. However, inter-operator LEO satellites produce frequent In-Line-Events (ILE) creating co-channel interference between their waveforms. This situation will be exacerbated with the launch of more constellations being launched. To address this challenge, we propose a novel interference mitigation system based on power control. Specifically, satellites from one operator will adjust its transmit power to create a sufficient received-power gap for co-frequency beams, enabling successive interference cancellation (SIC) or AI-assisted algorithms on the user-side for interference mitigation, where AI requires a smaller power gap. We use the waveforms from Starlink and EutelsatOneweb to evaluate the designed system. Results show the designed system can significantly mitigate interference and increase the overall spectrum efficiency.

eess.SP↗
arXiv2026

Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting

Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes management. Although time-series foundation models have shown strong general forecasting ability, their effectiveness for CGM prediction and the added value of multimodal dietary context remain unclear. We conduct a comprehensive empirical study using eight public CGM datasets spanning Type 1 diabetes, Type 2 diabetes, and non-diabetes populations. Under a unified protocol across multiple context lengths and prediction horizons, zero-shot foundation models did not consistently outperform strong task-specific baselines such as Elastic Net and PatchTST. In contrast, lightweight fine-tuning substantially improved forecasting performance. For example, fine-tuned Chronos-Bolt reduced RMSE by 6.5%-18.4% in the T1D cohort and by 8.6%-18.2% in the non-diabetes/T2D cohort, with comparable improvements in both in-distribution and out-of-distribution test settings. We further evaluate multimodal dietary context using CGMacros, which provides temporally aligned CGM signals, food images, and macronutrient records. A residual-based fusion framework reduced overall RMSE by approximately 3% and postprandial RMSE by approximately 15% relative to the CGM-only baseline. Moreover, Chronos-based CGM representations were more strongly correlated with observed postprandial glucose increments than representations from LSTM and CatBoost, even after those models incorporated additional dietary modalities, suggesting that pretrained temporal representations better preserve meal-induced excursion patterns. These findings show that foundation models require CGM-specific adaptation for reliable forecasting and that dietary context provides clinically meaningful signals beyond CGM alone, especially during postprandial periods.

stat.ML↗
arXiv2026

SafeLink-Agent: Agentic Maintenance for Adaptive Bitrate Controllers over Dynamic Starlink Networks

Low Earth orbit (LEO) satellite broadband, represented by Starlink, is making high-resolution video streaming feasible beyond fixed terrestrial coverage. However, Starlink access links change across time and regions, exposing adaptive bitrate (ABR) streaming to shifting throughput tails, latency, volatility, and handover conditions. Existing ABR controllers are usually designed, tuned, or trained for specific network conditions, making it difficult to handle newly exposed hard Starlink profiles. This paper proposes SafeLink-Agent, an agentic maintenance framework for ABR controllers over dynamic Starlink networks. SafeLink-Agent summarizes exposed failures and uses a large language model (LLM)-based agentic patch proposer to generate candidate patches, while replay verification determines whether each patch can be safely committed. The framework supports both rule-based controllers and learned controllers under the same maintenance workflow. Experiments on real Starlink networks show that SafeLink-Agent reduces the severe-session ratio of RobustMPC from 2.60% to 0.40% and reduces cumulative severe sessions from 45 to 7 in rolling maintenance. For learned controllers, verified adaptive auditing lowers the average severe-session ratio from 39.01% to 9.79%. These results demonstrate that agentic maintenance can improve ABR robustness under dynamic Starlink access conditions.

eess.SY↗
arXiv2026

A Circuit, Not The Circuit: Non-Unique Causal Localisation of the Mamba-2 State Sink

