arXiv subjects

Hao Liang

Publications and source records attributed to Hao Liang.

At least 109 records · Page 6Linked to original sources

arXiv2025

Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal scenarios. To address this gap, we introduce a caption-assisted reasoning framework that effectively bridges visual and textual modalities. Our approach achieved 1st place in the ICML 2025 AI for Math Workshop \& Challenge 2: SeePhys, highlighting its effectiveness and robustness. Furthermore, we validate its generalization on the MathVerse benchmark for geometric reasoning, demonstrating the versatility of our method. Our code is publicly available at https://github.com/OpenDCAI/SciReasoner.

cs.CL↗

arXiv2025

Direct measurement of the 103Rh(n,gamma) and 103Rh(gamma,n) cross section up to stellar temperatures at the CSNS Back-n and SSRF SLEGS

The cross sections of 103Rh(n,gamma) and 103Rh(gamma,n) play a crucial role in the stellar nucleosynthesis, rhodium-based self-powered neutron detectors, and nuclear medicine. The cross sections of 103Rh(n,gamma) was measured by the time-of-flight(TOF) method from 1 eV to 1000 keV at the Back-n facility of the Chinese Spallation Neutron Source. In the resolved resonance region, the data reported multiple new resonance structures for the first time. And some discrepancies were observed, offering valuable insights into the differences between the evaluated libraries. Maxwellian-averaged cross sections (MACSs) were calculated within the temperature range of the s process nucleosynthesis model, based on the averaged cross sections in the unresolved resonance region. Meanwhile the cross sections of 103Rh(gamma,n) within the range of p process nucleosynthesis were measured using laser Compton scattering (LCS) gamma rays and a new neutron flat efficiency detector (FED) array at the Shanghai Laser Electron Gamma Source (SLEGS), Shanghai Synchrotron Radiation Facility (SSRF). Using an unfolding iteration method, 103Rh(gamma,n) data were obtained with uncertainty less than 5%, and the inconsistencies between the available experimental data and the evaluated libraries were discussed. This study provides a reliable benchmark for nuclear data evaluation and model optimization, and lays a solid foundation for Rh medical isotope applications and astrophysical research.

nucl-ex↗

arXiv2025

Bright 25-attosecond light pulses reach the one atomic unit of time

Generating ever-shorter and brighter light pulses has long been a central pursuit in ultrafast science, as it benchmarks our ability to create and manipulate the coherence on the intrinsic timescale of sub-atomic electron motion. The current state-of-the-art in attosecond pulse generation reaches durations of 40-50 attoseconds (1 as = $10^{-18}$ seconds), produced via high-order harmonic generation (HHG) driven by secondary mid-infrared light sources. However, these sources often suffer from low stability and poor HHG conversion efficiency. In this work, we demonstrate the generation of 25$\pm$2 attosecond light pulses, a new world record for the shortest light pulse, driven by a post-compressed, industrial-grade Yb-based laser system. The resulting high-harmonic spectrum spans photon energies from 50 eV to 320 eV, covering the carbon K-edge, with a calibrated photon flux exceeding $10^{12}$ photons per second, approximately three orders of magnitude higher than previous studies. The pulse duration was characterized using an angle-resolved photoelectron streaking camera on helium atoms and systematically optimized through the use of dielectric filters of varying thicknesses to compensate the attochirp. Our study reaches the threshold of one atomic unit of time (24.2 attoseconds), the boundary between atomic and ionic physics, opening the door to resolving exciting ionic quantum dynamics with tabletop lasers.

physics.atom-ph↗

arXiv2025

SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models

Vision-Language Models (VLMs) have recently emerged, demonstrating remarkable vision-understanding capabilities. However, training these models requires large-scale datasets, which brings challenges related to efficiency, effectiveness, and quality of web data. In this paper, we introduce SynthVLM, a new data synthesis and curation method for generating image-caption pairs. Unlike traditional methods, where captions are generated from images, SynthVLM utilizes advanced diffusion models and high-quality captions to synthesize and select images from text captions, thereby creating precisely aligned image-text pairs. We further introduce SynthVLM-100K, a high-quality dataset consisting of 100K curated and synthesized image-caption pairs. In both model and human evaluations, SynthVLM-100K outperforms traditional real-world datasets. Leveraging this dataset, we develop a new family of multimodal large language models (MLLMs), SynthVLM-7B and SynthVLM-13B, which achieve state-of-the-art (SOTA) performance on various vision question-answering (VQA) tasks. Notably, our models outperform LLaVA across most metrics with only 18\% pretrain data. Furthermore, SynthVLM-7B and SynthVLM-13B attain SOTA performance on the MMLU benchmark, demonstrating that the high-quality SynthVLM-100K dataset preserves language abilities.

