arXiv subjects

Hong Liu

Publications and source records attributed to Hong Liu.

At least 91 records · Page 5Linked to original sources

arXiv2026

Cross-Modal Retrieval for Motion and Text via DropTriple Loss

Cross-modal retrieval of image-text and video-text is a prominent research area in computer vision and natural language processing. However, there has been insufficient attention given to cross-modal retrieval between human motion and text, despite its wide-ranging applicability. To address this gap, we utilize a concise yet effective dual-unimodal transformer encoder for tackling this task. Recognizing that overlapping atomic actions in different human motion sequences can lead to semantic conflicts between samples, we explore a novel triplet loss function called DropTriple Loss. This loss function discards false negative samples from the negative sample set and focuses on mining remaining genuinely hard negative samples for triplet training, thereby reducing violations they cause. We evaluate our model and approach on the HumanML3D and KIT Motion-Language datasets. On the latest HumanML3D dataset, we achieve a recall of 62.9% for motion retrieval and 71.5% for text retrieval (both based on R@10). The source code for our approach is publicly available at https://github.com/eanson023/rehamot.

cs.CV↗

arXiv2026

A Unified Evaluation Framework for Multi-Annotator Tendency Learning

Recent works have emerged in multi-annotator learning that shift focus from Consensus-oriented Learning (CoL), which aggregates multiple annotations into a single ground-truth prediction, to Individual Tendency Learning (ITL), which models annotator-specific labeling behavior patterns (i.e., tendency) to provide explanation analysis for understanding annotator decisions. However, no evaluation framework currently exists to assess whether ITL methods truly capture individual tendencies and provide meaningful behavioral explanations. To address this gap, we propose the first unified evaluation framework with two novel metrics: (1) Difference of Inter-annotator Consistency (DIC) quantifies how well models capture annotator tendencies by comparing predicted inter-annotator similarity structures with ground-truth; (2) Behavior Alignment Explainability (BAE) evaluates how well model explanations reflect annotator behavior and decision relevance by aligning explainability-derived with ground-truth labeling similarity structures via Multidimensional Scaling (MDS). Extensive experiments validate the effectiveness of our proposed evaluation framework.

cs.LG↗

arXiv2026

PA-MIL: Phenotype-Aware Multiple Instance Learning Guided by Language Prompting and Genotype-to-Phenotype Relationships

Deep learning has been extensively researched in the analysis of pathology whole-slide images (WSIs). However, most existing methods are limited to providing prediction interpretability by locating the model's salient areas in a post-hoc manner, failing to offer more reliable and accountable explanations. In this work, we propose Phenotype-Aware Multiple Instance Learning (PA-MIL), a novel ante-hoc interpretable framework that identifies cancer-related phenotypes from WSIs and utilizes them for cancer subtyping. To facilitate PA-MIL in learning phenotype-aware features, we 1) construct a phenotype knowledge base containing cancer-related phenotypes and their associated genotypes. 2) utilize the morphological descriptions of phenotypes as language prompting to aggregate phenotype-related features. 3) devise the Genotype-to-Phenotype Neural Network (GP-NN) grounded in genotype-to-phenotype relationships, which provides multi-level guidance for PA-MIL. Experimental results on multiple datasets demonstrate that PA-MIL achieves competitive performance compared to existing MIL methods while offering improved interpretability. PA-MIL leverages phenotype saliency as evidence and, using a linear classifier, achieves competitive results compared to state-of-the-art methods. Additionally, we thoroughly analyze the genotype-phenotype relationships, as well as cohort-level and case-level interpretability, demonstrating the reliability and accountability of PA-MIL.

cs.LG↗

arXiv2025

Geese achieve stationary takeoff via synergistic wing kinematics and enhanced aerodynamics

Stationary take-off, without a running start or elevated descent, requires substantial aerodynamic forces to overcome weight, particularly for large birds such as geese exceeding 2 kg. However, the complex wing motion and high-Reynolds-number (Re $\approx$$10^5$) flow dynamics challenge conventional expectations of avian flight aerodynamics, rendering this mechanism elusive. Analyzing 578 stationary take-offs from seven geese (\textit{Anser cygnoides}) and applying Principal Component Analysis (PCA), we reveal that the complex wing kinematics collapse onto a low-dimensional manifold dominated by two synergies: a Stroke Synergy responsible for fundamental rhythmic stroke, and a Morphing Synergy governing spanwise geometry. This modular control strategy orchestrates a stereotyped wing kinematics featuring an accelerated translational downstroke and a rapid tip-reversal upstroke. By integrating wing kinematic analysis with the mass distribution of the geese, we quantified the aerodynamic forces and found that entirely positive lift and thrust are generated throughout the motion cycle. The enhanced aerodynamic performance of geese takeoff results from three principal mechanisms. During the downstroke, significant lift generated from wing acceleration is predicted by the quasi-steady framework. Flow visualization reveals that wake capture further enhances the lift generation in downstroke by orienting the position of wake vortices. During the upstroke, the distal wing performs a rapid pitching motion and generates a substantial thrust, the vertical component of which contributes significantly to weight support.

