arXiv subjects

Chang Liu

Publications and source records attributed to Chang Liu.

At least 343 records · Page 19Linked to original sources

arXiv2025

EmoDiffTalk:Emotion-aware Diffusion for Editable 3D Gaussian Talking Head

Recent photo-realistic 3D talking head via 3D Gaussian Splatting still has significant shortcoming in emotional expression manipulation, especially for fine-grained and expansive dynamics emotional editing using multi-modal control. This paper introduces a new editable 3D Gaussian talking head, i.e. EmoDiffTalk. Our key idea is a novel Emotion-aware Gaussian Diffusion, which includes an action unit (AU) prompt Gaussian diffusion process for fine-grained facial animator, and moreover an accurate text-to-AU emotion controller to provide accurate and expansive dynamic emotional editing using text input. Experiments on public EmoTalk3D and RenderMe-360 datasets demonstrate superior emotional subtlety, lip-sync fidelity, and controllability of our EmoDiffTalk over previous works, establishing a principled pathway toward high-quality, diffusion-driven, multimodal editable 3D talking-head synthesis. To our best knowledge, our EmoDiffTalk is one of the first few 3D Gaussian Splatting talking-head generation framework, especially supporting continuous, multimodal emotional editing within the AU-based expression space.

cs.CV↗

arXiv2025

Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding

The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and describe complex visual content. However, applying these models to long-video understanding remains computationally intensive. Dense frame encoding generates excessive visual tokens, leading to high memory consumption, redundant computation, and limited scalability in real-world applications. This inefficiency highlights a key limitation of the traditional process-then-reason paradigm, which analyzes visual streams exhaustively before semantic reasoning. To address this challenge, we introduce Video-QTR (Query-Driven Temporal Reasoning), a lightweight framework that redefines video comprehension as a query-guided reasoning process. Instead of encoding every frame, Video-QTR dynamically allocates perceptual resources based on the semantic intent of the query, creating an adaptive feedback loop between reasoning and perception. Extensive experiments across five benchmarks: MSVD-QA, Activity Net-QA, Movie Chat, and Video MME demonstrate that Video-QTR achieves state-of-the-art performance while reducing input frame consumption by up to 73%. These results confirm that query-driven temporal reasoning provides an efficient and scalable solution for video understanding.

cs.CV↗

arXiv2025

Exploiting Supply Chain Interdependencies for Stock Return Prediction: A Full-State Graph Convolutional LSTM

Stock return prediction is fundamental to financial decision-making, yet traditional time series models fail to capture the complex interdependencies between companies in modern markets. We propose the Full-State Graph Convolutional LSTM (FS-GCLSTM), a novel temporal graph neural network that incorporates value-chain relationships to enhance stock return forecasting. Our approach features two key innovations: First, we represent inter-firm dependencies through value-chain networks, where nodes correspond to companies and edges capture supplier-customer relationships, enabling the model to leverage information beyond historical price data. Second, FS-GCLSTM applies graph convolutions to all LSTM components - current input features, previous hidden states, and cell states - ensuring that spatial information from the value-chain network influences every aspect of the temporal update mechanism. We evaluate FS-GCLSTM on Eurostoxx 600 and S&P 500 datasets using LSEG value-chain data. While not achieving the lowest traditional prediction errors, FS-GCLSTM consistently delivers superior portfolio performance, attaining the highest annualized returns, Sharpe ratios, and Sortino ratios across both markets. Performance gains are more pronounced in the denser Eurostoxx 600 network, and robustness tests confirm stability across different input sequence lengths, demonstrating the practical value of integrating value-chain data with temporal graph neural networks.

q-fin.ST↗

arXiv2025

Unveiling Hedge Funds: Topic Modeling and Sentiment Correlation with Fund Performance