cs.CV↗

arXiv2025

Flavor Physics at the CEPC: a General Perspective

We discuss the landscape of flavor physics at the Circular Electron-Positron Collider (CEPC), based on the nominal luminosity outlined in its Technical Design Report. The CEPC is designed to operate in multiple modes to address a variety of tasks. At the $Z$ pole, the expected production of 4 Tera $Z$ bosons will provide unique and highly precise measurements of $Z$ boson couplings, while the substantial number of boosted heavy-flavored quarks and leptons produced in clean $Z$ decays will facilitate investigations into their flavor physics with unprecedented precision. We investigate the prospects of measuring various physics benchmarks and discuss their implications for particle theories and phenomenological models. Our studies indicate that, with its highlighted advantages and anticipated excellent detector performance, the CEPC can explore beauty and $τ$ physics in ways that are superior to or complementary with the Belle II and Large-Hadron-Collider-beauty experiments, potentially enabling the detection of new physics at energy scales of 10 TeV and above. This potential also extends to the observation of yet-to-be-discovered rare and exotic processes, as well as testing fundamental principles such as lepton flavor universality, lepton and baryon number conservation, etc., making the CEPC a vibrant platform for flavor physics research. The $WW$ threshold scan, Higgs-factory operation and top-pair productions of the CEPC further enhance its merits in this regard, especially for measuring the Cabibbo-Kobayashi-Maskawa matrix elements, and Flavor-Changing-Neutral-Current physics of Higgs boson and top quarks. We outline the requirements for detector performance and considerations for future development to achieve the anticipated scientific goals.

hep-ex↗

arXiv2025

QAEncoder: Towards Aligned Representation Learning in Question Answering Systems

Modern QA systems entail retrieval-augmented generation (RAG) for accurate and trustworthy responses. However, the inherent gap between user queries and relevant documents hinders precise matching. We introduce QAEncoder, a training-free approach to bridge this gap. Specifically, QAEncoder estimates the expectation of potential queries in the embedding space as a robust surrogate for the document embedding, and attaches document fingerprints to effectively distinguish these embeddings. Extensive experiments across diverse datasets, languages, and embedding models confirmed QAEncoder's alignment capability, which offers a simple-yet-effective solution with zero additional index storage, retrieval latency, training costs, or catastrophic forgetting and hallucination issues. The repository is publicly available at https://github.com/IAAR-Shanghai/QAEncoder.

cs.CL↗

arXiv2025

Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models

Vision-Language Models (VLMs) face significant challenges when dealing with the diverse resolutions and aspect ratios of real-world images, as most existing models rely on fixed, low-resolution inputs. While recent studies have explored integrating native resolution visual encoding to improve model performance, such efforts remain fragmented and lack a systematic framework within the open-source community. Moreover, existing benchmarks fall short in evaluating VLMs under varied visual conditions, often neglecting resolution as a critical factor. To address the "Resolution Dilemma" stemming from both model design and benchmark limitations, we introduce RC-Bench, a novel benchmark specifically designed to systematically evaluate VLM capabilities under extreme visual conditions, with an emphasis on resolution and aspect ratio variations. In conjunction, we propose NativeRes-LLaVA, an open-source training framework that empowers VLMs to effectively process images at their native resolutions and aspect ratios. Based on RC-Bench and NativeRes-LLaVA, we conduct comprehensive experiments on existing visual encoding strategies. The results show that Native Resolution Visual Encoding significantly improves the performance of VLMs on RC-Bench as well as other resolution-centric benchmarks. Code is available at https://github.com/Niujunbo2002/NativeRes-LLaVA.