physics.flu-dyn↗

arXiv2025

Dual-Model Framework for CHIKV Transmission Modeling: ODE and Petri Net Analysis of the 2025 Foshan Outbreak

This study constructs a dual-model framework integrating Ordinary Differential Equations (ODE) and Petri Nets (PN) to analyze the 2025 Chikungunya outbreak in Foshan City, China. We employ SEICR compartmental modeling to compare two distinct approaches under identical epidemiological scenarios and evaluate intervention effectiveness through three-phase fitting protocols. Both models demonstrate excellent accuracy with MAE of 18.77-18.91 cases and RMSE of 36.52-36.54 cases. Models predicted epidemic peaks at day 32 (406 cases), 3 days earlier than observed (day 35, 432 cases), with 6.0% peak value error. Reproduction number analysis revealed initial R0 of 14.67 (ODE)/13.90 (PN), with effective reproduction numbers decreasing through intervention phases: 7.85/7.86 after Phase 1, 7.59/7.56 after Phase 2, and 0.059 in Phase 3, achieving transmission blockade. Sensitivity analysis showed recovery rate) as the most sensitive parameter (Sobol index 0.9672), explaining 96.72% of R0 variation. This study presents the first systematic ODE-Petri Net comparison, providing a novel dual-model framework for vector-borne disease modeling with significant theoretical and practical value for epidemic control strategy formulation.

q-bio.PE↗

arXiv2025

Synthetic bootstrapped pretraining

We introduce Synthetic Bootstrapped Pretraining (SBP), a language model (LM) pretraining procedure that first learns a model of relations between documents from the pretraining dataset and then leverages it to synthesize a vast new corpus for joint training. While the standard pretraining teaches LMs to learn causal correlations among tokens within a single document, it is not designed to efficiently model the rich, learnable inter-document correlations that can potentially lead to better performance. We validate SBP by designing a compute-matched pretraining setup and pretrain a 3B-parameter and a 6B-parameter model on up to 1T tokens from scratch. We find SBP consistently improves upon a strong repetition baseline and delivers up to 60% of performance improvement attainable by an oracle upper bound with access to 20x more unique data. Qualitative analysis reveals that the synthesized documents go beyond mere paraphrases -- SBP first abstracts a core concept from the seed material and then crafts a new narration on top of it. Besides strong empirical performance, SBP admits a natural Bayesian interpretation: the synthesizer implicitly learns to abstract the latent concepts shared between related documents.

cs.CL↗

arXiv2025

Listening Between the Frames: Bridging Temporal Gaps in Large Audio-Language Models

Recent Large Audio-Language Models (LALMs) exhibit impressive capabilities in understanding audio content for conversational QA tasks. However, these models struggle to accurately understand timestamps for temporal localization (e.g., Temporal Audio Grounding) and are restricted to short audio perception, leading to constrained capabilities on fine-grained tasks. We identify three key aspects that limit their temporal localization and long audio understanding: (i) timestamp representation, (ii) architecture, and (iii) data. To address this, we introduce TimeAudio, a novel method that empowers LALMs to connect their understanding of audio content with precise temporal perception. Specifically, we incorporate unique temporal markers to improve time-sensitive reasoning and apply an absolute time-aware encoding that explicitly grounds the acoustic features with absolute time information. Moreover, to achieve end-to-end long audio understanding, we introduce a segment-level token merging module to substantially reduce audio token redundancy and enhance the efficiency of information extraction. Due to the lack of suitable datasets and evaluation metrics, we consolidate existing audio datasets into a new dataset focused on temporal tasks and establish a series of metrics to evaluate the fine-grained performance. Evaluations show strong performance across a variety of fine-grained tasks, such as dense captioning, temporal grounding, and timeline speech summarization, demonstrating TimeAudio's robust temporal localization and reasoning capabilities.

cs.SD↗

arXiv2025

Contribution-Guided Asymmetric Learning for Robust Multimodal Fusion under Imbalance and Noise

