arXiv subjects

Ming Yang

Publications and source records attributed to Ming Yang.

At least 127 records · Page 7Linked to original sources

arXiv2025

VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning

Large language models (LLMs) have demonstrated impressive performance on reasoning tasks, including mathematical reasoning. However, the current evaluation mostly focuses on carefully constructed benchmarks and neglects the consideration of real-world reasoning problems that present missing or contradictory conditions, known as ill-defined problems. To further study this problem, we develop a largescale benchmark called Problems with Missing and Contradictory conditions (PMC) containing over 5,000 validated ill-defined mathematical problems. Our preliminary experiments through PMC reveal two challenges about existing methods: (1) traditional methods exhibit a trade-off between solving accuracy and rejection capabilities, and (2) formal methods struggle with modeling complex problems. To address these challenges, We develop Variable-Constraint Search (VCSEARCH), a trainingfree framework that leverages formal language to detect ill-defined problems, where a variableconstraint pair search strategy is incorporated to improve the modeling capability of formal language. Extensive experiments demonstrate that VCSEARCH improves the accuracy of identifying unsolvable problems by at least 12% across different LLMs, thus achieving stronger robust mathematical reasoning ability.

cs.AI↗

arXiv2025

HAMMER: Hamiltonian Curiosity Augmented Large Language Model Reinforcement

Recent curriculum reinforcement learning for large language models (LLMs) typically rely on difficulty-based annotations for data filtering and ordering. However, such methods suffer from local optimization, where continual training on simple samples in the early steps can cause the policy to lose its exploration. We propose a novel schema, namely Hamiltonian curiosity augmented large language model reinforcement (HAMMER), that transfers diversity metrics, commonly used in dataset evaluation, into the dynamic reinforcement learning procedure, where training samples are ordered via a minimum-semantic Hamiltonian path making the initial training retrain more exploration. From a theoretical perspective of generalization bounds, diversity-driven ordering facilitates stable convergence. Empirical evaluations indicate that HAMMER stimulates model "curiosity" and consistently achieves a 3% to 4% average accuracy gain across diverse inference benchmark.

cs.LG↗

arXiv2025

Bench-RNR: Dataset for Benchmarking Repetitive and Non-repetitive Scanning LiDAR for Infrastructure-based Vehicle Localization

Vehicle localization using roadside LiDARs can provide centimeter-level accuracy for cloud-controlled vehicles while simultaneously serving multiple vehicles, enhanc-ing safety and efficiency. While most existing studies rely on repetitive scanning LiDARs, non-repetitive scanning LiDAR offers advantages such as eliminating blind zones and being more cost-effective. However, its application in roadside perception and localization remains limited. To address this, we present a dataset for infrastructure-based vehicle localization, with data collected from both repetitive and non-repetitive scanning LiDARs, in order to benchmark the performance of different LiDAR scanning patterns. The dataset contains 5,445 frames of point clouds across eight vehicle trajectory sequences, with diverse trajectory types. Our experiments establish base-lines for infrastructure-based vehicle localization and compare the performance of these methods using both non-repetitive and repetitive scanning LiDARs. This work offers valuable insights for selecting the most suitable LiDAR scanning pattern for infrastruc-ture-based vehicle localization. Our dataset is a signifi-cant contribution to the scientific community, supporting advancements in infrastructure-based perception and vehicle localization. The dataset and source code are publicly available at: https://github.com/sjtu-cyberc3/BenchRNR.

cs.RO↗

arXiv2025

Observatory Science with eXTP

Scheduled for launch in 2030, the enhanced X-ray Timing and Polarization (eXTP) telescope is a Chinese space-based mission aimed at studying extreme conditions and phenomena in astrophysics. eXTP will feature three main payloads: Spectroscopy Focusing Arrays (SFAs), Polarimetry Focusing Arrays (PFAs), and a Wide-field Camera (W2C). This white paper outlines observatory science, incorporating key scientific advances and instrumental changes since the publication of the previous white paper [1]. We will discuss perspectives of eXTP on the research domains of flare stars, supernova remnants, pulsar wind nebulae, cataclysmic variables, X-ray binaries, ultraluminous X-ray sources, AGN, and pulsar-based positioning and timekeeping.