The hedge fund industry presents significant challenges for investors due to its opacity and limited disclosure requirements. This pioneering study introduces two major innovations in financial text analysis. First, we apply topic modeling to hedge fund documents-an unexplored domain for automated text analysis-using a unique dataset of over 35,000 documents from 1,125 hedge fund managers. We compared three state-of-the-art methods: Latent Dirichlet Allocation (LDA), Top2Vec, and BERTopic. Our findings reveal that LDA with 20 topics produces the most interpretable results for human users and demonstrates higher robustness in topic assignments when the number of topics varies, while Top2Vec shows superior classification performance. Second, we establish a novel quantitative framework linking document sentiment to fund performance, transforming qualitative information traditionally requiring expert interpretation into systematic investment signals. In sentiment analysis, contrary to expectations, the general-purpose DistilBERT outperforms the finance-specific FinBERT in generating sentiment scores, demonstrating superior adaptability to diverse linguistic patterns found in hedge fund documents that extend beyond specialized financial news text. Furthermore, sentiment scores derived using DistilBERT in combination with Top2Vec show stronger correlations with subsequent fund performance compared to other model combinations. These results demonstrate that automated topic modeling and sentiment analysis can effectively process hedge fund documents, providing investors with new data-driven decision support tools.

q-fin.CP↗

arXiv2025

Multi-Scale Protein Structure Modelling with Geometric Graph U-Nets

Geometric Graph Neural Networks (GNNs) and Transformers have become state-of-the-art for learning from 3D protein structures. However, their reliance on message passing prevents them from capturing the hierarchical interactions that govern protein function, such as global domains and long-range allosteric regulation. In this work, we argue that the network architecture itself should mirror this biological hierarchy. We introduce Geometric Graph U-Nets, a new class of models that learn multi-scale representations by recursively coarsening and refining the protein graph. We prove that this hierarchical design can theoretically more expressive than standard Geometric GNNs. Empirically, on the task of protein fold classification, Geometric U-Nets substantially outperform invariant and equivariant baselines, demonstrating their ability to learn the global structural patterns that define protein folds. Our work provides a principled foundation for designing geometric deep learning architectures that can learn the multi-scale structure of biomolecules.

cs.LG↗

arXiv2025

Spatiotemporal wall pressure forecast of a rectangular cylinder with physics-aware DeepU-Fourier neural network

The wall pressure is of great importance in understanding the forces and structural responses induced by fluid. Recent works have investigated the potential of deep learning techniques in predicting mean pressure coefficients and fluctuating pressure coefficients, but most of existing deep learning frameworks are limited to predicting a single snapshot using full spatial information. To forecast spatiotemporal wall pressure of flow past a rectangular cylinder, this study develops a physics-aware DeepU-Fourier neural Network (DeepUFNet) deep learning model. DeepUFNet comprises the UNet structure and the Fourier neural network, with physical high-frequency loss control embedded in the model training stage to optimize model performance. Wind tunnel testing was performed to collect wall pressures on two-dimensional rectangular cylinders using high-frequency pressure scanning, thereby constructing a database for DeepUFNet training and testing. The DeepUFNet model is found capable of forecasting spatiotemporal wall pressure information with high accuracy on the rectangular cylinder with side ratio 1.5. The comparison between forecast results and experimental data presents agreement in statistical information and physical interpretation. It is also found that embedding a physical high-frequency loss control coefficient b in the DeepUFNet model can significantly improve model performance in forecasting spatiotemporal wall pressure information, particularly, high-order frequency fluctuation and wall pressure variance. Furthermore, the DeepUFNet extrapolation capability is tested with sparse spatial information input, and the model presents a satisfactory extrapolation ability. Last, the DeepUFNet is tested for generalization in unseen cases, rectangular cylinders with side ratio 4 and 3.75, and the model presents satisfactory generalization ability.

physics.flu-dyn↗

arXiv2025

Vision-Language-Action Models for Selective Robotic Disassembly: A Case Study on Critical Component Extraction from Desktops

