arXiv subjects

Chang Liu

Publications and source records attributed to Chang Liu.

At least 397 records · Page 22Linked to original sources

arXiv2025

Mid-Infrared Dust Evolution and Late-time Circumstellar Medium Interaction in SN 2017eaw

We present JWST/MIRI and complementary ground-based near-infrared observations of the Type II SN 2017eaw taken 6 years post-explosion. SN 2017eaw is still detected out to 25 $μ$m and there is minimal evolution in the mid-infrared spectral energy distribution (SED) between the newly acquired JWST/MIRI observations and those taken a year earlier. Modeling of the mid-infrared SED reveals a cool $\sim$160 K dust component of $5.5\times10^{-4}\ \mathrm{M}_\odot$ and a hot $\sim$1700 K component of $5.4\times10^{-8}\ \mathrm{M}_\odot$ both composed of silicate dust. Notably there is no evidence of temperature or mass evolution in the cool dust component in the year between JWST observations. We also present new and archival HST and ground-based ultraviolet (UV) and optical observations which reveal reduced but continued circumstellar medium (CSM)-ejecta interaction at $>$2000 days post-explosion. The UV and mid-infrared emission show similar decline rates, suggesting both probe the interface between the ejecta and CSM. Given this, the continued existence of boxy H$α$ emission in the nebular spectra, the low inferred optical depth of the dust, and the lack of temperature and mass evolution, we suggest that the cool dust component in SN 2017eaw may be primarily due to pre-existing dust rather than newly-formed dust in the ejecta or cold dense shell.

astro-ph.HE↗

arXiv2025

Ultrafast cooperative electronic, structural, and magnetic switching in an altermagnet

Femtosecond laser control of antiferromagnetic order is a cornerstone for future memory and logic devices operating at terahertz clock rates. The advent of altermagnets -- antiferromagnets with unconventional spin-group symmetries -- creates new opportunities in this evolving field. Here, we demonstrate ultrafast laser-induced switching in altermagnetic $α$-MnTe that orchestrates the concerted dynamics of charge, lattice, and spin degrees of freedom. Time-resolved reflectivity and birefringence measurements reveal that the transient melting of spin order is accompanied by pronounced structural and electronic instabilities, as evidenced by phonon nonlinearity and accelerated band gap shrinkage. Theoretical modeling highlights the key roles of robust magnetic correlations and spin-charge coupling pathways intrinsic to this altermagnet.

cond-mat.str-el↗

arXiv2025

Mapping the Spatial Distribution of Fast Radio Bursts within their Host Galaxies

We present deep optical and near-infrared observations of the host galaxies of 34 fast radio bursts (FRBs) detected by the Commensal Real-time ASKAP Fast Transient (CRAFT) survey on the Australian SKA Pathfinder (ASKAP) to compare the locations of FRBs relative to their host light distributions. Incorporating three additional FRBs from the literature, for a total of four repeating and 33 apparently non-repeating FRBs, we determine their projected galactocentric offsets and find a median of $ 4.2^{+5.7}_{-2.5}$ kpc ($1.0^{+1.5}_{-0.6}r_e$). We model their host surface brightness profiles and develop synthetic spatial distributions of their globular clusters based on host properties. We calculate the likelihood the observed location of each FRB is consistent with the smooth light of its host galaxy, residual (primarily spiral) substructure, or globular cluster distributions. The majority of FRBs favor locations within the disks of their galaxies, while only 11$\pm$5\% favor a globular cluster origin, primarily those with galactocentric offsets $\gtrsim3r_e$. At $z<0.15$, where spiral structure is apparent in 86\% of our sample of FRB hosts, we find $\approx 20-46\%$ of FRBs favor an association with spiral arms. Assuming FRBs derive from magnetars, our results support multiple formation channels with the majority of progenitors associated with massive stars and a minority formed through dynamical channels. However, the moderate fraction of FRBs associated with spiral structure indicates that high star formation efficiency of the youngest and most massive stars is not a predominant driver in the production of FRB progenitors.

astro-ph.GA↗

arXiv2025

Investigating Student Interaction Patterns with Large Language Model-Powered Course Assistants in Computer Science Courses

Providing students with flexible and timely academic support is a challenge at most colleges and universities, leaving many students without help outside scheduled hours. Large language models (LLMs) are promising for bridging this gap, but interactions between students and LLMs are rarely overseen by educators. We developed and studied an LLM-powered course assistant deployed across multiple computer science courses to characterize real-world use and understand pedagogical implications. By Spring 2024, our system had been deployed to approximately 2,000 students across six courses at three institutions. Analysis of the interaction data shows that usage remains strong in the evenings and nights and is higher in introductory courses, indicating that our system helps address temporal support gaps and novice learner needs. We sampled 200 conversations per course for manual annotation: most sampled responses were judged correct and helpful, with a small share unhelpful or erroneous; few responses included dedicated examples. We also examined an inquiry-based learning strategy: only around 11% of sampled conversations contained LLM-generated follow-up questions, which were often ignored by students in advanced courses. A Bloom's taxonomy analysis reveals that current LLM capabilities are limited in generating higher-order cognitive questions. These patterns suggest opportunities for pedagogically oriented LLM-based educational systems and greater educator involvement in configuring prompts, content, and policies.