Mechanistic interpretability routinely reads a probe and labels its top-activating units as the circuit executing the computation. We test the move in Mamba, on the state sink: the selective state-space analogue of the Transformer attention sink, where the Delta-gate fires disproportionately on boundary tokens such as BOS and newline. At Mamba-1 channel granularity the probe's units carry the causal effect. At Mamba-2 head granularity the label-to-locus link breaks in three ways. The causal set is not unique: a near-disjoint set of top-activation heads, sharing almost none of the specialists, matches or exceeds their ablation effect. Representation does not track function: dual heads, a quarter to over a third of all heads, respond alike to BOS and newline yet do not reproduce the specialists' causal profile. And the effect dissociates by intervention surface: perturbing the input-dependent Delta the probe reads moves the loss by at most 0.16 nats, while suppressing the same heads' output moves it by 1.5 to 7.3 nats. The heads still matter behaviourally, dropping needle-retrieval success on a RULER-style probe from 30/30 to 0/30 at 1024 context on both flagship checkpoints. A representational signature in a selective state-space model thus marks a behaviourally important head set without pinning down the circuit: a single probe recovers a circuit, not the circuit.

cs.CL↗
arXiv2026

Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models

Reliable evaluation of large language models should separate supported answering from unsupported guessing without conflating either with data contamination, prompt idiosyncrasy, or generic refusal behavior. We present a contamination-aware, multi-zone benchmark for measuring the transition from answerable knowledge to abstention-expected unknowns under frozen build-time labels. The benchmark contains 1,200 items across five domains, explicit abstention expectations, contamination-risk metadata, and dual parsing with an official strict parser plus a normalized robustness parser. We evaluate FLAN-T5, Qwen2.5-Instruct, and Llama-3-Instruct models under locked answer-or-abstain prompts, answer-only controls, and prompt-template variants. The benchmark is not solved by generic non-answer behavior: FLAN baselines remain weak on productive abstention, while stronger instruction-tuned models expose a selective but incomplete transition from answering to abstaining. Qwen2.5-3B-Instruct achieves the best overall reliability, but answer-expected zones remain difficult, calibration remains poor, and benign-item refusal persists. Prompt and parser robustness analyses preserve the main ranking and qualitative conclusions. The benchmark therefore provides a reproducible protocol for auditing answerability, abstention, refusal, and contamination as distinct but interacting dimensions of LLM reliability.The dataset is publicly available at https://github.com/renweimeng/Know2Guess-A-Contamination-Aware-Multi-Zone-Benchmark.

cs.CL↗
arXiv2026

Are Hot Jupiters Tidally Disrupted During Stellar Main Sequence?

Once hot Jupiters (HJs) reach their very close orbits, they are expected to experience orbital decay due to tidal interactions with their host star. However, the strength of tidal dissipation is highly uncertain, and it remains an open question whether HJs are tidally disrupted during the stellar main sequence. A previous study found that HJ hosts have a smaller Galactic total velocity dispersion than their field star counterparts, which they interpreted as evidence of tidal disruption. We revisit this study and find that, after using the more reliable vertical velocity dispersion ($σ_W$) as the age indicator and accounting for the heterogeneity and anisotropy of their HJ sample, the kinematic age difference between their HJ hosts and matched field stars is significantly reduced. As an independent check, we collect HJs newly discovered by TESS and find that their $σ_W$ is statistically similar to that of matched field stars. We also find no statistically significant $σ_W$ difference between the field stars and the theoretically vulnerable ultra-hot Jupiters with $P<2$ d. Our results suggest that, after accounting for systematics in the age--velocity dispersion relation, there is no statistically strong evidence from the stellar kinematics that a large fraction of hot Jupiters around Sun-like stars are tidally destroyed during the stellar main sequence.

astro-ph.EP↗
arXiv2026

G0.5: One Autoregressive Stream for Robot Reasoning and Action

The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert. This makes the VLM a context encoder rather than a decision-maker. We introduce G0.5, a pretrained autoregressive VLA in which a single transformer decoder emits reasoning and action tokens under a single objective. Three components make this tractable at foundation-model scale: a learnable cross-embodiment action tokenizer that maps heterogeneous robot actions into a shared vocabulary; a native chain-of-thought stream interleaving task decomposition, object grounding, and action hints with action tokens; and a visual memory module that injects multi-second history through the vision encoder. Because reasoning and action share a single set of weights, the pretrained VLM's capabilities carry over to physical behavior: the model follows instructions closely, and prompts directly steer action granularity, task horizon, and out-of-distribution scene handling without further training. Pretrained on a large collection of robot datasets together with VQA samples, G0.5 surpasses state-of-the-art models across 7 independent regimes: real-world fine-tuning on R1lite and R1pro robots (76.7\% vs.\ 53.3\% for $π_{0.5}$ and 24.4\% for GR00T-N1.7), the 2025 BEHAVIOR Challenge on 50 long-horizon household mobile manipulation tasks using a generalist policy (31.4\% vs.\ 26.3\% for $π_{0.5}$ and 26.1\% for the challenge winner), DROID post-training followed by zero-shot transfer to an unseen environment and objects (82.5\%), a language-following Pick-and-Place benchmark, LIBERO (98.9\%), RoboTwin 2.0 (93.3\%), and SimplerEnv-Bridge (87.3\%).