Automating disassembly of critical components from end-of-life (EoL) desktops, such as high-value items like RAM modules and CPUs, as well as sensitive parts like hard disk drives, remains challenging due to the inherent variability and uncertainty of these products. Moreover, their disassembly requires sequential, precise, and dexterous operations, further increasing the complexity of automation. Current robotic disassembly processes are typically divided into several stages: perception, sequence planning, task planning, motion planning, and manipulation. Each stage requires explicit modeling, which limits generalization to unfamiliar scenarios. Recent development of vision-language-action (VLA) models has presented an end-to-end approach for general robotic manipulation tasks. Although VLAs have demonstrated promising performance on simple tasks, the feasibility of applying such models to complex disassembly remains largely unexplored. In this paper, we collected a customized dataset for robotic RAM and CPU disassembly and used it to fine-tune two well-established VLA approaches, OpenVLA and OpenVLA-OFT, as a case study. We divided the whole disassembly task into several small steps, and our preliminary experimental results indicate that the fine-tuned VLA models can faithfully complete multiple early steps but struggle with certain critical subtasks, leading to task failure. However, we observed that a simple hybrid strategy that combines VLA with a rule-based controller can successfully perform the entire disassembly operation. These findings highlight the current limitations of VLA models in handling the dexterity and precision required for robotic EoL product disassembly. By offering a detailed analysis of the observed results, this study provides insights that may inform future research to address current challenges and advance end-to-end robotic automated disassembly.

cs.RO↗

arXiv2025

Stochastic fluctuations in an eco-evolutionary game dynamics with environmental feedbacks

Building upon the eco-evolutionary game dynamics framework established by Tilman et al., we investigate stochastic fluctuations in a two-strategy system incorporating environmental feedback mechanisms, where the payoff matrix exhibits population size dependence. We adopt a systematic approach which is the so-called $Ω$-expansion. When the stochastic factor is integrated, it is shown that the population size for each strategy fluctuates around the interior equilibrium of the macroscopic equations (corresponding to the deterministic model of the eco-evolutionary game) and its variance converges to a constant that is proportional to the environmental carrying capacity if the interior equilibrium is asymptotically stable. The simulation results demonstrate that the $Ω$ expansion provides a valid approximation, and the reliability of the aforementioned conclusions is verified. Therefore, analogous to Fudenberg and Harris' s stochastic replicator dynamics for infinite populations under external noise (\emph{J. Econ. Theory 57, 420-441}), the dynamic stability of the eco-evolutionary game can be extended to the stochastic regime when the environmental carrying capacity is sufficiently large.

q-bio.PE↗

arXiv2025

A Fast and Flat Federated Learning Method via Weighted Momentum and Sharpness-Aware Minimization

In federated learning (FL), models must \emph{converge quickly} under tight communication budgets while \emph{generalizing} across non-IID client distributions. These twin requirements have naturally led to two widely used techniques: client/server \emph{momentum} to accelerate progress, and \emph{sharpness-aware minimization} (SAM) to prefer flat solutions. However, simply combining momentum and SAM leaves two structural issues unresolved in non-IID FL. We identify and formalize two failure modes: \emph{local-global curvature misalignment} (local SAM directions need not reflect the global loss geometry) and \emph{momentum-echo oscillation} (late-stage instability caused by accumulated momentum). To our knowledge, these failure modes have not been jointly articulated and addressed in the FL literature. We propose \textbf{FedWMSAM} to address both failure modes. First, we construct a momentum-guided global perturbation from server-aggregated momentum to align clients' SAM directions with the global descent geometry, enabling a \emph{single-backprop} SAM approximation that preserves efficiency. Second, we couple momentum and SAM via a cosine-similarity adaptive rule, yielding an early-momentum, late-SAM two-phase training schedule. We provide a non-IID convergence bound that \emph{explicitly models the perturbation-induced variance} $σ_ρ^2=σ^2+(Lρ)^2$ and its dependence on $(S, K, R, N)$ on the theory side. We conduct extensive experiments on multiple datasets and model architectures, and the results validate the effectiveness, adaptability, and robustness of our method, demonstrating its superiority in addressing the optimization challenges of Federated Learning. Our code is available at https://github.com/Huang-Yongzhi/NeurlPS_FedWMSAM.