astro-ph.IM↗

arXiv2025

Gravitational-wave inference at GPU speed: A bilby-like nested sampling kernel within blackjax-ns

We present a GPU-accelerated implementation of the gravitational-wave Bayesian inference pipeline for parameter estimation and model comparison. Specifically, we implement the `acceptance-walk' sampling method, a cornerstone algorithm for gravitational-wave inference within the bilby and dynesty framework. By integrating this trusted kernel with the vectorized blackjax-ns framework, we achieve typical speedups of 20-40x for aligned spin binary black hole analyses, while recovering posteriors and evidences that are statistically identical to the original CPU implementation. This faithful re-implementation of a community-standard algorithm establishes a foundational benchmark for gravitational-wave inference. It quantifies the performance gains attributable solely to the architectural shift to GPUs, creating a vital reference against which future parallel sampling algorithms can be rigorously assessed. This allows for a clear distinction between algorithmic innovation and the inherent speedup from hardware. Our work provides a validated community tool for performing GPU-accelerated nested sampling in gravitational-wave data analyses.

gr-qc↗

arXiv2025

From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots

Achieving general agile whole-body control on humanoid robots remains a major challenge due to diverse motion demands and data conflicts. While existing frameworks excel in training single motion-specific policies, they struggle to generalize across highly varied behaviors due to conflicting control requirements and mismatched data distributions. In this work, we propose BumbleBee (BB), an expert-generalist learning framework that combines motion clustering and sim-to-real adaptation to overcome these challenges. BB first leverages an autoencoder-based clustering method to group behaviorally similar motions using motion features and motion descriptions. Expert policies are then trained within each cluster and refined with real-world data through iterative delta action modeling to bridge the sim-to-real gap. Finally, these experts are distilled into a unified generalist controller that preserves agility and robustness across all motion types. Experiments on two simulations and a real humanoid robot demonstrate that BB achieves state-of-the-art general whole-body control, setting a new benchmark for agile, robust, and generalizable humanoid performance in the real world. The project webpage is available at https://beingbeyond.github.io/BumbleBee/.

cs.RO↗

arXiv2025

Time Tells All: Deanonymization of Blockchain RPC Users with Zero Transaction Fee (Extended Version)

Remote Procedure Call (RPC) services have become a primary gateway for users to access public blockchains. While they offer significant convenience, RPC services also introduce critical privacy challenges that remain insufficiently examined. Existing deanonymization attacks either do not apply to blockchain RPC users or incur costs like transaction fees assuming an active network eavesdropper. In this paper, we propose a novel deanonymization attack that can link an IP address of a RPC user to this user's blockchain pseudonym. Our analysis reveals a temporal correlation between the timestamps of transaction confirmations recorded on the public ledger and those of TCP packets sent by the victim when querying transaction status. We assume a strong passive adversary with access to network infrastructure, capable of monitoring traffic at network border routers or Internet exchange points. By monitoring network traffic and analyzing public ledgers, the attacker can link the IP address of the TCP packet to the pseudonym of the transaction initiator by exploiting the temporal correlation. This deanonymization attack incurs zero transaction fee. We mathematically model and analyze the attack method, perform large-scale measurements of blockchain ledgers, and conduct real-world attacks to validate the attack. Our attack achieves a high success rate of over 95% against normal RPC users on various blockchain networks, including Ethereum, Bitcoin and Solana.

cs.CR↗

arXiv2025

Embracing Aleatoric Uncertainty: Generating Diverse 3D Human Motion

Generating 3D human motions from text is a challenging yet valuable task. The key aspects of this task are ensuring text-motion consistency and achieving generation diversity. Although recent advancements have enabled the generation of precise and high-quality human motions from text, achieving diversity in the generated motions remains a significant challenge. In this paper, we aim to overcome the above challenge by designing a simple yet effective text-to-motion generation method, \textit{i.e.}, Diverse-T2M. Our method introduces uncertainty into the generation process, enabling the generation of highly diverse motions while preserving the semantic consistency of the text. Specifically, we propose a novel perspective that utilizes noise signals as carriers of diversity information in transformer-based methods, facilitating a explicit modeling of uncertainty. Moreover, we construct a latent space where text is projected into a continuous representation, instead of a rigid one-to-one mapping, and integrate a latent space sampler to introduce stochastic sampling into the generation process, thereby enhancing the diversity and uncertainty of the outputs. Our results on text-to-motion generation benchmark datasets~(HumanML3D and KIT-ML) demonstrate that our method significantly enhances diversity while maintaining state-of-the-art performance in text consistency.