cs.RO↗
arXiv2026

LoopVSR: A Loop Engineering Framework for Automated Repair of Visual Speech Recognition Inference Pipelines

Visual speech recognition (VSR) recovers speech from lip movements when audio is noisy or unavailable. Its multi-stage inference pipeline spans video decoding, mouth-region extraction, preprocessing, model invocation, and decoding, where upstream failures can mask downstream faults. Pipeline maintenance therefore still relies largely on predefined checks and manual debugging. We propose LoopVSR, a Loop Engineering framework that enables a code agent to automatically diagnose and repair VSR inference pipelines using end-to-end execution evidence. It couples constrained repository-level diagnosis and patching with an external controller that audits changes, runs real inference, and accepts or rolls back patches using failures and character error rate (CER). The resulting feedback loop returns newly observed exceptions, tensor statistics, and recognition errors to the agent, progressively exposing faults masked by upstream failures. On the CMLR VSR system, LoopVSR repairs all 11 main faults with 100% mean recovery, whereas the Static guard repairs 2 of 11 with 18.13% mean recovery. It also resolves three cascading tasks in seven accepted iterations and preserves recovery on an independent 200-video hidden set. These results demonstrate that LoopVSR enables measurable, end-to-end automated repair of VSR inference pipelines.

eess.IV↗
arXiv2026

Beyond Global Latents: Chunk-Based Sparse Grid VAE for Scalable 3D Modeling

Sparse voxel grids preserve the spatial structure needed for detailed 3D reconstruction, but their memory still grows rapidly with resolution as active surface cells increase. We introduce ChunkVAE, a sparse grid variational autoencoder organized around local chunks rather than a global latent volume. Local learned operators permit independently chosen encoder and decoder partitions and allow inference chunk sizes to differ from training. Two complementary data operators make this flexibility practical: Balanced Binary Object Partitioning distributes active cells while limiting replicated overlap, while S-Curve weighted stitching attenuates unreliable boundary features when assembling a global latent or reconstruction. Across three object benchmarks, ChunkVAE is competitive with or better than strong baselines from $512^3$ to $1536^3$; smaller chunks lower peak allocated memory and shorten per-chunk compute, enabling faster parallel inference. Stable stitched latents and improved image to 3D metrics indicate that local compression can scale geometry while retaining the global interface required downstream.

cs.CV↗
arXiv2026

Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents

ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which reasoning or action step to take next, and when to stop, often producing shallow, redundant, or poorly targeted trajectories. Prior work has explored rubrics as external quality signals, but existing uses are mostly evaluative rather than action-guiding: rubrics typically serve as training-time rewards or post-hoc evaluators of completed outputs, and in deep-research settings they are often coarse-grained and report-level rather than step-level. We introduce Co-ReAct, a rubric-guided action-selection framework that uses rubrics as step-level guidance during inference. At each decision step, Co-ReAct injects a rubric into the agent's context to guide the next Reason-or-Act decision, specifying what the agent should target in evidence seeking, search, reasoning, or self-evaluation. To make this guidance reliable, we train a dedicated rubric generator with GRPO. Unlike prior pairwise or binary preference formulations, our objective optimizes a list-wise Spearman rank-correlation reward against multi-judge expert consensus rankings, encouraging rubrics that are discriminative rather than merely plausible. On DeepResearchBench and SQA-CS-V2, Co-ReAct consistently improves over ReAct and representative test-time compute baselines across search agents built on both 8B/14B open-source and frontier closed-source base models. The trained rubric generator can also serve as a drop-in component that improves these baselines without changing their underlying decision mechanisms. Our code is publicly available at https://github.com/ZBWpro/Co-ReAct.

