arXiv subjects

Haitao Li

Publications and source records attributed to Haitao Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model

Reinforcement learning for flow-matching text-to-speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE and track per-step likelihood ratios, introducing stochastic perturbations and substantial overhead. We propose GROW, a group-relative advantage-weighted on-policy RL method that acts directly on the standard flow-matching objective. For each prompt, GROW samples a group of on-policy utterances, separately standardizes intelligibility and speaker-similarity rewards within the group, and combines them to reweight flow-matching regression. A Wasserstein-2 velocity penalty anchors the updated model to a frozen pretrained reference. A group-mean reward baseline is introduced to convert reward weighting into advantage weighting. For strong pretrained TTS models with concentrated rewards, positive exponential weighting is dominated by reward-agnostic self-imitation, whereas a zero-mean signed advantage preserves effective within-group credit assignment. Instantiated on DiTAR and evaluated on LibriSpeech and Seed-TTS EN/ZH, GROW reduces average WER from 2.016 to 1.558 and raises speaker similarity from 0.676 to 0.715 while keeping UTMOS. With 10-NFE training rollouts and 32-NFE evaluation, GROW retains comparable performance while training 2.9x faster than 32-NFE DiTAR-GRPO. We will open-source complete GROW codes, faithful DiTAR reproduction, and all model checkpoints.

eess.AS↗

arXiv2026

LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception

Long-horizon tool agents are bottlenecked by how their context grows toward the limits of the context window. Recent systems make context management agent- or system-controlled, but they either learn compression policies that discard evidence or manage context in a layer the agent never sees. We argue that both miss a more basic gap: frontier language models are proprioceptively blind to their own context. From the prompt alone they cannot reliably infer block size, recency, or the remaining budget, all of which are needed for keep-or-archive decisions. We introduce VISTA (Visible Internal State for Tool Agents), a training-free, model-agnostic layer that represents working memory as typed addressable blocks, surfaces a runtime dashboard of token usage, recency, archive status, and remaining budget, and archives blocks as recoverable full-fidelity payloads. On LOCA-Bench, BrowseComp-Plus, and GAIA, the same untrained interface transfers across 1M-, 100K-, and 10K-scale trajectories. On LOCA-Bench it lifts Gemini-3-Flash from 22.7 to 50.7%, reaches 58.0% on BrowseComp-Plus, and remains competitive on GAIA. Gains grow with context pressure and transfer across backbones, while ablations confirm that the dashboard matters beyond archive and recovery tools.

cs.CL↗

arXiv2026

Dirac-vortex modes beyond the continuum limit

Dirac-vortex modes (DVMs) in Kekule-modulated lattices provide a topological route to wave confinement and are commonly described by the continuum Jackiw-Rossi model, in which the initial phase acts as a redundant gauge degree of freedom and does not affect observables of the mode. Here we show that this picture breaks down in discrete lattices when the complex mass texture that induces the DVMs no longer satisfies the slowly varying envelope approximation. In this regime, lattice discreteness turns the initial phase into a physically observable parameter that shifts the DVM center. By further introducing a sublattice-antisymmetric perturbation, we convert this phase-dependent center motion into a continuous spectral response of the DVM, enabling its frequency tuning across nearly the entire topological bandgap. Our simulation and experimental results agree well with a revised continuum model accounting for the mode-center motion. Within this perturbative framework, the model shows that the frequency shift exhibits a sinusoidal-like dependence on the initial phase. These findings reveal initial phase-sensitivity of the DVMs realized in lattices, an important and basic feature absent from the ideal continuum Jackiw-Rossi model, and demonstrate initial phase engineering as a potential pathway towards reconfigurable photonic devices.

physics.optics↗

arXiv2026

Hybrid Rigid-Soft Robotic Gripper with Shape Adaptation, Uniform Force Distribution, and Self-Locking Capabilities

