arXiv subjects

Haitao Li

Publications and source records attributed to Haitao Li.

At least 55 records · Page 3Linked to original sources

arXiv2026

LegalOne: A Family of Foundation Models for Reliable Legal Reasoning

While Large Language Models (LLMs) have demonstrated impressive general capabilities, their direct application in the legal domain is often hindered by a lack of precise domain knowledge and complexity of performing rigorous multi-step judicial reasoning. To address this gap, we present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain. LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning. First, during mid-training phase, we propose Plasticity-Adjusted Sampling (PAS) to address the challenge of domain adaptation. This perplexity-based scheduler strikes a balance between the acquisition of new knowledge and the retention of original capabilities, effectively establishing a robust legal foundation. Second, during supervised fine-tuning, we employ Legal Agentic CoT Distillation (LEAD) to distill explicit reasoning from raw legal texts. Unlike naive distillation, LEAD utilizes an agentic workflow to convert complex judicial processes into structured reasoning trajectories, thereby enforcing factual grounding and logical rigor. Finally, we implement a Curriculum Reinforcement Learning (RL) strategy. Through a progressive reinforcement process spanning memorization, understanding, and reasoning, LegalOne evolves from simple pattern matching to autonomous and reliable legal reasoning. Experimental results demonstrate that LegalOne achieves state-of-the-art performance across a wide range of legal tasks, surpassing general-purpose LLMs with vastly larger parameter counts through enhanced knowledge density and efficiency. We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI, paving the way for deploying trustworthy and interpretable foundation models in high-stakes judicial applications.

cs.CL↗

arXiv2026

ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs

Long-context inputs in large language models (LLMs) often suffer from the "lost in the middle" problem, where critical information becomes diluted or ignored due to excessive length. Context compression methods aim to address this by reducing input size, but existing approaches struggle with balancing information preservation and compression efficiency. We propose Adaptive Task-Aware Compressor (ATACompressor), which dynamically adjusts compression based on the specific requirements of the task. ATACompressor employs a selective encoder that compresses only the task-relevant portions of long contexts, ensuring that essential information is preserved while reducing unnecessary content. Its adaptive allocation controller perceives the length of relevant content and adjusts the compression rate accordingly, optimizing resource utilization. We evaluate ATACompressor on three QA datasets: HotpotQA, MSMARCO, and SQUAD-showing that it outperforms existing methods in terms of both compression efficiency and task performance. Our approach provides a scalable solution for long-context processing in LLMs. Furthermore, we perform a range of ablation studies and analysis experiments to gain deeper insights into the key components of ATACompressor.

cs.CL↗

arXiv2026

VideoPro: Adaptive Program Reasoning for Long Video Understanding

Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on closed-source models, lack systematic reasoning, and struggle with long-form video question answering (videoQA). To address these challenges, we introduce the FS-VisPR framework, an adaptive visual program reasoning approach that balances fast reasoning for simple queries with slow reasoning for difficult ones. First, we design efficient visual modules (e.g., key clip retrieval and subtitle retrieval) to support long-form video tasks. Then, we construct a diverse and high-quality fast-slow reasoning dataset with a strong LLM to align open-source language models' ability to generate visual program workflows as FS-LLM. Next, we design a fast-slow reasoning framework with FS-LLM: Simple queries are directly solved by VideoLLMs, while difficult ones invoke visual program reasoning, motivated by human-like reasoning processes. During this process, low-confidence fast-thinking answers will trigger a second-stage slow-reasoning process, and a fallback mechanism to fast reasoning is activated if the program execution fails. Moreover, we improve visual programs through parameter search during both training and inference. By adjusting the parameters of the visual modules within the program, multiple variants are generated: during training, programs that yield correct answers are selected, while during inference, the program with the highest confidence result is applied. Experiments show that FS-VisPR improves both efficiency and reliability in visual program workflows. It achieves 50.4% accuracy on LVBench, surpassing GPT-4o, matching the performance of Qwen2.5VL-72B on VideoMME.

cs.CV↗

arXiv2026

Evaluation of Large Language Models in Legal Applications: Challenges, Methods, and Future Directions