cs.AI↗
arXiv2026

OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations

Although large language model (LLM) conversational systems process millions of multi-turn dialogues daily, they remain fundamentally reactive: they respond only after the user types a query. A key step toward proactive interaction is next-query prediction, which anticipates the user's subsequent query based solely on the preceding dialogue. Progress on this task is hindered by the lack of dedicated benchmarks and a fundamental efficiency--quality trade-off: naively concatenating full dialogue history incurs linearly growing token consumption, while truncating to the latest turn discards crucial cross-turn context. Our key insight is that accurate prediction does not require re-reading raw history; it suffices to track the user's evolving intent trajectory across topics, unresolved needs, and interest shifts. We propose OnePred, which maintains a recursively updated memory as its sole cross-turn context, bounding the per-turn cost independently of conversation length. We train the model via a two-stage reinforcement learning pipeline that first teaches what to predict, then what to compress, shaping the memory into a prediction-oriented intent chain. To establish a rigorous testbed, we introduce NQP-Bench, spanning three diverse subsets. Experiments demonstrate that OnePred reduces per-turn token consumption by up to 22$\times$ compared to full-history inputs while consistently exceeding all baselines in prediction quality, with larger gains on longer conversations. Our code is publicly available at https://github.com/ZBWpro/OnePred.

cs.CL↗
arXiv2026

AnyBand: Unified Multi-Bandwidth Speech Extension via Frequency-Aware In-Context Spectral Infilling

Bandwidth extension (BWE) aims to recover missing high-frequency content from band-limited speech. Existing methods often formulate BWE as a fixed or predefined bandwidth conversion problem, potentially requiring cutoff-specific models or retraining when the input bandwidth changes. This assumption limits their applicability to practical scenarios where speech may arrive with diverse cutoff frequencies. We propose AnyBand, a unified BWE framework that recasts bandwidth extension as in-context spectral infilling. Motivated by prompt-based zero-shot speech generation, AnyBand conditions high-frequency generation on the observed low-frequency spectrum, using the available band as a frequency-domain prompt that conveys content, speaker, prosodic, and spectral-envelope cues. This formulation enables a single model to perform cutoff-conditioned generation over a continuous range of input bandwidths. AnyBand is trained with missing-band conditional flow matching and an Easy-to-Balanced cutoff curriculum over continuously sampled cutoff frequencies. To better exploit the spectral prompt, we introduce a frequency-aware Diffusion Transformer that models cross-frequency interactions and long-range temporal dependencies, followed by a physically motivated multi-view adversarial refinement stage to enhance spectral realism, envelope coherence, and harmonic consistency. Experiments on multiple datasets and bandwidth settings show that AnyBand consistently improves spectral reconstruction over existing baselines while achieving competitive perceptual quality across both standard and irregular input cutoffs. Audio samples are available.

cs.SD↗
arXiv2026

Intraday Gas Fee Heterogeneity on Ethereum: Evidence from Operational Firms

Ethereum's EIP-1559 fee mechanism was designed under the assumption of homogeneous, myopic agents responding to a single congestion signal. We examine how this assumption interacts with the heterogeneous demand structure of real-world Ethereum users. Analyzing 62,142 confirmed transactions from seven operational firms across seven industries (January--March 2026), we document significant intraday gas-fee variation: fees peak at hour~12 UTC (7\,AM ET, $\hatβ_{12}=\$0.054$ above the U.S.\ evening baseline, $p<0.001$) and are associated with periods of elevated speculative-arbitrage activity. Operational firms exhibit heterogeneous scheduling responses moderated by transaction deferrability and gas intensity. Residual cost floors, i.e. the gap between observed expenditure and the counterfactual under perfect off-peak scheduling, range from 40.7\% to 92.5\% of actual expenditure, and persist even during the lowest-cost hours ($h\in\{20,21,22,23\}$ UTC, 3--6\,PM ET). We introduce an On-Chain Scheduling Matrix that maps firms to four scheduling regimes as a practical framework for managing gas-fee exposure under the current mechanism.