Multimodal learning faces two major challenges: modality imbalance and data noise, which significantly affect the robustness and generalization ability of models. Existing methods achieve modality balance by suppressing dominant modalities, but they neglect the inherent differences in the information value between modalities, potentially leading to convergence to suboptimal solutions. This paper proposes an innovative modality compression paradigm, Contribution-Guided Asymmetric Learning (CAL), which aims to enhance the contribution of high-contribution modalities while compressing weak modalities to increase their contribution, allowing both to improve the performance of multimodal information fusion. CAL is based on a modality contribution metric W^m combining the information quantity I(m) and confidence D(m), and it designs an asymmetric gradient acceleration mechanism and a contribution-aware Asymmetric Information Bottleneck (AIB) compression mechanism. The former accelerates the gradient update of modalities, while the latter dynamically compresses the noise of low-contribution modalities. On five benchmark datasets, including emotion recognition, scene recognition, and event localization tasks, CAL has shown outstanding performance in imbalanced fusion tasks and noise robustness tests. On CREMA-D, KS, and AVE, CAL achieves 79.30%, 74.82%, and 74.21% accuracy, significantly outperforming the existing state-of-the-art model ARL. In high-noise robustness tests, CAL also achieved leading performance under various attack strategies on the MVSA-Single and NYUD2 datasets. These results validate the significant advantages of CAL in modality imbalance and noise interference. CAL, as a flexible and efficient framework, is easy to transfer to other tasks and has broad adaptability and potential application prospects.

cs.MM↗

arXiv2025

Fooling the Censor: Going beyond inner horizons with the OPE

The analytic structure of holographic correlation functions at finite temperature contains information about curvature singularities of black holes in AdS. We compute the Operator Product Expansion (OPE) coefficients of the holographic two-point function of scalar operators at finite temperature and finite chemical potential. We show that the stress-tensor and current (T+J) sector of the OPE contains a singularity in the complex time plane at a location that can be identified with the time-shift of a bouncing geodesic in the charged black hole geometry: The geodesic starts at a boundary of a charged black hole in AdS, bounces off the timelike singularity, before returning to a different asymptotic boundary on the same side of the Penrose diagram. We show that the singularity in the T+J sector is smooth across the point where black hole becomes extremal, indicating that the analytic properties of holographic correlators could potentially probe naked singularities.

hep-th↗

arXiv2025

HDCNet: A Hybrid Depth Completion Network for Grasping Transparent and Reflective Objects

Depth perception of transparent and reflective objects has long been a critical challenge in robotic manipulation.Conventional depth sensors often fail to provide reliable measurements on such surfaces, limiting the performance of robots in perception and grasping tasks. To address this issue, we propose a novel depth completion network,HDCNet,which integrates the complementary strengths of Transformer,CNN and Mamba architectures.Specifically,the encoder is designed as a dual-branch Transformer-CNN framework to extract modality-specific features. At the shallow layers of the encoder, we introduce a lightweight multimodal fusion module to effectively integrate low-level features. At the network bottleneck,a Transformer-Mamba hybrid fusion module is developed to achieve deep integration of high-level semantic and global contextual information, significantly enhancing depth completion accuracy and robustness. Extensive evaluations on multiple public datasets demonstrate that HDCNet achieves state-of-the-art(SOTA) performance in depth completion tasks.Furthermore,robotic grasping experiments show that HDCNet substantially improves grasp success rates for transparent and reflective objects,achieving up to a 60% increase.

cs.RO↗

arXiv2025

Introducing LongCat-Flash-Thinking: A Technical Report

We present LongCat-Flash-Thinking, an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model. Its advanced capabilities are cultivated through a meticulously crafted training process, beginning with long Chain-of-Thought (CoT) data cold-start and culminating in large-scale Reinforcement Learning (RL). We first employ a well-designed cold-start training strategy, which significantly enhances the reasoning potential and equips the model with specialized skills in both formal and agentic reasoning. Then, a core innovation is our domain-parallel training scheme, which decouples optimization across distinct domains (e.g., STEM, Code, Agentic) and subsequently fuses the resulting expert models into a single, nearly Pareto-optimal model. This entire process is powered by our Dynamic ORchestration for Asynchronous rollout (DORA) system, a large-scale RL framework that delivers a greater than threefold training speedup over synchronous methods on tens of thousands of accelerators. As a result, LongCat-Flash-Thinking achieves state-of-the-art performance among open-source models on a suite of complex reasoning tasks. The model exhibits exceptional efficiency in agentic reasoning, reducing average token consumption by 64.5% (from 19, 653 to 6, 965) on AIME-25, without degrading task accuracy. We release LongCat-Flash-Thinking to promote further advances in reasoning systems and agentic AI research.