Conventional robotic grippers face a significant challenge in agricultural automation: the trade-off between compliant, adaptive grasping, pressure balancing among all joints, and high load capacity, often at the cost of high energy consumption. This paper presents a novel hybrid rigid-soft gripper that integrated low-cost, membrane-based pneumatic actuators with 3D-printed dual ratchet-pawl mechanisms to simultaneously achieve shape adaptation, uniform force distribution, and energy-free self-locking. The dual-ratchet structure assembled in an offset configuration significantly increased the angular resolution of the joint locking mechanism. Key experimental results demonstrated the gripper's superior performance: a remarkable maximum load capacity of 4200 g, far exceeding that of conventional soft grippers (45-210 g); more uniform force distribution across object sizes (1.75-35.29% difference ratio) compared to a rigid gripper (56.77-66.44%), with peak contact forces remaining below surface damage thresholds; and a 50.05% reduction in total energy consumption to 42.6 J per grasp cycle, achieved by eliminating the need for continuous pneumatic pressure through the self-locking mechanism, compared to 85.28 J for a conventional soft gripper. The combination of additive manufacturing for ratchets and commercially available materials for pneumatic chambers ensured a low-cost and easily fabricated design. These findings validated that the proposed gripper successfully bridged the gap between soft compliance and rigid reliability, offering a robust and efficient solution for scalable agricultural harvesting and manipulation tasks.

cs.RO↗

arXiv2026

Cross-Receiver Open-Set Radio Frequency Fingerprinting via Structure-First Adaptation

Radio frequency fingerprint identification (RFFI) provides a critical physical-layer security mechanism for dynamic Internet of Things (IoT) and ad hoc networks. However, the decentralized and open nature of these networks imposes two strict deployment criteria: the credential must transfer reliably across physically dispersed, heterogeneous receivers, and it must decisively reject unregistered rogue traffic. Cross-receiver hardware shifts depress the confidence of registered devices and may also place unseen rogue transmitters in high-confidence known regions under naive domain adaptation, increasing false acceptance. To address these risks, we propose CRODA-ST, a joint optimization framework that couples Discriminative Structure Anchoring (DSA) with Rejection Oriented Alignment (ROA). Within this coupled objective, DSA establishes a stable target-known semantic foundation for shifted registered devices, while ROA regularizes the open-set decision boundaries governing rejection of unseen rogue transmitters. In the canonical WiSig setting, CRODA-ST achieves an open-set classification rate (OSCR) of 0.9580 and a target-domain false positive rate of 0.0469 at a 90% true positive rate (FPR90). A controllable LoRa simulation provides a complementary diagnostic under synthesized hardware distortions. At the distinct source-calibrated deployment operating point with rho = 0.80, CRODA-ST yields a target-unknown false acceptance rate (FAR) of 0.0075 in the evaluated setting.

eess.SP↗

arXiv2026

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↗

arXiv2026

Spatiotemporal Optical Vortices From All-Dielectric Bilayer Metagratings

Spatiotemporal optical vortices (STOVs) carry transverse orbital angular momentum within the space-time domain, rendering them powerful tools for constructing high-dimensional and quantum optical fields. However, most existing approaches rely on highly lossy metallic structures or complex pulse-shaping systems. Here, we propose an all-dielectric route to STOV generation based on symmetry-protected bound states in the continuum (BICs) in a bilayer metagrating and provide proof-of-concept validation of its key momentum-frequency signatures. By simply introducing a lateral shift between the upper and lower layers of the vertical slots on the dielectric metagrating, the Γ-point BIC transforms into a quasi-BIC (qBIC) with momentum-dependent directional radiation and asymmetric coupling. This qBIC further leads to an isolated zero-transmission dip associated with a clear phase singularity and branch cut in the momentum-frequency response, enabling stable STOV generation under excitation by a spatiotemporal Gaussian pulse. The multipole analysis of the qBIC reveals the key role of the Kerker-type interference between its electric and magnetic dipoles and associated asymmetric coupling in the STOV generation. Experimentally, free-space transmission measurements reveal a transmission zero and a branch cut that agree excellently with theoretical analysis. Therefore, our work provides an experimentally validated, scalable route for manipulating spatiotemporal optical fields on low-loss all-dielectric metasurfaces via only gliding offsets, with potential applications in directional coupling of quantum light sources and spatiotemporal shaping of single-photon wave packets.