Large language models (LLMs) are being increasingly integrated into legal applications, including judicial decision support, legal practice assistance, and public-facing legal services. While LLMs show strong potential in handling legal knowledge and tasks, their deployment in real-world legal settings raises critical concerns beyond surface-level accuracy, involving the soundness of legal reasoning processes and trustworthy issues such as fairness and reliability. Systematic evaluation of LLM performance in legal tasks has therefore become essential for their responsible adoption. This survey identifies key challenges in evaluating LLMs for legal tasks grounded in real-world legal practice. We analyze the major difficulties involved in assessing LLM performance in the legal domain, including outcome correctness, reasoning reliability, and trustworthiness. Building on these challenges, we review and categorize existing evaluation methods and benchmarks according to their task design, datasets, and evaluation metrics. We further discuss the extent to which current approaches address these challenges, highlight their limitations, and outline future research directions toward more realistic, reliable, and legally grounded evaluation frameworks for LLMs in legal domains.

cs.CY↗

arXiv2026

Unveiling spin-orbital angular momentum locking in photonic Dirac vortex cavities

Dirac vortices, originally studied in quantum field theories to predict localized zero-energy modes, were recently realized in photonics, leading to Dirac vortex cavities. With topological protection, Dirac vortex cavities offer robust single-mode large-area localized modes appealing for high-performance micro-lasers and other applications. As a spectrally-isolated single mode, the radiation of a Dirac vortex cavity mode was believed as having vanishing orbital angular momentum due to time-reversal symmetry. Here, we report the direct observation of orbital angular momentum radiation of a Dirac vortex cavity through spin-resolved measurements. Remarkably, we confirm the spin-orbital angular momentum locking in such radiation due to the spin-valley locking and inter-valley couplings. We demonstrate that the spin-orbital angular momentum locking is controlled by the chirality of the Kekulé modulation and propose design schemes for arbitrary-order single-mode OAM radiation.

physics.optics↗

arXiv2025

Giant and Rapidly Switching Intrinsic Chirality Enabled by Toroidal Quasi-Bound States in the Continuum

Circular dichroism (CD), arising from spin-selective light-matter interactions controlled by chirality, is critical for advanced applications such as chiral imaging and ultrasensitive biosensing. However, CD of chiral natural materials is inherently constrained owing to molecular symmetry and thermodynamic stability. Recently, artificially engineered metasurfaces incorporating chiral quasi-bound states in the continuum (Q-BICs) have emerged as a promising solution, which enables near-unity CD responses. However, their current designs heavily rely on complex three-dimensional geometries, posing significant challenges for integration with planar on-chip platforms. To address the stringent challenges, we demonstrate a truly planar metasurface that achieves giant intrinsic chiral responses by utilizing a chiral Q-BIC dominated by out-of-plane toroidal dipoles (Tz). With deep-subwavelength (λ/20) thickness, our metasurface exhibits outstanding intrinsic CD values in both simulations (>0.90) and experiments (~0.80). Moreover, in contrast to previous electric or magnetic chiral Q-BICs, the toroidal Q-BIC produces a rapidly switching CD response - transitioning sharply between positive and negative giant CD values within ~0.2 GHz, and the switching is highly sensitive to small oblique incidence of opposite angles. Therefore, our scheme provides a planar platform for studying chiral light-matter interactions involving toroidal dipoles, important for future development of polarization- and angle-sensitive photonic and optoelectronic devices.

physics.optics↗

arXiv2025

Kirigami-based Flexible Metasurface with Reconfigurable Intrinsic Chirality from Zero to Near-unity

Chiral responses in electromagnetic metasurfaces are typically categorized as extrinsic, resulting from asymmetric interactions between the structure and incident waves, and intrinsic, arising from three-dimensional symmetry breaking of the unit cell. However, most existing metasurface designs target only one type of chirality and lack a unified, continuously tunable platform for broader chiroptical control. To address this limitation, the designed kirigami-based flexible metasurface is proposed for dynamic, continuous modulation of chirality, which expands the control scope to both extrinsic and intrinsic chiral responses within a single, reconfigurable platform. Initially, the unfolded metasurface exhibits extrinsic chirality under oblique incidence. By introducing well-designed kirigami-based cuts and folds, the metasurface transitions from a planar and achiral configuration to a three-dimensional chiral geometry that breaks the mirror symmetry, thereby exhibiting tunable intrinsic chirality and asymmetric extrinsic chirality. As the folding angle increases, the resulting deformation enables continuous tuning of the chiral response, with circular dichroism and its asymmetry under oblique incidences progressively increasing and reaching pronounced levels across the X-band. Our work provides a lightweight, easy-fabricated, and mechanically reconfigurable metasurface, which offers strong potential for future development in adaptive photonic systems and advanced chiroptical technologies.

physics.optics↗

arXiv2025

Hybrid Cavity from Tunable Coupling between Anapole and Fabry-Perot Resonance or Anti-resonance