econ.EM↗
arXiv2026

RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models

Recent large language models (LLMs) have shown strong performance on software engineering tasks, yet most existing benchmarks evaluate code reasoning at the function level, where all relevant information is localized. This setting fails to reflect real-world development, which requires reasoning across multiple files and complex dependency structures. We introduce RepoReasoner, a benchmark for evaluating repository-level code reasoning. It assesses two complementary abilities: Output Prediction, which measures fine-grained, stateful execution reasoning across files, and Call Chain Prediction, which evaluates high-level architectural dependency understanding under noisy context. Our benchmark is constructed through a multi-stage pipeline that leverages dynamic tracing of pytest executions to obtain ground-truth call chains, along with LLM-based I/O rewriting to reduce memorization effects. We evaluate seven state-of-the-art LLMs. Even under oracle context, the best-performing model achieves only 69.1% Pass@1 on Output Prediction, indicating that cross-file reasoning remains a major challenge. In Call Chain Prediction, models exhibit high precision but low recall, suggesting limited multi-hop dependency understanding. Furthermore, performance drops on rewritten data reveal partial reliance on memorization, and longer contexts do not consistently improve results due to noise. These findings highlight fundamental limitations in current LLMs' repository-level reasoning and motivate future work on structured architectural understanding and cross-file inference.

cs.SE↗
arXiv2026

StarCodex: Dynamic Coding Harness for Starlink Measurement Analysis and Experiment Automation

Starlink and other low Earth orbit (LEO) satellite broadband systems are producing increasingly diverse measurement data across regions, time periods, and access conditions. These measurements are valuable for throughput prediction, adaptive bitrate (ABR) evaluation, and network experimentation, but converting continuously arriving data into reusable experimental evidence still relies heavily on manually developed analysis code and expert-guided data inspection and failure-case organization. This paper proposes StarCodex, a dynamic coding harness for Starlink measurement analysis and experiment automation. StarCodex detects analysis gaps from the current measurement state, converts them into structured coding tasks, uses Codex to generate or repair executable analysis artifacts, and accepts artifacts through code, data-interface, measurement-semantics, and output validation. Experiments on real Starlink measurements show that StarCodex discovers 49 of 56 uncovered system-risk cases, attains higher average precision than the strongest predefined analysis baseline, and constructs a benchmark with denser and broader system-risk evidence. The generated prediction and replay artifacts further reveal prediction risks and quality-of-experience (QoE)--risk differences among ABR controllers. These results demonstrate the feasibility of using a dynamic coding harness to convert evolving Starlink measurements into validated analysis artifacts for automated experiment workflows.

eess.SY↗
arXiv2026

TikStance: A Multimodal and Hierarchical Dataset for Multi-target Stance Analysis in TikTok Political Conversations

Political discourse has increasingly moved to short-video platforms, yet computational analysis of such content remains constrained by the scarcity of datasets that jointly preserve audiovisual information and hierarchical conversations. Here we present TikStance, a multimodal and context-aware dataset comprising 161 videos and 13,876 comments from TikTok, designed for stance detection in political discussions. The dataset covers three major political figures in the 2024 U.S. election cycle--Donald Trump, Joe Biden, and Kamala Harris--with content collected between September 2023 and January 2025. Each discussion unit links a host video and its metadata to a parent-linked comment tree, enabling stance analysis within both audiovisual and conversational context. Each item was independently labeled by three annotators using a three-class scheme (Favor, Against, None) for video-to-target and comment-to-target stance; items with disagreement were re-annotated, and the final Krippendorff's \(α\) reached 0.743, 0.723, and 0.722 for the Trump, Biden, and Harris subsets, respectively. Descriptive analysis further reveals target-dependent differences in stance distributions and conversational depth, with nested replies accounting for 23.3\% of all comments. By combining multi-target coverage, hierarchical conversations, and reliable multi-level human annotations, TikStance supports research in multimodal stance detection, political communication, computational social science, and context-aware natural language processing.

cs.CL↗