cs.AI↗

arXiv2025

Bipartite Turán problems via graph gluing

For graphs $H_1$ and $H_2$, if we glue them by identifying a given pair of vertices $u \in V(H_1)$ and $v \in V(H_2)$, what is the extremal number of the resulting graph $H_1^u \odot H_2^v$? In this paper, we study this problem and show that interestingly it is equivalent to an old question of Erdős and Simonovits on the Zarankiewicz problem. When $H_1, H_2$ are copies of a same bipartite graph $H$ and $u, v$ come from a same part, we prove that $\operatorname{ex}(n, H_1^u \odot H_2^v) = Θ\bigl( \operatorname{ex}(n, H) \bigr)$. As a corollary, we provide a short self-contained disproof of a conjecture of Erdős, which was recently disproved by Janzer.

math.CO↗

arXiv2025

MoSa: Motion Generation with Scalable Autoregressive Modeling

We introduce MoSa, a novel hierarchical motion generation framework for text-driven 3D human motion generation that enhances the Vector Quantization-guided Generative Transformers (VQ-GT) paradigm through a coarse-to-fine scalable generation process. In MoSa, we propose a Multi-scale Token Preservation Strategy (MTPS) integrated into a hierarchical residual vector quantization variational autoencoder (RQ-VAE). MTPS employs interpolation at each hierarchical quantization to effectively retain coarse-to-fine multi-scale tokens. With this, the generative transformer supports Scalable Autoregressive (SAR) modeling, which predicts scale tokens, unlike traditional methods that predict only one token at each step. Consequently, MoSa requires only 10 inference steps, matching the number of RQ-VAE quantization layers. To address potential reconstruction degradation from frequent interpolation, we propose CAQ-VAE, a lightweight yet expressive convolution-attention hybrid VQ-VAE. CAQ-VAE enhances residual block design and incorporates attention mechanisms to better capture global dependencies. Extensive experiments show that MoSa achieves state-of-the-art generation quality and efficiency, outperforming prior methods in both fidelity and speed. On the Motion-X dataset, MoSa achieves an FID of 0.06 (versus MoMask's 0.20) while reducing inference time by 27 percent. Moreover, MoSa generalizes well to downstream tasks such as motion editing, requiring no additional fine-tuning. The code is available at https://mosa-web.github.io/MoSa-web

cs.CV↗

arXiv2025

Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model

We present Ring-1T, the first open-source, state-of-the-art thinking model with a trillion-scale parameter. It features 1 trillion total parameters and activates approximately 50 billion per token. Training such models at a trillion-parameter scale introduces unprecedented challenges, including train-inference misalignment, inefficiencies in rollout processing, and bottlenecks in the RL system. To address these, we pioneer three interconnected innovations: (1) IcePop stabilizes RL training via token-level discrepancy masking and clipping, resolving instability from training-inference mismatches; (2) C3PO++ improves resource utilization for long rollouts under a token budget by dynamically partitioning them, thereby obtaining high time efficiency; and (3) ASystem, a high-performance RL framework designed to overcome the systemic bottlenecks that impede trillion-parameter model training. Ring-1T delivers breakthrough results across critical benchmarks: 93.4 on AIME-2025, 86.72 on HMMT-2025, 2088 on CodeForces, and 55.94 on ARC-AGI-1. Notably, it attains a silver medal-level result on the IMO-2025, underscoring its exceptional reasoning capabilities. By releasing the complete 1T parameter MoE model to the community, we provide the research community with direct access to cutting-edge reasoning capabilities. This contribution marks a significant milestone in democratizing large-scale reasoning intelligence and establishes a new baseline for open-source model performance.