cs.LG↗

arXiv2025

Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings

Message passing graph neural networks are widely used for learning on graphs, yet their expressive power is limited by the one-dimensional Weisfeiler-Lehman test and can fail to distinguish structurally different nodes. We provide rigorous theory for a Laplacian positional encoding that is invariant to eigenvector sign flips and to basis rotations within eigenspaces. We prove that this encoding yields node identifiability from a constant number of observations and establishes a sample-complexity separation from architectures constrained by the Weisfeiler-Lehman test. The analysis combines a monotone link between shortest-path and diffusion distance, spectral trilateration with a constant set of anchors, and quantitative spectral injectivity with logarithmic embedding size. As an instantiation, pairing this encoding with a neural-process style decoder yields significant gains on a drug-drug interaction task on chemical graphs, improving both the area under the ROC curve and the F1 score and demonstrating the practical benefits of resolving theoretical expressiveness limitations with principled positional information.

cs.LG↗

arXiv2025

MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation

Unified multimodal models aim to integrate understanding and generation within a single framework, yet bridging the gap between discrete semantic reasoning and high-fidelity visual synthesis remains challenging. We present MammothModa2 (Mammoth2), a unified autoregressive-diffusion (AR-Diffusion) framework designed to effectively couple autoregressive semantic planning with diffusion-based generation. Mammoth2 adopts a serial design: an AR path equipped with generation experts performs global semantic modeling over discrete tokens, while a single-stream Diffusion Transformer (DiT) decoder handles high-fidelity image synthesis. A carefully designed AR-Diffusion feature alignment module combines multi-layer feature aggregation, unified condition encoding, and in-context conditioning to stably align AR's representations with the diffusion decoder's continuous latents. Mammoth2 is trained end-to-end with joint Next-Token Prediction and Flow Matching objectives, followed by supervised fine-tuning and reinforcement learning over both generation and editing. With roughly 60M supervised generation samples and no reliance on pre-trained generators, Mammoth2 delivers strong text-to-image and instruction-based editing performance on public benchmarks, achieving 0.87 on GenEval, 87.2 on DPGBench, and 4.06 on ImgEdit, while remaining competitive with understanding-only backbones (e.g., Qwen3-VL-8B) on multimodal understanding tasks. These results suggest that a carefully coupled AR-Diffusion architecture can provide high-fidelity generation and editing while maintaining strong multimodal comprehension within a single, parameter- and data-efficient model.

cs.CV↗

arXiv2025

Anatomy of information scrambling and decoherence in the integrable Sachdev-Ye-Kitaev model

The growth of information scrambling, captured by out-of-time-order correlation functions (OTOCs), is a central indicator of the nature of many-body quantum dynamics. Here, we compute analytically the complete time dependence of the OTOC for an integrable Sachdev-Ye-Kitaev (SYK) model, $N$ Majoranas with random two-body interactions of infinite range, coupled to a Markovian bath at finite temperature. In the limit of no coupling to the bath, the time evolution of scrambling experiences different stages. For $t \lesssim \sqrt{N}$, after an initial polynomial growth, the OTOC approaches saturation in a power-law fashion with oscillations superimposed. At $t \sim \sqrt{N}$, the OTOC reverses trend and starts to decrease linearly in time. The reason for this linear decrease is that, despite being a subleading $1/N$ effect, the OTOC in this region is governed by the spectral form factor of the antisymmetric couplings of the SYK model. The linear decrease stops at $t \sim 2N$, the Heisenberg time, where saturation occurs. The effect of the environment is an overall exponential decay of the OTOC for times longer than the inverse of the coupling strength to the bath. The oscillations at $t \lesssim \sqrt{N}$ indicate lack of thermalization -- a desired feature for a better performance of quantum information devices.