physics.optics↗

arXiv2026

OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, existing RMs struggle on knowledge-intensive and long-form tasks, where evaluating correctness requires grounding beyond the model's internal knowledge. This limitation hinders them from reliably discriminating subtle quality differences, especially when external evidence is necessary. To address this, we introduce OpenRM, a tool-augmented long-form reward model that systematically judges open-ended responses by invoking external tools to gather relevant evidence. We train OpenRM with Group Relative Policy Optimization (GRPO) on over 27K synthesized pairwise examples generated through a controllable data synthesis framework. The training objective jointly supervises intermediate tool usage and final outcome accuracy, incentivizing our reward model to learn effective evidence-based judgment strategies. Extensive experiments on three newly-collected datasets and two widely-used benchmarks demonstrate that OpenRM substantially outperforms existing reward modeling approaches. As a further step, we integrate OpenRM into both inference-time response selection and training-time data selection. This yields consistent gains in downstream LLM alignment tasks, highlighting the potential of tool-augmented reward models for scaling reliable long-form evaluation.

cs.CL↗

arXiv2026

CLoE: Expert Consistency Learning for Robust Missing Modality Segmentation

Multimodal medical image segmentation often faces missing modalities at inference, which induces disagreement among modality experts and makes fusion unstable, particularly on small foreground structures. We propose Consistency Learning of Experts (CLoE), a consistency-driven framework for missing-modality segmentation that preserves strong performance when all modalities are available. CLoE formulates robustness as decision-level expert consistency control and introduces a dual-branch Expert Consistency Learning objective. Modality Expert Consistency enforces global agreement among expert predictions to reduce case-wise drift under partial inputs, while Region Expert Consistency emphasizes agreement on clinically critical foreground regions to avoid background-dominated regularization. We further map consistency scores to modality reliability weights using a lightweight gating network, enabling reliability-aware feature recalibration before fusion. Extensive experiments on BraTS 2020 and MSD Prostate demonstrate that CLoE outperforms state-of-the-art methods in incomplete multimodal segmentation, while exhibiting strong cross-dataset generalization and improving robustness on clinically critical structures.

cs.CV↗

arXiv2026

Civil Court Simulation with Large Language Models

Court simulation bridges legal education and judicial practice, yet human-based simulations are costly and difficult to scale. Large language models (LLMs) offer a scalable alternative, but existing court-simulation research mainly focuses on criminal cases. Civil litigation is more common in practice and harder to simulate because its claims, liability, and remedies are more flexible. We present a multi-agent court simulation framework for Chinese civil cases. The framework organizes role-based interaction through a five-stage civil trial procedure and integrates memory module and statute retrieval to support long-process adjudication. Experiments show that the framework produces reliable civil judgments, with clear strengths in liability allocation and multi-item adjudication. Further experiments show that memory quality substantially affects downstream simulation quality. Through a five-layer factor framework, we analyze how legal grounding, information conditions, judicial capability and role orientation, organizational pressure, and social context affect the framework's reliability and behavior. These results support the effectiveness of the proposed framework for civil court simulation. The dataset and code are available at: https://github.com/foggpoy/Civil-Court.

cs.CL↗

arXiv2026

APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL

Text-to-SQL systems powered by Large Language Models have excelled on academic benchmarks but struggle in complex enterprise environments. The primary limitation lies in their reliance on static schema representations, which fails to resolve semantic ambiguity and scale effectively to large, complex databases. To address this, we propose APEX-SQL, an Agentic Text-to-SQL Framework that shifts the paradigm from passive translation to agentic exploration. Our framework employs a hypothesis-verification loop to ground model reasoning in real data. In the schema linking phase, we use logical planning to verbalize hypotheses, dual-pathway pruning to reduce the search space, and parallel data profiling to validate column roles against real data, followed by global synthesis to ensure topological connectivity. For SQL generation, we introduce a deterministic mechanism to retrieve exploration directives, allowing the agent to effectively explore data distributions, refine hypotheses, and generate semantically accurate SQLs. Experiments on BIRD (70.65% execution accuracy) and Spider 2.0-Snow (51.01% execution accuracy) demonstrate that APEX-SQL outperforms competitive baselines with reduced token consumption. Further analysis reveals that agentic exploration acts as a performance multiplier, unlocking the latent reasoning potential of foundation models in enterprise settings. Ablation studies confirm the critical contributions of each component in ensuring robust and accurate data analysis. Our code is released at https://github.com/Tencent/APEX-SQL-Project.