Enhancing light-matter interactions depends critically on the ability to tailor photonic modes at subwavelength scales, and combining distinct resonant modes has shown remarkable potential unattainable by individual resonances alone. Despite recent advances in anapole metasurfaces for energy confinement and Fabry-Perot (FP) cavities for spectral control, their synergistic coupling and resulting opportunities remain largely unexplored due to challenges such as precise nanoscale assembly. Here, we demonstrate that embedding a terahertz (THz) anapole metasurface within a tunable FP cavity results in a hybrid cavity that demonstrates exotic properties as the anapole transitions between coupling to FP resonances and anti-resonances via cavity-length tuning. At room temperature, we observe ultrastrong coupling (> 30% of the anapole frequency) between anapoles and FP resonances, generating tunable-dispersion polaritons that blend favorable properties of both modes. Meanwhile, anapole spectrally aligns with FP anti-resonances, leading to weak coupling that narrows the linewidth of the anapole's transmission peak by two orders of magnitude and enhances its local density of states (LDOS) near the metasurface correspondingly. With exceptional capabilities including formation of polaritons and significant enhancement of LDOS, the hybrid cavity enables strong interaction with functional materials, paving the way for exploration of quantum optics, molecular sensing, and ultrafast nonlinear photonics.

physics.optics↗

arXiv2025

Translating Electrocardiograms to Cardiac Magnetic Resonance Imaging Useful for Cardiac Assessment and Disease Screening: A Multi-Center Study

Cardiovascular diseases (CVDs) are the leading cause of global mortality, necessitating accessible and accurate diagnostic tools. While cardiac magnetic resonance imaging (CMR) provides gold-standard insights into cardiac structure and function, its clinical utility is limited by high cost and complexity. In contrast, electrocardiography (ECG) is inexpensive and widely available but lacks the granularity of CMR. We propose CardioNets, a deep learning framework that translates 12-lead ECG signals into CMR-level functional parameters and synthetic images, enabling scalable cardiac assessment. CardioNets integrates cross-modal contrastive learning and generative pretraining, aligning ECG with CMR-derived cardiac phenotypes and synthesizing high-resolution CMR images via a masked autoregressive model. Trained on 159,819 samples from five cohorts, including the UK Biobank (n=42,483) and MIMIC-IV-ECG (n=164,550), and externally validated on independent clinical datasets (n=3,767), CardioNets achieved strong performance across disease screening and phenotype estimation tasks. In the UK Biobank, it improved cardiac phenotype regression R2 by 24.8% and cardiomyopathy AUC by up to 39.3% over baseline models. In MIMIC, it increased AUC for pulmonary hypertension detection by 5.6%. Generated CMR images showed 36.6% higher SSIM and 8.7% higher PSNR than prior approaches. In a reader study, ECG-only CardioNets achieved 13.9% higher accuracy than human physicians using both ECG and real CMR. These results suggest that CardioNets offers a promising, low-cost alternative to CMR for large-scale CVD screening, particularly in resource-limited settings. Future efforts will focus on clinical deployment and regulatory validation of ECG-based synthetic imaging.

eess.IV↗

arXiv2025

STCTS: Generative Semantic Compression for Ultra-Low Bitrate Speech via Explicit Text-Prosody-Timbre Decomposition

Voice communication in bandwidth-constrained environments--maritime, satellite, and tactical networks--remains prohibitively expensive. Traditional codecs struggle below 1 kbps, while existing semantic approaches (STT-TTS) sacrifice prosody and speaker identity. We present STCTS, a generative semantic compression framework enabling natural voice communication at 80 bps. STCTS explicitly decomposes speech into linguistic content, prosodic expression, and speaker timbre, applying tailored compression: context-aware text encoding (70 bps), sparse prosody transmission via TTS interpolation (<14 bps at 0.1-1 Hz), and amortized speaker embedding. Evaluations on LibriSpeech demonstrate a 75x bitrate reduction versus Opus (6 kbps) and 12x versus EnCodec (1 kbps), while maintaining perceptual quality (NISQA MOS > 4.26), graceful degradation under packet loss and noise resilience. We also discover a bimodal quality distribution with prosody sampling rate: sparse and dense updates both achieve high quality, while mid-range rates degrade due to perceptual discontinuities--guiding optimal configuration design. Beyond efficiency, our modular architecture supports privacy-preserving encryption, human-interpretable transmission, and flexible deployment on edge devices, offering a robust solution for ultra-low bandwidth scenarios.