hep-th↗

arXiv2025

Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias

Accurately predicting the long-term evolution of turbulence is crucial for advancing scientific understanding and optimizing engineering applications. However, existing deep learning methods face significant bottlenecks in long-term autoregressive prediction, which exhibit excessive smoothing and fail to accurately track complex fluid dynamics. Our extensive experimental and spectral analysis of prevailing methods provides an interpretable explanation for this shortcoming, identifying Spectral Bias as the core obstacle. Concretely, spectral bias is the inherent tendency of models to favor low-frequency, smooth features while overlooking critical high-frequency details during training, thus reducing fidelity and causing physical distortions in long-term predictions. Building on this insight, we propose Turb-L1, an innovative turbulence prediction method, which utilizes a Hierarchical Dynamics Synthesis mechanism within a multi-grid architecture to explicitly overcome spectral bias. It accurately captures cross-scale interactions and preserves the fidelity of high-frequency dynamics, enabling reliable long-term tracking of turbulence evolution. Extensive experiments on the 2D turbulence benchmark show that Turb-L1 demonstrates excellent performance: (I) In long-term predictions, it reduces Mean Squared Error (MSE) by $80.3\%$ and increases Structural Similarity (SSIM) by over $9\times$ compared to the SOTA baseline, significantly improving prediction fidelity. (II) It effectively overcomes spectral bias, accurately reproducing the full enstrophy spectrum and maintaining physical realism in high-wavenumber regions, thus avoiding the spectral distortions or spurious energy accumulation seen in other methods.

cs.LG↗

arXiv2025

MalRAG: A Retrieval-Augmented LLM Framework for Open-set Malicious Traffic Identification

Fine-grained identification of IDS-flagged suspicious traffic is crucial in cybersecurity. In practice, cyber threats evolve continuously, making the discovery of novel malicious traffic a critical necessity as well as the identification of known classes. Recent studies have advanced this goal with deep models, but they often rely on task-specific architectures that limit transferability and require per-dataset tuning. In this paper we introduce MalRAG, the first LLM driven retrieval-augmented framework for open-set malicious traffic identification. MalRAG freezes the LLM and operates via comprehensive traffic knowledge construction, adaptive retrieval, and prompt engineering. Concretely, we construct a multi-view traffic database by mining prior malicious traffic from content, structural, and temporal perspectives. Furthermore, we introduce a Coverage-Enhanced Retrieval Algorithm that queries across these views to assemble the most probable candidates, thereby improving the inclusion of correct evidence. We then employ Traffic-Aware Adaptive Pruning to select a variable subset of these candidates based on traffic-aware similarity scores, suppressing incorrect matches and yielding reliable retrieved evidence. Moreover, we develop a suite of guidance prompts where task instruction, evidence referencing, and decision guidance are integrated with the retrieved evidence to improve LLM performance. Across diverse real-world datasets and settings, MalRAG delivers state-of-the-art results in both fine-grained identification of known classes and novel malicious traffic discovery. Ablation and deep-dive analyses further show that MalRAG effective leverages LLM capabilities yet achieves open-set malicious traffic identification without relying on a specific LLM.

cs.CR↗

arXiv2025

A Joint Delay-Energy-Security Aware Framework for Intelligent Task Scheduling in Satellite-Terrestrial Edge Computing Network

In this paper, we propose a two-stage optimization framework for secure task scheduling in satellite-terrestrial edge computing networks (STECNs). The framework jointly considers secure user association and task offloading to balance transmission delay, energy consumption, and physical-layer security. To address the inherent complexity, we decouple the problem into two stages. In the first stage, a secrecy-aware user association strategy is designed by discretizing artificial noise (AN) power ratios and identifying feasible links that satisfy secrecy constraints, resulting in a set of candidate secure associations. In the second stage, we formulate a delay-energy-aware task scheduling problem as an integer linear program and solve it using a heuristic Mayfly Algorithm (MA) to obtain low-complexity, high-quality solutions. Extensive simulation results demonstrate the effectiveness and superiority of the proposed framework in achieving secure and efficient task scheduling under dynamic satellite environments.