cs.DB↗

arXiv2026

MulFeRL: Enhancing Reinforcement Learning with Verbal Feedback in a Multi-turn Loop

Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning across domains, but outcome-only scalar rewards are often sparse and uninformative. This limitation is especially severe for failed samples, where scalar rewards indicate only that a solution is incorrect without explaining why the reasoning breaks down. In this paper, we leverage richer verbal feedback to guide RLVR on failed samples and convert feedback-induced progress into trainable learning signals. We propose MulFeRL (Multi-turn Feedback-guided Reinforcement Learning), a multi-turn, event-triggered RLVR framework that combines progress induction for feedback-guided regeneration of failed samples, progress credit assignment for learning from verifier-confirmed progress, and structured feedback injection for integrating feedback into the model's reasoning process. Trained on sampled OpenR1-Math, MulFeRL outperforms supervised, self-distillation-based, and RLVR baselines in-domain, while also showing strong out-of-domain generalization.

cs.AI↗

arXiv2026

UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems

LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules, while agents are rarely optimized through a unified reinforcement learning interface. Existing RL post-training frameworks mainly target single-policy optimization and lack abstractions for user-defined multi-agent workflows, structured interaction, role-specific credit assignment, and configurable parameter sharing. We present UnityMAS-O, a general RL optimization framework for LLM-based multi-agent systems. UnityMAS-O treats the complete workflow as the optimization unit, rather than a single response or policy trajectory. It represents workflows through four first-class objects: logical agent roles, graph trajectories, user-defined rewards, and agent--model mappings. This decouples logical agents from physical model parameters, supporting full sharing, full separation, and partial sharing, with rewards assigned at role, turn, and trajectory levels. UnityMAS-O extends verl with a Ray-based star-topology runtime. A central controller executes workflows, invokes tools, records structured trajectories, and assembles rewards; model-local worker groups handle rollout, buffering, advantage computation, and distributed PPO-style updates. Users can define agents, workflows, model mappings, and rewards without rewriting the optimization infrastructure. We instantiate UnityMAS-O on retrieval-augmented QA, iterative agentic search, and reflective code generation. Across Natural Questions, HotpotQA, and held-out code tasks, multi-agent RL improves manually specified workflows after optimization, with especially large gains for smaller models and strict code all-passed metrics. These results show that UnityMAS-O can serve as a reusable substrate for converting diverse LLM-based multi-agent workflows into trainable multi-agent RL systems.

cs.AI↗

arXiv2026

X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning

In this paper, we present X-Voice, a 0.4B multilingual zero-shot voice cloning model that clones arbitrary voices and enables everyone to speak 30 languages. X-Voice is trained on a 420K-hour multilingual corpus using the International Phonetic Alphabet (IPA) as a unified representation. To eliminate the reliance on prompt text without complex preprocessing like forced alignment, we design a two-stage training paradigm. In Stage 1, we establish X-Voice$_{\text{s1}}$ through standard conditional flow-matching training and use it to synthesize 10K hours of speaker-consistent segments as audio prompts. In Stage 2, we fine-tune on these audio pairs with prompt text masked to derive X-Voice$_{\text{s2}}$, which enables zero-shot voice cloning without requiring transcripts of audio prompts. Architecturally, we extend F5-TTS by implementing a dual-level injection of language identifiers and decoupling and scheduling of Classifier-Free Guidance to facilitate multilingual speech synthesis. Subjective and objective evaluation results demonstrate that X-Voice outperforms existing flow-matching based multilingual systems like LEMAS-TTS and achieves zero-shot cross-lingual cloning capabilities comparable to billion-scale models such as Qwen3-TTS. To facilitate research transparency and community advancement, we open-source all related resources.