cs.CV↗

arXiv2025

One-to-one correspondence reconstruction at the electron-positron Higgs factory

We propose one-to-one correspondence reconstruction for electron-positron Higgs factories. For each visible particle, one-to-one correspondence aims to associate relevant detector hits with only one reconstructed particle and accurately identify its species. To achieve this goal, we develop a novel detector concept featuring 5-dimensional calorimetry that provides spatial, energy, and time measurements for each hit, and a reconstruction framework that combines state-of-the-art particle flow and artificial intelligence algorithms. In the benchmark process of Higgs to di-jets, over 90% of visible energy can be successfully mapped into well-reconstructed particles that not only maintain a one-to-one correspondence relationship but also associate with the correct combination of cluster and track, improving the invariant mass resolution of hadronically decayed Higgs bosons by 25%. Performing simultaneous identification on these well-reconstructed particles, we observe efficiencies of 97% to nearly 100% for charged particles ($e^{\pm}$, $μ^{\pm}$, $π^{\pm}$, $K^{\pm}$, $p/\bar{p}$) and photons ($γ$), and 75% to 80% for neutral hadrons ($K_L^0$, $n$, $\bar{n}$). For physics measurements of Higgs to invisible and exotic decays, golden channels to probe new physics, one-to-one correspondence could enhance discovery power by 10% to up to a factor of two. This study demonstrates the necessity and feasibility of one-to-one correspondence reconstruction at electron-positron Higgs factories.

hep-ex↗

arXiv2025

LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning

Large language models (LLMs) excel at many supervised tasks but often struggle with structured reasoning in unfamiliar settings. This discrepancy suggests that standard fine-tuning pipelines may instill narrow, domain-specific heuristics rather than fostering general-purpose thinking strategies. In this work, we propose a "play to learn" framework that fine-tunes LLMs through reinforcement learning on a suite of seven custom logic puzzles, each designed to cultivate distinct reasoning skills such as constraint propagation, spatial consistency, and symbolic deduction. Using a reinforcement learning setup with verifiable rewards, models receive binary feedback based on puzzle correctness, encouraging iterative, hypothesis-driven problem solving. We demonstrate that this training approach significantly improves out-of-distribution performance on a range of mathematical benchmarks, especially for mid-difficulty problems that require multi-step reasoning. Analyses across problem categories and difficulty levels reveal that puzzle training promotes transferable reasoning routines, strengthening algebraic manipulation, geometric inference, and combinatorial logic, while offering limited gains on rote or highly specialized tasks. These findings show that reinforcement learning over logic puzzles reshapes the internal reasoning of LLMs, enabling more robust and compositional generalization without relying on task-specific symbolic tools.

cs.LG↗

arXiv2025

MTCMB: A Multi-Task Benchmark Framework for Evaluating LLMs on Knowledge, Reasoning, and Safety in Traditional Chinese Medicine

Traditional Chinese Medicine (TCM) is a holistic medical system with millennia of accumulated clinical experience, playing a vital role in global healthcare-particularly across East Asia. However, the implicit reasoning, diverse textual forms, and lack of standardization in TCM pose major challenges for computational modeling and evaluation. Large Language Models (LLMs) have demonstrated remarkable potential in processing natural language across diverse domains, including general medicine. Yet, their systematic evaluation in the TCM domain remains underdeveloped. Existing benchmarks either focus narrowly on factual question answering or lack domain-specific tasks and clinical realism. To fill this gap, we introduce MTCMB-a Multi-Task Benchmark for Evaluating LLMs on TCM Knowledge, Reasoning, and Safety. Developed in collaboration with certified TCM experts, MTCMB comprises 12 sub-datasets spanning five major categories: knowledge QA, language understanding, diagnostic reasoning, prescription generation, and safety evaluation. The benchmark integrates real-world case records, national licensing exams, and classical texts, providing an authentic and comprehensive testbed for TCM-capable models. Preliminary results indicate that current LLMs perform well on foundational knowledge but fall short in clinical reasoning, prescription planning, and safety compliance. These findings highlight the urgent need for domain-aligned benchmarks like MTCMB to guide the development of more competent and trustworthy medical AI systems. All datasets, code, and evaluation tools are publicly available at: https://github.com/Wayyuanyuan/MTCMB.

cs.CL↗

arXiv2025

Scalable twin-field quantum key distribution network enabled by adaptable architecture

Quantum key distribution (QKD) is a key application in quantum communication, enabling secure key exchange between parties using quantum states. Twin-field (TF) QKD offers a promising solution that surpasses the repeaterless limits, and its measurement-device-independent nature makes it suitable for star-type network architectures. In this work, we propose a scalable TF-QKD network with adaptable architecture, where users prepare quantum signals and send them to network nodes. These nodes use an optical switch to route the signals to multi-user measurement units, enabling secure key distribution among arbitrary users and adapting to complex connection demands of the network. A proof-of-principle demonstration with three users successfully achieved secure key sharing over simulated link losses of up to $30$ dB, with an average rate of $19.57$ bit/s. Additionally, simulations show that the proposed architecture can achieve a total secure key rate of $4.84 \times 10^{4}$ bit/s at $100$ km in a symmetric $32$-user network. This approach represents a significant advancement in the topology of untrusted-node QKD networks and holds promise for practical, large-scale applications in secure communication.

