Searcharxiv⌕ Search

arXiv subjects

Haitao Li

Publications and source records attributed to Haitao Li.

At least 19 recordsLinked to original sources

Think Once, Act Fast: Cost-Effective Recursive Self-Improvement for Decision Model Harness

Fast System-1 models enable responsive actions but struggle with complex or unfamiliar tasks. Large language model (LLM)-based System-2 provides strong reasoning capabilities, yet repeated invocation incurs substantial latency and computational costs. To bridge this gap, we propose JevRSI, a System-1/System-2 collaboration framework that transforms LLM reasoning into transferable decision support through recursive harness improvement. A Jev-style System-1 model enables low-latency action selection, while an asynchronous System-2 LLM develops a modular harness. The harness integrates procedures, state memory, and world models to provide decision contexts spanning the past, present, and future. Utility-driven retrieval selects modules based on both contextual relevance and their utility on previous tasks. Environmental feedback guides targeted revisions and enables recursive self-improvement. Experiments across three datasets show that JevRSI consistently improves decision quality, matching or surpassing LLM agents in several settings. It preserves low-latency execution with favorable performance-cost trade-offs. Moreover, System-2 development interventions decrease as the harness evolves, amortizing System-2 costs through continuous improvement. Our project is available at https://github.com/usail-hkust/JevRSI.

cs.AI↗

Pluggable Subband-Decoupled Fusion and Unlabeled Capture Prototype Calibration: Bridging High-SNR Null-Subcarrier Regrowth and Low-SNR Coherent Preambles for Cross-Domain IoT RF Fingerprinting

Zero-overhead physical-layer authentication at edge wireless access points (APs) is vital for securing resource-constrained Internet of Things (IoT) transceivers against credential cloning, yet cross-domain IEEE 802.11a/g radio frequency fingerprint identification (RFFI) faces an acute signal-to-noise ratio (SNR) crossover. Power-amplifier spectral regrowth on unpopulated null subcarriers resists indoor multipath at high SNR but decays quadratically below the thermal noise floor, whereas populated active in-band preambles survive low SNR yet degrade under severe multipath, causing static fusion to lose up to 44.7 percentage points (pp). To our knowledge, we propose the first RFFI framework that dynamically modulates active in-band waveforms and unpopulated null-subcarrier regrowth via a blind physical SNR gate: Pluggable Gated Subband-Decoupled Fusion with Unlabeled Capture-Aware Prototype Calibration (GSDF-CAPC). Avoiding the 20-35 dB subband gradient imbalance of joint training, GSDF pairs any frozen pretrained host backbone with a 46.3K null-subcarrier plug-in encoder (NS-Branch), fusing scale-standardized logits and gate-warped spherical embeddings under a source-calibrated lag-64 thermal-SNR gate with exact low-SNR fallback. Over unlabeled target AP captures, forward-only unbalanced optimal-transport calibration (UOT-CAPC) aligns shifted prototypes under packet-arrival skew and recovers parameter-free balanced Sinkhorn (U-CAPC) at equipartition. Across DataPort-WiFi, WiSig, and ORBIT MobRFFI, zero-retrain GSDF wins all 72/72 paired runs across eight backbones with 0.00 pp low-SNR loss, while edge IB-Host + GSDF (92.6K-93.3K active parameters, 1.82 ms single-core CPU latency) and timing-synchronized GSDF-STO / GSDF-Tri reach 57.50%-65.05% three-benchmark Macro-F1 (89.04%-100.00% over 5-10-packet IoT bursts).

cs.AI↗

Conflict-Aware Multi-Teacher On-Policy Distillation in Aligned Action Spaces for Cross-Game Generalization