cs.CV↗

arXiv2025

LumiSculpt: Enabling Consistent Portrait Lighting in Video Generation

Lighting plays a pivotal role in ensuring the naturalness and aesthetic quality of video generation. However, the impact of lighting is deeply coupled with other factors of videos, e.g., objects and scenes. Thus, it remains challenging to disentangle and model coherent lighting conditions independently, limiting the flexibility to control lighting in video generation. In this paper, inspired by the established controllable T2I models, we propose LumiSculpt, which enables precise and consistent lighting control in T2V generation models. LumiSculpt equips the video generation with new interactive capabilities, allowing the input of reference image sequences with customized lighting conditions. Furthermore, the core learnable plug-and-play module of LumiSculpt facilitates direct control over the intensity, position and trajectory of an assumed light source in video diffusion models. To effectively train LumiSculpt and address the issue of insufficient lighting data, we construct LumiHuman, a new lightweight and flexible dataset for portrait lighting of images and videos. Experimental results demonstrate that LumiSculpt achieves precise and high-quality lighting control in video generation. The analysis demonstrates the flexibility of LumiHuman.

cs.CV↗

arXiv2025

Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination

Cross-client data heterogeneity in federated learning induces biases that impede unbiased consensus condensation and the complementary fusion of generalization- and personalization-oriented knowledge. While existing approaches mitigate heterogeneity through model decoupling and representation center loss, they often rely on static and restricted metrics to evaluate local knowledge and adopt global alignment too rigidly, leading to consensus distortion and diminished model adaptability. To address these limitations, we propose FedMate, a method that implements bilateral optimization: On the server side, we construct a dynamic global prototype, with aggregation weights calibrated by holistic integration of sample size, current parameters, and future prediction; a category-wise classifier is then fine-tuned using this prototype to preserve global consistency. On the client side, we introduce complementary classification fusion to enable merit-based discrimination training and incorporate cost-aware feature transmission to balance model performance and communication efficiency. Experiments on five datasets of varying complexity demonstrate that FedMate outperforms state-of-the-art methods in harmonizing generalization and adaptation. Additionally, semantic segmentation experiments on autonomous driving datasets validate the method's real-world scalability.

cs.LG↗

arXiv2025

Social Debiasing for Fair Multi-modal LLMs

Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities. However, these models often inherit deep-rooted social biases from their training data, leading to uncomfortable responses with respect to attributes such as race and gender. This paper addresses the issue of social biases in MLLMs by i) introducing a comprehensive counterfactual dataset with multiple social concepts (CMSC), which complements existing datasets by providing 18 diverse and balanced social concepts; and ii) proposing a counter-stereotype debiasing (CSD) strategy that mitigates social biases in MLLMs by leveraging the opposites of prevalent stereotypes. CSD incorporates both a novel bias-aware data sampling method and a loss rescaling method, enabling the model to effectively reduce biases. We conduct extensive experiments with four prevalent MLLM architectures. The results demonstrate the advantage of the CMSC dataset and the edge of CSD strategy in reducing social biases compared to existing competing methods, without compromising the overall performance on general multi-modal reasoning benchmarks.