cs.SD↗

arXiv2025

Modeling Atmospheric Ion Escape from Kepler-1649 b and c over Time

Rocky planets orbiting M-dwarf stars are prime targets for atmospheric characterization, yet their long-term evolution under intense stellar winds and high-energy radiation remains poorly constrained. The Kepler-1649 system, hosting two terrestrial exoplanets orbiting an M5V star, provides a valuable laboratory for studying atmospheric evolution in the extreme environments typical of M-dwarf systems. In this Letter we show that both planets could have retained atmospheres over gigayear timescales. Using a multi-species magnetohydrodynamic model, we simulate atmospheric ion escape driven by stellar winds and extreme ultraviolet radiation from 0.8 to 4.0 Gyr. The results reveal a clear decline in total ion escape rates with stellar age, as captured by a nonparametric LOWESS regression, with O$^{+}$ comprising 98.3%-99.9% of the total loss. Escape rates at 4.0 Gyr are two to three orders of magnitude lower than during early epochs. At 0.8 Gyr, planet b exhibits 3.79$\times$ higher O$^{+}$ escape rates than planet c, whereas by 4.0 Gyr its O$^{+}$ escape rate becomes 39.5$\times$ lower. This reversal arises from a transition to sub-magnetosonic star-planet interactions, where the fast magnetosonic Mach number, $M_f$, falls below unity. Despite substantial early atmospheric erosion, both planets may have retained significant atmospheres, suggesting potential long-term habitability. These findings offer predictive insight into atmospheric retention in the Kepler-1649 system and inform future JWST observations of similar M-dwarf terrestrial exoplanets aimed at refining habitability assessments.

astro-ph.EP↗

arXiv2025

Deep Research: A Systematic Survey

Large language models (LLMs) have rapidly evolved from text generators into powerful problem solvers. Yet, many open tasks demand critical thinking, multi-source, and verifiable outputs, which are beyond single-shot prompting or standard retrieval-augmented generation. Recently, numerous studies have explored Deep Research (DR), which aims to combine the reasoning capabilities of LLMs with external tools, such as search engines, thereby empowering LLMs to act as research agents capable of completing complex, open-ended tasks. This survey presents a comprehensive and systematic overview of deep research systems, including a clear roadmap, foundational components, practical implementation techniques, important challenges, and future directions. Specifically, our main contributions are as follows: (i) we formalize a three-stage roadmap and distinguish deep research from related paradigms; (ii) we introduce four key components: query planning, information acquisition, memory management, and answer generation, each paired with fine-grained sub-taxonomies; (iii) we summarize optimization techniques, including prompting, supervised fine-tuning, and agentic reinforcement learning; and (iv) we consolidate evaluation criteria and open challenges, aiming to guide and facilitate future development. As the field of deep research continues to evolve rapidly, we are committed to continuously updating this survey to reflect the latest progress in this area.

cs.CL↗

arXiv2025

anyECG-chat: A Generalist ECG-MLLM for Flexible ECG Input and Multi-Task Understanding

The advent of multimodal large language models (MLLMs) has sparked interest in their application to electrocardiogram (ECG) analysis. However, existing ECG-focused MLLMs primarily focus on report generation tasks, often limited to single 12-lead, short-duration (10s) ECG inputs, thereby underutilizing the potential of MLLMs. To this end, we aim to develop a MLLM for ECG analysis that supports a broader range of tasks and more flexible ECG inputs. However, existing ECG-QA datasets are often monotonous. To address this gap, we first constructed the anyECG dataset, which encompasses a wide variety of tasks, including report generation, abnormal waveform localization, and open-ended question answering. In addition to standard hospital ECGs, we introduced long-duration reduced-lead ECGs for home environments and multiple ECG comparison scenarios commonly encountered in clinical practice. Furthermore, we propose the anyECG-chat model, which supports dynamic-length ECG inputs and multiple ECG inputs. We trained the model using a three-stage curriculum training recipe with the anyECG dataset. A comprehensive evaluation was conducted, demonstrating that anyECG-chat is capable of supporting various practical application scenarios, including not only common report generation tasks but also abnormal waveform localization for long-duration reduced-lead ECGs in home environments and comprehensive comparative analysis of multiple ECGs. Our code and data are available at: https://github.com/CuCl-2/anyECG-chat.