Zero-shot cross-game generalization aims to consolidate accessible source-game experts into a single vision-language model (VLM) that controls unseen games from raw pixels without target-game parameter updates. While multi-teacher on-policy distillation (MOPD) mitigates offline exposure bias and single-game reinforcement learning (RL) overfitting, scaling it to autoregressive VLMs faces two bottlenecks. First, token-to-action misalignment from subword length bias distorts discrete action probabilities and uncertainty margins. Second, multi-teacher policy conflict arises as source teachers under incompatible dynamics issue contradictory closed-loop corrections, causing negative transfer. We propose CAMOPD (Conflict-Aware Multi-Teacher On-Policy Distillation), a post-training framework that resolves multi-teacher policy conflict within an aligned semantic action space. CAMOPD first uses complete-action alignment to normalize command completion likelihoods over each game's legal action set, forming a calibrated categorical policy that provides reliable uncertainty margins for selective on-policy retention and visual specialist probes that can be evaluated across source games. To resolve policy conflict without target-game data, conflict-aware multi-teacher consolidation cross-evaluates these specialists across source games to capture both visual identifiability and inter-teacher compatibility, upweighting compatible teachers while suppressing conflicting corrections. On GameWorld's temporal and directional transfer suites with Qwen3.5-4B, CAMOPD achieves 26/30 (86.7%) and 24/30 (80.0%) Task-1 zero-shot success on unseen GeoDash and Doodle Jump, outperforming prompting, weight-merging, and multi-task baselines.

cs.AI↗

VoxMel TTS Technical Report

Continuous autoregressive TTS relies on an acoustic target that enables stable next-latent modeling while preserving fine-grained acoustic details. While existing approaches employ learned compressed representations (e.g., continuous VAE latents) to render prediction tractable, they rely on complex neural encoders that often cap generation fidelity. Conversely, training-free targets like mel-spectrograms eliminate encoder overhead, yet their potential for autoregressive generation remains largely underexplored. In this work, we propose VoxMel, a tokenizer-free framework for autoregressive TTS that makes stable mel modeling tractable through a fixed, exactly invertible two-axis Haar transform. The transform first decomposes each mel spectrogram along frequency into local averages and a frequency residual, then splits the averaged component along time into Coarse-Mel and a temporal residual. A language-model backbone with a flow-matching head autoregressively generates Coarse-Mel. Non-autoregressive residual tiers then predict the temporal residual from Coarse-Mel, followed by the frequency residual conditioned on the reconstructed Frequency-Averaged Mel. Neither residual is fed back into the autoregressive history. Trained on 100K hours of Emilia, the supervised 0.6B model obtains 1.51\% WER and 0.738 speaker similarity (SIM) on test-en, and 1.29\% CER and 0.755 SIM on test-zh. GRPO improves these results to 1.15\% WER / 0.753 SIM and 1.17\% CER / 0.776 SIM, respectively. We also distill the guided flow head into two- and four-step students, requiring 2 or 4 head evaluations per coarse frame. The four-step student retains competitive SIM and nearly matches the supervised model in WER/CER.

eess.AS↗

IntentLens: Grounding Underspecified Multimodal Queries for Recommendation via Tool-Augmented Reasoning

As intelligent personal assistants are increasingly deployed in real-world scenarios, recommendation paradigms are shifting from passive preference matching to inferring user intent from underspecified multimodal inputs. In practical interactions, users typically issue a reference image paired with a vague natural language query, keeping key visual attributes, personalized preferences, and item-side constraints implicit. Existing recommendation methods either leverage historical user interactions augmented with multimodal item features or assume fully articulated textual queries; both paradigms struggle to resolve underspecified multimodal queries for accurate item matching. To address this limitation, we propose IntentLens, a tool-augmented recommendation framework that grounds ambiguous multimodal queries into query-relevant evidence prior to user-item matching. IntentLens follows a ground-then-rank pipeline: a shared multimodal LLM leverages visual tools, user memory modules, and item attribute retrieval tools to (i) infer latent user intent from image-text inputs and (ii) augment each candidate item with fine-grained, query-conditioned evidence. Subsequently, a lightweight ranker scores candidates based on the grounded representations. To facilitate research in this novel setting, we construct two benchmarks with underspecified multimodal queries, namely \textsc{GoogleReview-MMTool} and \textsc{Yelp-MMTool}. Extensive experiments on these benchmarks demonstrate that IntentLens outperforms competitive MLLM and retrieval baselines, and exhibits strong generalization to unseen categories and datasets.