cs.CL↗

arXiv2025

MultiPark: Multimodal Parking Transformer with Next-Segment Prediction

Parking accurately and safely in highly constrained spaces remains a critical challenge. Unlike structured driving environments, parking requires executing complex maneuvers such as frequent gear shifts and steering saturation. Recent attempts to employ imitation learning (IL) for parking have achieved promising results. However, existing works ignore the multimodal nature of parking behavior in lane-free open space, failing to derive multiple plausible solutions under the same situation. Notably, IL-based methods encompass inherent causal confusion, so enabling a neural network to generalize across diverse parking scenarios is particularly difficult. To address these challenges, we propose MultiPark, an autoregressive transformer for multimodal parking. To handle paths filled with abrupt turning points, we introduce a data-efficient next-segment prediction paradigm, enabling spatial generalization and temporal extrapolation. Furthermore, we design learnable parking queries factorized into gear, longitudinal, and lateral components, parallelly decoding diverse parking behaviors. To mitigate causal confusion in IL, our method employs target-centric pose and ego-centric collision as outcome-oriented loss across all modalities beyond pure imitation loss. Evaluations on real-world datasets demonstrate that MultiPark achieves state-of-the-art performance across various scenarios. We deploy MultiPark on a production vehicle, further confirming our approach's robustness in real-world parking environments.

cs.RO↗

arXiv2025

CasP: Improving Semi-Dense Feature Matching Pipeline Leveraging Cascaded Correspondence Priors for Guidance

Semi-dense feature matching methods have shown strong performance in challenging scenarios. However, the existing pipeline relies on a global search across the entire feature map to establish coarse matches, limiting further improvements in accuracy and efficiency. Motivated by this limitation, we propose a novel pipeline, CasP, which leverages cascaded correspondence priors for guidance. Specifically, the matching stage is decomposed into two progressive phases, bridged by a region-based selective cross-attention mechanism designed to enhance feature discriminability. In the second phase, one-to-one matches are determined by restricting the search range to the one-to-many prior areas identified in the first phase. Additionally, this pipeline benefits from incorporating high-level features, which helps reduce the computational costs of low-level feature extraction. The acceleration gains of CasP increase with higher resolution, and our lite model achieves a speedup of $\sim2.2\times$ at a resolution of 1152 compared to the most efficient method, ELoFTR. Furthermore, extensive experiments demonstrate its superiority in geometric estimation, particularly with impressive cross-domain generalization. These advantages highlight its potential for latency-sensitive and high-robustness applications, such as SLAM and UAV systems. Code is available at https://github.com/pq-chen/CasP.

cs.CV↗

arXiv2025

Versatile Multimodal Controls for Expressive Talking Human Animation

In filmmaking, directors typically allow actors to perform freely based on the script before providing specific guidance on how to present key actions. AI-generated content faces similar requirements, where users not only need automatic generation of lip synchronization and basic gestures from audio input but also desire semantically accurate and expressive body movement that can be ``directly guided'' through text descriptions. Therefore, we present VersaAnimator, a versatile framework that synthesizes expressive talking human videos from arbitrary portrait images. Specifically, we design a motion generator that produces basic rhythmic movements from audio input and supports text-prompt control for specific actions. The generated whole-body 3D motion tokens can animate portraits of various scales, producing talking heads, half-body gestures and even leg movements for whole-body images. Besides, we introduce a multi-modal controlled video diffusion that generates photorealistic videos, where speech signals govern lip synchronization, facial expressions, and head motions while body movements are guided by the 2D poses. Furthermore, we introduce a token2pose translator to smoothly map 3D motion tokens to 2D pose sequences. This design mitigates the stiffness resulting from direct 3D to 2D conversion and enhances the details of the generated body movements. Extensive experiments shows that VersaAnimator synthesizes lip-synced and identity-preserving videos while generating expressive and semantically meaningful whole-body motions.

cs.CV↗

arXiv2025

Wheeler-DeWitt wavefunctions for 5d BKL dynamics, automorphic L-functions and complex primon gases

The near-singularity BKL dynamics of five dimensional gravity and supergravity (and also an extended four-dimensional supergravity) is known to be given by the billiard problem of a particle within a fundamental domain of the Bianchi groups $PSL(2,{\mathcal O}) \subset PSL(2,\mathbb{C})$, acting on $\mathbb{H}_3$. Here ${\mathcal O}$ are the Gaussian or Eisenstein integers, which define a square or triangular lattice in $\mathbb{C}$. The Wheeler-DeWitt wavefunctions near the singularity are, correspondingly, automorphic Maass forms of $PSL(2,{\mathcal O})$. We show how these wavefunctions are associated to certain $L$-functions evaluated along their critical axis. Each of these $L$-functions admits an Euler product representation over the complex primes ${\mathcal{P}}_{\mathcal O} \subset {\mathcal O}$. From this fact we write the $L$-function as the trace over an auxiliary Hilbert space of charged harmonic oscillators, labeled by the complex primes ${\mathcal{P}}_{\mathcal O}$. In this way we have constructed a 'dual' primon gas partition function for the wavefunction of the universe close to a five dimensional cosmological singularity.