quant-ph↗

arXiv2025

ChatStitch: Visualizing Through Structures via Surround-View Unsupervised Deep Image Stitching with Collaborative LLM-Agents

Surround-view perception has garnered significant attention for its ability to enhance the perception capabilities of autonomous driving vehicles through the exchange of information with surrounding cameras. However, existing surround-view perception systems are limited by inefficiencies in unidirectional interaction pattern with human and distortions in overlapping regions exponentially propagating into non-overlapping areas. To address these challenges, this paper introduces ChatStitch, a surround-view human-machine co-perception system capable of unveiling obscured blind spot information through natural language commands integrated with external digital assets. To dismantle the unidirectional interaction bottleneck, ChatStitch implements a cognitively grounded closed-loop interaction multi-agent framework based on Large Language Models. To suppress distortion propagation across overlapping boundaries, ChatStitch proposes SV-UDIS, a surround-view unsupervised deep image stitching method under the non-global-overlapping condition. We conducted extensive experiments on the UDIS-D, MCOV-SLAM open datasets, and our real-world dataset. Specifically, our SV-UDIS method achieves state-of-the-art performance on the UDIS-D dataset for 3, 4, and 5 image stitching tasks, with PSNR improvements of 9\%, 17\%, and 21\%, and SSIM improvements of 8\%, 18\%, and 26\%, respectively.

cs.CV↗

arXiv2025

How Reconnection-Unfavored Magnetic Flux Emergence Suppresses Solar Filament Eruptions

Magnetic flux emergence is traditionally considered a key trigger of solar filament eruptions; however, its role in suppressing filament eruptions remains less understood. Using multi-wavelength observations from the Solar Dynamics Observatory, this study investigates a unique case of flux emergence below a quiescent filament from January 3 to 5, 2016, where the newly emerging magnetic flux suppressed rather than promoted the eruption of the filament. It is found that the emerging magnetic bipole within the filament channel directly interacted and reconnected with the overlying filament magnetic field and produced a series of two-sided coronal jets along the filament axis. Instead of eruption, the filament kept stable but broke into two segments at the reconnection site. Further magnetic cancellation or recession of the emerged bipole allowed the filament to recover its original structure. Our analysis results revealed that the flux emergence suppressed the filament eruption by reducing the upward net force. The formation and evolution of filament fine structures, such as filament threads, are closely linked to the reconnection processes between the emerging bipole and the horizontal magnetic field of the filament. This study provides direct observational evidence for the stabilization of solar filaments driven by flux emergence, offering new insights into the dual role of magnetic emergence in triggering and suppressing solar eruptions.

astro-ph.SR↗

arXiv2025

CFBench: A Comprehensive Constraints-Following Benchmark for LLMs

The adeptness of Large Language Models (LLMs) in comprehending and following natural language instructions is critical for their deployment in sophisticated real-world applications. Existing evaluations mainly focus on fragmented constraints or narrow scenarios, but they overlook the comprehensiveness and authenticity of constraints from the user's perspective. To bridge this gap, we propose CFBench, a large-scale Comprehensive Constraints Following Benchmark for LLMs, featuring 1,000 curated samples that cover more than 200 real-life scenarios and over 50 NLP tasks. CFBench meticulously compiles constraints from real-world instructions and constructs an innovative systematic framework for constraint types, which includes 10 primary categories and over 25 subcategories, and ensures each constraint is seamlessly integrated within the instructions. To make certain that the evaluation of LLM outputs aligns with user perceptions, we propose an advanced methodology that integrates multi-dimensional assessment criteria with requirement prioritization, covering various perspectives of constraints, instructions, and requirement fulfillment. Evaluating current leading LLMs on CFBench reveals substantial room for improvement in constraints following, and we further investigate influencing factors and enhancement strategies. The data and code are publicly available at https://github.com/PKU-Baichuan-MLSystemLab/CFBench

cs.CL↗

arXiv2025

Unified Vertex Motion Estimation for Integrated Video Stabilization and Stitching in Tractor-Trailer Wheeled Robots