cs.IR↗

From Solver Trajectories to Teaching Trajectories: Cognition-Aligned Reasoning Distillation

Knowledge distillation from large reasoning models (LRMs) often uses raw teacher trajectories as supervision. However, this practice creates a mismatch between the goal of distillation and the nature of teacher trajectories. Advanced LRMs typically improve their reasoning capabilities through reward-driven post-training, such as RLHF. This training optimizes them as strong solvers, rather than as teachers that produce reasoning processes smaller models can easily learn. Since smaller models have different "cognitive capacities" compared to their larger teachers, directly imitating raw teacher trajectories can sometimes be ineffective and often requires a substantial number of high-quality samples. To bridge this mismatch, we propose Cognition-Aligned Reasoning Distillation (CARD), an RL-based framework that transforms solver trajectories into teaching trajectories aligned with the student's cognition. Avoiding expensive resampling, our framework directly transforms existing trajectories. We optimize CARD with two reward signals: (1) a Distribution Alignment Reward that matches the student's predictive distribution, and (2) a Logical Coherence Reward that reduces misleading failed reasoning steps. Comprehensive evaluations across multiple student models and settings demonstrate that CARD outperforms distillation from raw teacher trajectories in in-domain settings while achieving substantial gains in out-of-distribution performance. Code is available at https://github.com/LiteSSLHub/CARD.

cs.AI↗

Physics-Informed Structure Anchoring With Capture-Aware Prototype Calibration for Cross-Environment RF Fingerprinting

Radio frequency fingerprint identification (RFFI) exploits transmitter-specific hardware imperfections as physicallayer identity cues for Internet of Things (IoT) devices, but deep models often degrade across acquisition environments. In multi-antenna reception, antenna topology and frequencyoffset dynamics structure receiver observations, while capturedependent variation distorts target embeddings and misaligns source-trained decision boundaries. This article proposes physicsinformed structure anchoring with capture-aware prototype calibration (PISA-CAPC) to address both representation and decision mismatches. The two stages separate source representation construction from target decision correction. During source training, PISA organizes antenna tokens through a topology-guided graph, conditions propagation on CFO-derived acquisition dynamics, and applies bounded contextual residual suppression to preserve identity evidence. At deployment, unlabeled capture-aware prototype calibration (U-CAPC) estimates capture-local prototypes and recalibrates target decision scores while keeping the representation and source classifier fixed. Thus, calibration uses neither target labels nor target-domain backbone updates. On a measured WiFi benchmark with four receive antennas and ten transmitters, PISA-CAPC achieves a mean target-domain Macro-F1 of 0.9257 under a balanced transductive setting. Component ablations support complementary roles for topology-guided anchoring, CFO-conditioned modulation, reliability-aware token aggregation, contextual suppression, and capture-aware calibration. These results indicate that physically motivated representation learning can be combined with labelfree decision calibration to improve cross-environment RFFI under the evaluated protocol without changing the deployed backbone.

eess.SP↗

GeoPrompt: Geometry-Conditioned Prompt Learning for Underwater Open-Vocabulary Instance Segmentation

Open-vocabulary instance segmentation (OVIS) provides a promising solution for marine perception by recognizing and segmenting categories beyond predefined label spaces. Existing OVIS methods usually rely on vision-language alignment, where visual region features are matched with textual category embeddings to recognize both seen and unseen classes. However, this alignment assumption becomes fragile in underwater environments. Color attenuation, scattering, turbidity, and low contrast distort visual appearance, causing region features to deviate from their corresponding semantic concepts. As a result, the similarity between degraded visual features and textual classifiers becomes unreliable, which particularly weakens the recognition of unseen underwater categories that cannot be corrected by category-specific supervision. To address these issues, we propose GeoPrompt, a geometry-conditioned prompt learning framework for underwater open-vocabulary instance segmentation. Our key insight is that geometric structure is more stable than visual appearance in degraded underwater scenes. Specifically, GeoPrompt introduces a geometry-guided visual adaptation module (GVAM) to extract depth-derived structural priors and inject them into multi-scale visual features. It further develops a geometry-conditioned prompt learning (GCPL) that generates geometry-aware textual classifiers from structural representations. These geometry-aware classifiers are integrated with fixed and image-conditioned textual classifiers to improve open-vocabulary semantic alignment. Experiments on the MARIS-OpenIS benchmark show that GeoPrompt achieves state-of-the-art performance and brings consistent improvements on underwater open-vocabulary instance segmentation.