eess.SY↗

arXiv2025

Ripple-assisted adsorption of noble gases on graphene at room temperature

Controllable gas adsorption is critical for both scientific and industrial fields, and high-capacity adsorption of gases on solid surfaces provides a significant promise due to its high-safety and low-energy consumption. However, the adsorption of nonpolar gases, particularly noble gases, poses a considerable challenge under atmospheric pressure and room temperature (RT). Here, we theoretically simulate and experimentally realize the stable adsorption of noble gases like xenon (Xe), krypton (Kr), argon (Ar), and helium (He) on highly rippled graphene at RT. The elemental characteristics of adsorbed Xe are confirmed by electron energy loss spectroscopy and X-ray photoelectron spectroscopy. The adsorbed gas atoms are crystalized with periodic arrangements. These adsorbed noble gases on graphene exhibit high stability at RT and can be completely desorbed at approximately 350 °C without damaging the intrinsic lattice of graphene. The structural and physical properties of graphene are significantly influenced by the adsorbed gas, and they fully recover after desorption. Additionally, this controllable adsorption could be generalized to other layered adsorbents such as NbSe2, MoS2 and carbon nanotubes. We anticipate that this ripple-assisted adsorption will not only re-define the theoretical framework of gas adsorption, but also accelerate advancements in gas storage and separation technologies, as well as enhance the applications in catalysis, surface modification, and other related fields.

cond-mat.mtrl-sci↗

arXiv2025

S2D-ALIGN: Shallow-to-Deep Auxiliary Learning for Anatomically-Grounded Radiology Report Generation

Radiology Report Generation (RRG) aims to automatically generate diagnostic reports from radiology images. To achieve this, existing methods have leveraged the powerful cross-modal generation capabilities of Multimodal Large Language Models (MLLMs), primarily focusing on optimizing cross-modal alignment between radiographs and reports through Supervised Fine-Tuning (SFT). However, by only performing instance-level alignment with the image-text pairs, the standard SFT paradigm fails to establish anatomically-grounded alignment, where the templated nature of reports often leads to sub-optimal generation quality. To address this, we propose \textsc{S2D-Align}, a novel SFT paradigm that establishes anatomically-grounded alignment by leveraging auxiliary signals of varying granularities. \textsc{S2D-Align} implements a shallow-to-deep strategy, progressively enriching the alignment process: it begins with the coarse radiograph-report pairing, then introduces reference reports for instance-level guidance, and ultimately utilizes key phrases to ground the generation in specific anatomical details. To bridge the different alignment stages, we introduce a memory-based adapter that empowers feature sharing, thereby integrating coarse and fine-grained guidance. For evaluation, we conduct experiments on the public \textsc{MIMIC-CXR} and \textsc{IU X-Ray} benchmarks, where \textsc{S2D-Align} achieves state-of-the-art performance compared to existing methods. Ablation studies validate the effectiveness of our multi-stage, auxiliary-guided approach, highlighting a promising direction for enhancing grounding capabilities in complex, multi-modal generation tasks.

cs.CV↗

arXiv2025

ZTF25abjmnps (AT2025ulz) and S250818k: A Candidate Superkilonova from a Sub-threshold Sub-Solar Gravitational Wave Trigger

On August 18, 2025, the LIGO-Virgo-KAGRA collaboration reported gravitational waves from a sub-threshold binary neutron star merger. If astrophysical, this event would have a surprisingly low chirp mass, suggesting that at least one neutron star was below a solar mass. The Zwicky Transient Facility mapped the coarse localization and discovered a transient, ZTF25abjmnps (AT2025ulz), that was spatially and temporally coincident with the gravitational wave trigger. The first week of follow-up suggested properties reminiscent of a GW170817-like kilonova. Subsequent follow-up suggests properties most similar to a young, stripped-envelope, Type IIb supernova. Although we cannot statistically rule out chance coincidence, we undertake due diligence analysis to explore the possible association between ZTF25abjmnps and S250818k. Theoretical models have been proposed wherein sub-solar neutron star(s) may form (and subsequently merge) via accretion disk fragmentation or core fission inside a core-collapse supernova i.e. a ``superkilonova". Here, we qualitatively discuss our multi-wavelength dataset in the context of the superkilonova picture. Future higher significance gravitational wave detections of sub-solar neutron star mergers with extensive electromagnetic follow-up would conclusively resolve this tantalizing multi-messenger association.

astro-ph.HE↗