Tractor-trailer wheeled robots need to perform comprehensive perception tasks to enhance their operations in areas such as logistics parks and long-haul transportation. The perception of these robots faces three major challenges: the asynchronous vibrations between the tractor and trailer, the relative pose change between the tractor and trailer, and the significant camera parallax caused by the large size. In this paper, we employ the Dual Independence Stabilization Motion Field Estimation method to address asynchronous vibrations between the tractor and trailer, effectively eliminating conflicting motion estimations for the same object in overlapping regions. We utilize the Random Plane-based Stitching Motion Field Estimation method to tackle the continuous relative pose changes caused by the articulated hitch between the tractor and trailer, thus eliminating dynamic misalignment in overlapping regions. Furthermore, we apply the Unified Vertex Motion Estimation method to manage the challenges posed by the tractor-trailer's large physical size, which results in severely low overlapping regions between the tractor and trailer views, thus preventing distortions in overlapping regions from exponentially propagating into non-overlapping areas. Furthermore, this framework has been successfully implemented in real tractor-trailer wheeled robots. The proposed Unified Vertex Motion Video Stabilization and Stitching method has been thoroughly tested in various challenging scenarios, demonstrating its accuracy and practicality in real-world.

cs.RO↗

arXiv2025

Hearing carrier-envelope offset frequency and phase in air with a microphone

Attosecond science and frequency metrology rely on the precise measurement and control of the laser pulse waveform, a feat traditionally achieved using optoelectronic techniques. In this study, we conducted a laser-induced acoustic experiment in air ionized by carrier-envelope phase (CEP)-stabilized sub-4 femtosecond pulses. Our results reveal that the acoustic signal exhibits CEP dependence in few-cycle pulses, primarily through amplitude modulation from laser-driven ionization. This novel optoacoustic phenomenon enables not only the measurement of the carrier-envelope offset frequency but also the direct characterization of the waveform of optical pulses through a microphone. Our study highlights the potential of laser-induced acoustic waves for advancing frequency metrology and ultrafast science.

physics.optics↗

arXiv2025

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

Current vision-language models (VLMs) show exceptional abilities across diverse tasks, such as visual question answering. To enhance user experience, recent studies investigate VLM personalization to understand user-provided concepts. However, they mainly focus on single-concept personalization, neglecting the existence and interplay of multiple concepts, which limits real-world applicability. This paper proposes the first multi-concept personalization paradigm, MC-LLaVA. Specifically, MC-LLaVA employs a multi-concept instruction tuning strategy, effectively integrating multiple concepts in a single training step. To reduce the costs related to joint training, we propose a personalized textual prompt that uses visual token information to initialize concept tokens. Additionally, we introduce a personalized visual prompt during inference, aggregating location confidence maps for enhanced recognition and grounding capabilities. To advance multi-concept personalization research, we further contribute a high-quality instruction tuning dataset. We carefully collect images with multiple characters and objects from movies and manually generate question-answer samples for multi-concept scenarios, featuring superior diversity. Comprehensive qualitative and quantitative experiments demonstrate that MC-LLaVA can achieve impressive multi-concept personalized responses, paving the way for VLMs to become better user-specific assistants. The code and dataset will be publicly available at https://github.com/arctanxarc/MC-LLaVA}.

cs.CV↗

arXiv2025

Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning

Large Language Models (LLMs) have exhibited significant potential in performing diverse tasks, including the ability to call functions or use external tools to enhance their performance. While current research on function calling by LLMs primarily focuses on single-turn interactions, this paper addresses the overlooked necessity for LLMs to engage in multi-turn function calling--critical for handling compositional, real-world queries that require planning with functions but not only use functions. To facilitate this, we introduce an approach, BUTTON, which generates synthetic compositional instruction tuning data via bottom-up instruction construction and top-down trajectory generation. In the bottom-up phase, we generate simple atomic tasks based on real-world scenarios and build compositional tasks using heuristic strategies based on atomic tasks. Corresponding function definitions are then synthesized for these compositional tasks. The top-down phase features a multi-agent environment where interactions among simulated humans, assistants, and tools are utilized to gather multi-turn function calling trajectories. This approach ensures task compositionality and allows for effective function and trajectory generation by examining atomic tasks within compositional tasks. We produce a dataset BUTTONInstruct comprising 8k data points and demonstrate its effectiveness through extensive experiments across various LLMs.

cs.CL↗