cs.CV↗

Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models

User feedback offers natural supervision for persistent LLM improvement, but a single message may support multiple behavioral changes with different scopes of generalization. We introduce SLIFT, a selective self-learning framework built on a task-relative view of user feedback. SLIFT decomposes each feedback message into atomic components and interprets each component relative to the original task as Fix, Spec, or Null: requirements for task validity, compatible condition-specific refinements, or content with no reliable positive update direction. To incorporate each change at the appropriate scope, SLIFT trains two complementary LoRA adapters on a shared frozen backbone: a Generalist that consolidates Fix requirements into default behavior through feedback-conditioned self-distillation, and a Specialist that observes only the task and Generalist response to supply residual guidance for applicable, unmet Spec refinements. Null components induce no positive update. Across backbones, SLIFT achieves strong performance on both MemoryBench and WildFB, with targeted analyses further examining its underlying mechanisms. We release our code at https://anonymous.4open.science/r/SLIFT.

cs.AI↗

Overview of the NTCIR-19 Automatic Evaluation of LLMs 2 (AEOLLM-2) Task

In this paper, we provide an overview of the NTCIR-19 Automatic Evaluation of LLMs 2 (AEOLLM-2) task. Building on the success of the NTCIR-18 core task AEOLLM, we proposed AEOLLM-2 for NTCIR-19 to further investigate automatic evaluation methods for Large Language Models (LLMs), particularly in long-form text generation scenarios. In AEOLLM-2, we introduced a new subtask, Deep Research Evaluation, which focuses on the automatic evaluation of long-form deep research reports generated by LLMs. Participants developed evaluation methods to automatically assess the quality of these reports, and the performance of each method was measured by comparing its scores against human-annotated ground-truth labels. This year, we received 91 runs from 10 teams in total. This paper describes the background of the task, the dataset construction, the evaluation measures, the participants' methods, and the final evaluation results.

cs.IR↗

RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments

General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities carry into the physical world. To investigate this, we introduce RobotWorld, a challenging simulation testbed for robot use: turning instructions and observations into physical task execution through robot interfaces. Its 84 tasks span manipulation, mobile manipulation, locomotion, driving, and aerial control, with explicit interaction budgets and executable success checks. By analysing task outcomes alongside execution traces, we identify both the capabilities that transfer and the gaps that prevent reliable completion. Furthermore, we find that current agents can construct sophisticated perception and control workflows, including image segmentation, camera calibration, spatial estimation, and dynamics-based computation. These capabilities, however, do not consistently compose into successful behaviour: agents lose task-relevant object states despite reaching commanded poses, fail to correct ineffective actions, recover too late, or mistake unfinished tasks for completion. This uneven transfer also differs across models: Astra succeeds more often on spatial and constrained-contact goals, whereas Opus 5.5 succeeds more often on continuous-balance and timed-interaction goals. By linking these outcomes to execution behaviour, RobotWorld provides both a rigorous proving ground and an empirical account of the remaining capability gaps, thereby establishing concrete targets for training and designing more reliable physical-world agents.