cs.CL↗

arXiv2025

Auto-PRE: An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation

The rapid development of large language models (LLMs) has highlighted the need for efficient and reliable methods to evaluate their performance. Traditional evaluation methods often face challenges like high costs, limited task formats, dependence on human references, and systematic biases. To address these limitations, we propose Auto-PRE, an automatic LLM evaluation framework inspired by the peer review process. Unlike previous approaches that rely on human annotations, Auto-PRE automatically selects evaluator LLMs based on three core traits: consistency, pertinence, and self-confidence, which correspond to the instruction, content, and response stages, respectively, and collectively cover the entire evaluation process. Experiments on three representative tasks, including summarization, non-factoid QA, and dialogue generation, demonstrate that Auto-PRE achieves state-of-the-art performance while significantly reducing evaluation costs. Furthermore, the structured and scalable design of our automatic qualification exam framework provides valuable insights into automating the evaluation of LLMs-as-judges, paving the way for more advanced LLM-based evaluation frameworks.

cs.CL↗

arXiv2025

SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation

Existing retrieval-augmented code generation (RACG) methods typically use an external retrieval module to fetch semantically similar code snippets used for generating subsequent fragments. However, even for consecutive code fragments, the content often diverges due to logical progression, resulting in a content gap. This gap undermines the performance of current RACG methods, as \textit{external} retrieval modules based on content matching fail to infer the specific information need of LLMs to generate the next code fragment. Therefore, we propose \textbf{SelfRACG}, a novel paradigm that enables large language models (LLMs) to \textbf{Self}-express their information needs to enhance \textbf{RACG}. Specifically, SelfRACG includes an information need expression module and a two-stage information need-guided training strategy, which encourages LLMs to express their information need. Extensive experiments demonstrate that SelfRACG can retrieve external knowledge that better aligns with the LLM's own information needs, resulting in superior generation performance compared to vanilla RACG.

cs.IR↗

arXiv2025

JustEva: A Toolkit to Evaluate LLM Fairness in Legal Knowledge Inference

The integration of Large Language Models (LLMs) into legal practice raises pressing concerns about judicial fairness, particularly due to the nature of their "black-box" processes. This study introduces JustEva, a comprehensive, open-source evaluation toolkit designed to measure LLM fairness in legal tasks. JustEva features several advantages: (1) a structured label system covering 65 extra-legal factors; (2) three core fairness metrics - inconsistency, bias, and imbalanced inaccuracy; (3) robust statistical inference methods; and (4) informative visualizations. The toolkit supports two types of experiments, enabling a complete evaluation workflow: (1) generating structured outputs from LLMs using a provided dataset, and (2) conducting statistical analysis and inference on LLMs' outputs through regression and other statistical methods. Empirical application of JustEva reveals significant fairness deficiencies in current LLMs, highlighting the lack of fair and trustworthy LLM legal tools. JustEva offers a convenient tool and methodological foundation for evaluating and improving algorithmic fairness in the legal domain.

cs.AI↗

arXiv2025

Chinese Court Simulation with LLM-Based Agent System

Mock trial has long served as an important platform for legal professional training and education. It not only helps students learn about realistic trial procedures, but also provides practical value for case analysis and judgment prediction. Traditional mock trials are difficult to access by the public because they rely on professional tutors and human participants. Fortunately, the rise of large language models (LLMs) provides new opportunities for creating more accessible and scalable court simulations. While promising, existing research mainly focuses on agent construction while ignoring the systematic design and evaluation of court simulations, which are actually more important for the credibility and usage of court simulation in practice. To this end, we present the first court simulation framework -- SimCourt -- based on the real-world procedure structure of Chinese courts. Our framework replicates all 5 core stages of a Chinese trial and incorporates 5 courtroom roles, faithfully following the procedural definitions in China. To simulate trial participants with different roles, we propose and craft legal agents equipped with memory, planning, and reflection abilities. Experiment on legal judgment prediction show that our framework can generate simulated trials that better guide the system to predict the imprisonment, probation, and fine of each case. Further annotations by human experts show that agents' responses under our simulation framework even outperformed judges and lawyers from the real trials in many scenarios. These further demonstrate the potential of LLM-based court simulation.

cs.CY↗

arXiv2025

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes. Through multi-stage training on 23T tokens and comprehensive post-training with expert model iteration and reinforcement learning, GLM-4.5 achieves strong performance across agentic, reasoning, and coding (ARC) tasks, scoring 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified. With much fewer parameters than several competitors, GLM-4.5 ranks 3rd overall among all evaluated models and 2nd on agentic benchmarks. We release both GLM-4.5 (355B parameters) and a compact version, GLM-4.5-Air (106B parameters), to advance research in reasoning and agentic AI systems. Code, models, and more information are available at https://github.com/zai-org/GLM-4.5.

cs.CL↗