cs.SD↗

arXiv2026

Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs

Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on external retrieval, which is similarity-based, can introduce noise, and adds latency. We introduce SEAM (Structured Experience Adapter Module), a lightweight, executor-specific plug-in that stores experience in its parameters and generates a structured, instance-tailored experience entry in a single forward pass to guide a frozen LLM executor. SEAM is trained for utility via executor rollouts and GRPO while keeping the executor frozen, and it can be further improved after deployment with supervised fine-tuning on logged successful trajectories. Experiments on mathematical reasoning benchmarks show consistent accuracy gains across executors with low overhead. Extensive ablations and analyses further elucidate the mechanisms underlying SEAM's effectiveness and robustness.

cs.LG↗

arXiv2026

ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesis

Zero-shot text-to-speech models can clone a speaker's timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires carefully selecting reference audio, which is impractical when only limited or mismatched references are available. While recent controllable TTS methods attempt to address this issue, they typically rely on absolute style targets and discrete textual prompts, and therefore do not support continuous and reference-relative style control. We propose ReStyle-TTS, a framework that enables continuous and reference-relative style control in zero-shot TTS. Our key insight is that effective style control requires first reducing the model's implicit dependence on reference style before introducing explicit control mechanisms. To this end, we introduce Decoupled Classifier-Free Guidance (DCFG), which independently controls text and reference guidance, reducing reliance on reference style while preserving text fidelity. On top of this, we apply style-specific LoRAs together with Orthogonal LoRA Fusion to enable continuous and disentangled multi-attribute control, and introduce a Timbre Consistency Optimization module to mitigate timbre drift caused by weakened reference guidance. Experiments show that ReStyle-TTS enables user-friendly, continuous, and relative control over pitch, energy, and multiple emotions while maintaining intelligibility and speaker timbre, and performs robustly in challenging mismatched reference-target style scenarios.

eess.AS↗

arXiv2026

Closeby Habitable Exoplanet Survey (CHES). V. Planetary Parameters Derived from Angular Separation Variations

The Closeby Habitable Exoplanet Survey (CHES) aims to achieve microarcsecond-level astrometry of about one hundred nearby FGK-type stars within 10 parsecs to detect Earth-like planets. Such precision exceeds the capability of absolute astrometry relying on Gaia catalogs, whose positional accuracy degrades over time due to error propagation from stellar motion and epoch offsets, limiting their use in microarcsecond-level detection. Traditional relative astrometry depends on positional components along right ascension and declination, requiring precise knowledge of field rotation and satellite attitude, which introduces additional errors. To address this, we propose a new relative measurement model based solely on variations in the length of angular separation between the target and reference stars, independent of direction. The model incorporates effects such as proper motion, parallax, radial velocity, light aberration, gravitational lensing, and planetary perturbations, enabling reconstruction of planetary orbits and masses. This approach enhances measurement stability and precision, providing a framework that is not entirely dependent on the Gaia catalog and suitable for CHES and other future high-accuracy astrometric missions.

astro-ph.EP↗

arXiv2026

A Contrastive Learning Foundation Model Based on Perfectly Aligned Sample Pairs for Remote Sensing Images

Self-Supervised Learning (SSL) enables us to pre-train foundation models without costly labeled data. Among SSL methods, Contrastive Learning (CL) methods are better at obtaining accurate semantic representations in noise interference. However, due to the significant domain gap, while CL methods have achieved great success in many computer vision tasks, they still require specific adaptation for Remote Sensing (RS) images. To this end, we present a novel self-supervised method called PerA, which produces all-purpose RS features through semantically Perfectly Aligned sample pairs. Specifically, PerA obtains features from sampled views by applying spatially disjoint masks to augmented images rather than random cropping. Our framework provides high-quality features by ensuring consistency between teacher and student and predicting learnable mask tokens. Compared to previous contrastive methods, our method demonstrates higher memory efficiency and can be trained with larger batches due to its sparse inputs. Additionally, the proposed method demonstrates remarkable adaptability to uncurated RS data and reduce the impact of the potential semantic inconsistency. We also collect an unlabeled pre-training dataset, which contains about 5 million RS images. We conducted experiments on multiple downstream task datasets and achieved performance comparable to previous state-of-the-art methods with a limited model scale, demonstrating the effectiveness of our approach. We hope this work will contribute to practical remote sensing interpretation works.

eess.IV↗