cs.RO↗

EnGRICH: Enhancing Generative Reward Modeling with Critiques from Humans

Generative reward models (GRMs) are important for LLM optimization. Unlike scalar reward models, GRMs generate natural-language critiques alongside preference judgments, providing finer-grained evaluation signals. Their effectiveness depends heavily on critique reliability. However, existing GRM training typically uses final preference correctness as outcome supervision. Because the preference outcome space is highly constrained, unreliable critiques can still yield correct outcomes and thus be reinforced. Recent work leverages human critiques for process supervision, but such critiques are scarce and are often reduced to scalar rewards, leaving their fine-grained evaluative information underutilized. We argue that evaluative criteria learned from human critiques can be generalized to broader outcome-only preference data. To this end, we propose \textbf{EnGRICH}, a GRM training framework that pairs the GRM with a training-time MetaCritic learned from a small set of human critiques. MetaCritic constructs response-specific rubrics and uses them to evaluate the evidence coverage and correctness of generated critiques. The resulting signals provide both process rewards for fine-grained credit assignment and structured guidance for exploring better critiques. During GRM training, MetaCritic is further optimized to generalize human-grounded evaluative criteria to outcome-only data. At inference, the trained GRM operates independently. Experiments across seven reward-model benchmarks show that EnGRICH consistently improves over competitive baselines, while further analyses validate the effectiveness of its core mechanisms.

cs.AI↗

ECG-Scroll: A Long-Horizon, Streaming Benchmark and Agent Environment for Interpretation of Ambulatory Electrocardiograms

Multimodal large language models (MLLMs) can now interpret a standard ten-second, twelve-lead electrocardiogram (ECG) with clinically grounded, reward-verified reasoning. Real cardiac monitoring is different. Ambulatory (Holter) and telemetry recordings span hours to days and are read as they stream in, and their clinically decisive findings are paroxysmal, brief episodes buried in an otherwise unremarkable trace. Such a recording cannot be held in one context at diagnostic resolution, and its future has not yet happened, so a reader must work online, deciding what to measure now, committing evidence to memory as it passes, and reporting events as they occur. We recast long-duration ECG interpretation as a long-horizon, online (streaming, causal) sequential decision process and introduce ECG-Scroll. As a benchmark, long ambulatory recordings are streamed to an agent chunk by chunk, and it must localize, quantify, and promptly flag paroxysmal events without access to future signal; because the underlying signal is retained, every answer is checkable against objective ground truth, giving rule-based rather than judge-based rewards, and the streaming formulation adds a metric batch evaluation cannot express, the detection latency between an event's onset and the moment the agent records it. As an agent environment, it is a fixed, gym-style interaction layer that exercises three competencies single-glance ECG models never touch: Memory, Tool use through signal-grounded measurement rather than reading pixels, and Planning of what to measure now and when to commit. We release 390 whole-recording instances spanning 2,536 hours of two-lead ambulatory ECG and evaluate a signal-threshold rule agent alongside off-the-shelf LLM agents online, characterizing how they use memory, tools, and planning and where the benchmark's head-room lies.

cs.LG↗

Orthogonal Flatbands-Enabled Robust Fano Resonances through Brillouin-Zone Folding

Fano resonances based on coherent interference between localized Lorentz modes and Fabry-Perot radiation continua have been widely explored for microwave metamaterial sensors, filters, and photonic devices. However, conventional Fano metasurfaces suffer from angular dispersion and polarization-dependent spectral variations, limiting robustness under dynamic illumination. Here, we propose a band-folding-enabled flatband engineering strategy to realize robust Fano resonances in a planar microwave metasurface with a 2x2 enlarged cell of orthogonally arranged H-shaped metallic resonators. The enlarged cell induces Brillouin-zone folding, generating a nearly dispersionless flatband near 15.3 GHz with suppressed momentum dependence and enhanced photonic confinement. This flatband state provides a high-Q localized resonance strongly coupled to the FP radiation continuum, producing a stable asymmetric Fano response. Furthermore, the orthogonal resonator configuration supports two polarization-decoupled dipole modes with comparable excitation efficiency, reducing polarization-induced spectral distortion. Near-field measurements and simulations verify localized flatband features, while far-field experiments demonstrate stable Fano responses under oblique incidence from 0° to 30° with minor resonance variation. A temporal coupled-mode theory model is developed to quantitatively describe Fano spectral evolution under different illumination conditions. This work establishes a flatband-mediated route toward robust microwave Fano metasurfaces and offers a general strategy for stable resonant photonic device design.