hep-th↗

arXiv2025

Video Virtual Try-on with Conditional Diffusion Transformer Inpainter

Video virtual try-on aims to naturally fit a garment to a target person in consecutive video frames. It is a challenging task, on the one hand, the output video should be in good spatial-temporal consistency, on the other hand, the details of the given garment need to be preserved well in all the frames. Naively using image-based try-on methods frame by frame can get poor results due to severe inconsistency. Recent diffusion-based video try-on methods, though very few, happen to coincide with a similar solution: inserting temporal attention into image-based try-on model to adapt it for video try-on task, which have shown improvements but there still exist inconsistency problems. In this paper, we propose ViTI (Video Try-on Inpainter), formulate and implement video virtual try-on as a conditional video inpainting task, which is different from previous methods. In this way, we start with a video generation problem instead of an image-based try-on problem, which from the beginning has a better spatial-temporal consistency. Specifically, at first we build a video inpainting framework based on Diffusion Transformer with full 3D spatial-temporal attention, and then we progressively adapt it for video garment inpainting, with a collection of masking strategies and multi-stage training. After these steps, the model can inpaint the masked garment area with appropriate garment pixels according to the prompt with good spatial-temporal consistency. Finally, as other try-on methods, garment condition is added to the model to make sure the inpainted garment appearance and details are as expected. Both quantitative and qualitative experimental results show that ViTI is superior to previous works.

cs.CV↗

arXiv2025

Reversing Flow for Image Restoration

Image restoration aims to recover high-quality (HQ) images from degraded low-quality (LQ) ones by reversing the effects of degradation. Existing generative models for image restoration, including diffusion and score-based models, often treat the degradation process as a stochastic transformation, which introduces inefficiency and complexity. In this work, we propose ResFlow, a novel image restoration framework that models the degradation process as a deterministic path using continuous normalizing flows. ResFlow augments the degradation process with an auxiliary process that disambiguates the uncertainty in HQ prediction to enable reversible modeling of the degradation process. ResFlow adopts entropy-preserving flow paths and learns the augmented degradation flow by matching the velocity field. ResFlow significantly improves the performance and speed of image restoration, completing the task in fewer than four sampling steps. Extensive experiments demonstrate that ResFlow achieves state-of-the-art results across various image restoration benchmarks, offering a practical and efficient solution for real-world applications.

cs.CV↗

arXiv2025

Algal Optics

Nearly a decade ago it was discovered that the spherical cell body of the alga $Chlamydomonas~reinhardtii$ can act as a lens to concentrate incoming light onto the cell's membrane-bound photoreceptor and thereby affect phototaxis. Since many nearly transparent cells in marine environments have complex, often non-axisymmetric shapes, this observation raises fundamental, yet little-explored questions in biological optics about light refraction by the bodies of microorganisms. There are two distinct contexts for such questions: the $absorption$ problem for $incoming$ light, typified by photosynthetic activity taking place in the chloroplasts of green algae, and the $emission$ problem for $outgoing$ light, where the paradigm is bioluminescence emitted from scintillons within dinoflagellates. Here we examine both of these aspects of ``algal optics" in the special case where the absorption or emission is localized in structures that are small relative to the overall organism size, taking into account both refraction and reflections at the cell-water boundary. Analytical and numerical results are developed for the distribution of light intensities inside and outside the body, and we establish certain duality relationships that connect the incoming and outgoing problems. For strongly non-spherical shapes we find lensing effects that may have implications for photosynthetic activity and for the angular distribution of light emitted during bioluminescent flashes.

cond-mat.soft↗