cs.CL↗

arXiv2025

NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation

The widespread application of 3D human pose estimation (HPE) is limited by resource-constrained edge devices, requiring more efficient models. A key approach to enhancing efficiency involves designing networks based on the structural characteristics of input data. However, effectively utilizing the structural priors in human skeletal inputs remains challenging. To address this, we leverage both explicit and implicit spatio-temporal priors of the human body through innovative model design and a pre-training proxy task. First, we propose a Nano Human Topology Network (NanoHTNet), a tiny 3D HPE network with stacked Hierarchical Mixers to capture explicit features. Specifically, the spatial Hierarchical Mixer efficiently learns the human physical topology across multiple semantic levels, while the temporal Hierarchical Mixer with discrete cosine transform and low-pass filtering captures local instantaneous movements and global action coherence. Moreover, Efficient Temporal-Spatial Tokenization (ETST) is introduced to enhance spatio-temporal interaction and reduce computational complexity significantly. Second, PoseCLR is proposed as a general pre-training method based on contrastive learning for 3D HPE, aimed at extracting implicit representations of human topology. By aligning 2D poses from diverse viewpoints in the proxy task, PoseCLR aids 3D HPE encoders like NanoHTNet in more effectively capturing the high-dimensional features of the human body, leading to further performance improvements. Extensive experiments verify that NanoHTNet with PoseCLR outperforms other state-of-the-art methods in efficiency, making it ideal for deployment on edge devices like the Jetson Nano. Code and models are available at https://github.com/vefalun/NanoHTNet.

cs.CV↗

arXiv2025

Lectures on entanglement, von Neumann algebras, and emergence of spacetime

We review recent developments in the use of von Neumann algebras to analyze the entanglement structure of quantum gravity and the emergence of spacetime in the semi-classical limit. Von Neumann algebras provide a natural framework for describing quantum subsystems when standard tensor factorizations are unavailable, capturing both kinematic and dynamical aspects of entanglement. The first part of the review introduces the fundamentals of von Neumann algebras, including their classification, and explains how they can be applied to characterize entanglement. Topics covered include modular and half-sided modular flows and their role in the emergence of time, as well as the crossed-product construction of von Neumann algebras. The second part turns to applications in quantum gravity, including an algebraic formulation of AdS/CFT in the large-$N$ limit, the emergence of bulk spacetime structure through subregion-subalgebra duality, and an operator-algebraic perspective on gravitational entropy. It also discusses simple operator-algebraic models of quantum gravity, which provide concrete settings in which to explore these ideas. In addition, several original conceptual contributions are presented, including a diagnostic of firewalls and an algebraic formulation of entanglement islands. The review concludes with some speculative remarks on the mathematical structures underlying quantum gravity.

hep-th↗

arXiv2025

PANICL: Mitigating Over-Reliance on Single Prompt in Visual In-Context Learning

Visual In-Context Learning (VICL) uses input-output image pairs, referred to as in-context pairs (or examples), as prompts alongside query images to guide models in performing diverse vision tasks. However, VICL often suffers from over-reliance on a single in-context pair, which can lead to biased and unstable predictions. We introduce PAtch-based $k$-Nearest neighbor visual In-Context Learning (PANICL), a general training-free framework that mitigates this issue by leveraging multiple in-context pairs. PANICL smooths assignment scores across pairs, reducing bias without requiring additional training. Extensive experiments on a variety of tasks, including foreground segmentation, single object detection, colorization, multi-object segmentation, and keypoint detection, demonstrate consistent improvements over strong baselines. Moreover, PANICL exhibits strong robustness to domain shifts, including dataset-level shift (e.g., from COCO to Pascal) and label-space shift (e.g., FSS-1000), and generalizes well to other VICL models such as SegGPT, Painter, and LVM, highlighting its versatility and broad applicability.

cs.CV↗

arXiv2025

Topological Catenation-induced Pore Size in 2D Olympic Network

Assemblies of ring DNA and proteins, such as kinetoplast DNA (kDNA) and the chainmail-like network of the HK97 bacteriophage capsid, form "Olympic" topologies that govern the dynamics of gene-regulatory proteins, cellular metabolites, and viral genomes. Yet the pore sizes that control transport and diffusion in these topologically linked networks remain poorly quantified. Here, using coarse-grained simulations of idealized square (SQR) and hexagonal (HEX) lattice catenated two-dimensional Olympic networks, we measure pore size as the radius of the largest rigid tracer that can pass through an aperture and delineate how backbone bending stiffness and topological tension regulate this structure. We identify two competing regulators: (i) ring entropic elasticity, which enlarges pores at low stiffness, and (ii) ring rotation angle, which reduces pore size at high stiffness. Their competition yields bimodal pore size distributions over a defined parameter range. Network geometry further modulates spatial correlations in pore size and the pore size autocorrelation time, predicting distinct propagation of perturbations in isostatic (SQR) versus hypostatic (HEX) architectures. These results provide testable predictions for enzyme diffusion kinetics and cargo release in natural or synthetic catenane DNA networks and mechanically interlocked capsid proteins, and offer a theoretical framework for interpreting FRAP (fluorescence recovery after photobleaching) and SMT (single-molecule tracking) measurements in topologically catenated biopolymer networks.

cond-mat.soft↗