physics.optics↗

FOCAL: Fine-Grained Optimal-Transport-Driven Contrastive Alignment of Language and ECGs with Waveform Enhancement

Electrocardiograms (ECGs) are essential non-invasive tools for diagnosing cardiovascular diseases. While recent multimodal ECG-Report contrastive learning methods have shown promise for zero-shot ECG interpretation, they predominantly rely on global representations, failing to capture the fine-grained relationship between localized waveform patches and specific pathological tags. This limitation is further exacerbated by the fact that nearly 55% of standard clinical reports (e.g., in MIMIC-ECG) lack explicit waveform descriptions. In this paper, we propose FOCAL, a novel framework that achieves precise, fine-grained alignment between localized ECG segments and individual report tags via Optimal Transport. Furthermore, because fine-grained alignment at the tag level exacerbates the false negative problem among reports sharing common diagnoses, we introduce a semantic similarity matrix to guide the contrastive objective and correct misalignments. To address the scarcity of detailed waveform text, we introduce a coarse-to-fine enrichment pipeline that leverages Large Language Models (LLMs) to recover missing semantics, utilizing a coarse model verification step to rigorously filter out hallucinations. Extensive experiments across six datasets demonstrate that FOCAL establishes new state-of-the-art performance in zero-shot prediction and linear probing.

eess.SP↗

AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following

The rapid advancement of instruction-guided audio generation has highlighted the critical need for robust alignment evaluation. Current automated evaluation methods heavily rely on holistic scoring from general-purpose large language models, which struggle to decouple complex instructions, lack interpretability, and fail to capture fine-grained attribute mismatches. To address this, we introduce a novel dynamic rubric-based evaluation paradigm that adaptively decomposes complex audio captions into a variable number of independent, verifiable binary rubric items. To rigorously benchmark this capability, we propose the AnyAudio-Judge Bench, a comprehensive, bilingual benchmark comprising 7,920 meticulously curated samples across four diverse audio domains (speech, sound, music, and mixed), featuring deliberately constructed hard negatives. Furthermore, we construct a large-scale corpus of 105K samples with explicit Chain-of-Thought (CoT) rationales to train our dedicated evaluator, the AnyAudio-Judge model. By employing a training pipeline that combines Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO), our model successfully aligns its reasoning paths with the rubric-based scoring mechanism. Extensive experiments demonstrate that AnyAudio-Judge not only significantly enhances zero-shot alignment detection compared to state-of-the-art baselines, but also provides precise and interpretable reward signals that substantially improve instruction alignment in downstream reinforcement learning for audio generation.

eess.AS↗

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↗

AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing

We introduce AuK, an open-source foundational model that unifies speech generation and editing through a common interface of natural-language instructions and audio context. To support this broad capability set, we construct approximately 3.03 billion instruction--audio instances and 1.95 million hours of effective supervision across five task families: speech generation, content editing, enhancement and separation, paralinguistic editing, and acoustic editing. AuK combines a multimodal large language model for semantic conditioning, an VAE jointly trained on speech, general audio, and music for acoustic conditioning, and a hybrid rectified-flow Transformer that performs dual-stream MMDiT blocks followed by unified single-stream DiT blocks for generation. Training begins with generation-only warm-up and proceeds to joint generation--editing pre-training. We then apply complementary post-training strategies: human-feedback preference optimization for open-ended editing and reward-based reinforcement learning for speech generation. To reduce inference cost, we further distill the model with consistency initialization and task-routed Decoupled DMD. The resulting AuK-Flash performs 4-step inference without classifier-free guidance and achieves a 4.5 wall-clock speedup over the full model under matched conditions. Experiments demonstrate leading performance on zero-shot and instruction-controlled speech generation and general instruction-guided editing, while remaining competitive on signal-level restoration tasks. We release both the source code and model weights to support reproducibility and further research.

cs.SD↗