cs.CY↗

arXiv2025

SaD: A Scenario-Aware Discriminator for Speech Enhancement

Generative adversarial network-based models have shown remarkable performance in the field of speech enhancement. However, the current optimization strategies for these models predominantly focus on refining the architecture of the generator or enhancing the quality evaluation metrics of the discriminator. This approach often overlooks the rich contextual information inherent in diverse scenarios. In this paper, we propose a scenario-aware discriminator that captures scene-specific features and performs frequency-domain division, thereby enabling a more accurate quality assessment of the enhanced speech generated by the generator. We conducted comprehensive experiments on three representative models using two publicly available datasets. The results demonstrate that our method can effectively adapt to various generator architectures without altering their structure, thereby unlocking further performance gains in speech enhancement across different scenarios.

cs.SD↗

arXiv2025

Magnetic excitations in biaxial-strain detwinned $α$-RuCl$_{3}$

The honeycomb magnet $α$-RuCl$_{3}$ has been a leading candidate for realizing the Kitaev quantum spin liquid (QSL), but its intrinsic spin dynamics have remained obscured by crystal twinning. Here we apply biaxial anisotropic strain to detwin $α$-RuCl$_{3}$ single crystals and directly visualize the intrinsic magnetic excitations using inelastic neutron scattering. We discover that the low-energy spin waves emerge from the $M$ points -- transverse to the magnetic Bragg peaks -- providing direct evidence of anisotropic magnetic interactions in $α$-RuCl$_{3}$. The intrinsic spin-wave spectrum imposes stringent constraints on the extended Kitaev Hamiltonian, yielding a refined, quantitatively consistent set of exchange couplings for the zigzag ground state and its low-energy dynamics. Above the magnon band, we uncover broad excitation continua: while a twofold-symmetric feature near 6 meV at $Γ$ is consistent with bimagnon scattering, the dominant spectral weight forms a sixfold-symmetric continuum extending up to $\sim 16$ meV that cannot be explained by conventional magnons. This strongly supports the presence of fractionalized excitations-a hallmark of Kitaev QSL physics. Our findings establish biaxial strain as a powerful symmetry-breaking probe to access the intrinsic spin dynamics of Kitaev materials and provide critical benchmarks for refining theoretical models of quantum magnetism in $α$-RuCl$_{3}$.

cond-mat.str-el↗

arXiv2025

DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning

Grounding natural language queries in graphical user interfaces (GUIs) poses unique challenges due to the diversity of visual elements, spatial clutter, and the ambiguity of language. In this paper, we introduce DiMo-GUI, a training-free framework for GUI grounding that leverages two core strategies: dynamic visual grounding and modality-aware optimization. Instead of treating the GUI as a monolithic image, our method splits the input into textual elements and iconic elements, allowing the model to reason over each modality independently using general-purpose vision-language models. When predictions are ambiguous or incorrect, DiMo-GUI dynamically focuses attention by generating candidate focal regions centered on the model's initial predictions and incrementally zooms into subregions to refine the grounding result. This hierarchical refinement process helps disambiguate visually crowded layouts without the need for additional training or annotations. We evaluate our approach on standard GUI grounding benchmarks and demonstrate consistent improvements over baseline inference pipelines, highlighting the effectiveness of combining modality separation with region-focused reasoning.

cs.AI↗

arXiv2025

MobileRAG: Enhancing Mobile Agent with Retrieval-Augmented Generation

Smartphones have become indispensable in people's daily lives, permeating nearly every aspect of modern society. With the continuous advancement of large language models (LLMs), numerous LLM-based mobile agents have emerged. These agents are capable of accurately parsing diverse user queries and automatically assisting users in completing complex or repetitive operations. However, current agents 1) heavily rely on the comprehension ability of LLMs, which can lead to errors caused by misoperations or omitted steps during tasks, 2) lack interaction with the external environment, often terminating tasks when an app cannot fulfill user queries, and 3) lack memory capabilities, requiring each instruction to reconstruct the interface and being unable to learn from and correct previous mistakes. To alleviate the above issues, we propose MobileRAG, a mobile agents framework enhanced by Retrieval-Augmented Generation (RAG), which includes InterRAG, LocalRAG, and MemRAG. It leverages RAG to more quickly and accurately identify user queries and accomplish complex and long-sequence mobile tasks. Additionally, to more comprehensively assess the performance of MobileRAG, we introduce MobileRAG-Eval, a more challenging benchmark characterized by numerous complex, real-world mobile tasks that require external knowledge assistance. Extensive experimental results on MobileRAG-Eval demonstrate that MobileRAG can easily handle real-world mobile tasks, achieving 10.3\% improvement over state-of-the-art methods with fewer operational steps. Our code is publicly available at: https://github.com/liuxiaojieOutOfWorld/MobileRAG_arxiv

cs.CL↗

arXiv2025

Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions

Large language models (LLMs) have gained widespread recognition for their superior comprehension and have been deployed across numerous domains. Building on Chain-of-Thought (CoT) ideology, Large Reasoning models (LRMs) further exhibit strong reasoning skills, enabling them to infer user intent more accurately and respond appropriately. However, both LLMs and LRMs face the potential safety risks under jailbreak attacks, which raise concerns about their safety capabilities. Current safety evaluation methods often focus on the content dimensions, or simply aggregate different attack methods, lacking consideration of the complexity. In fact, instructions of different complexity can reflect the different safety capabilities of the model: simple instructions can reflect the basic values of the model, while complex instructions can reflect the model's ability to deal with deeper safety risks. Therefore, a comprehensive benchmark needs to be established to evaluate the safety performance of the model in the face of instructions of varying complexity, which can provide a better understanding of the safety boundaries of the LLMs. Thus, this paper first quantifies "Reasoning Complexity" as an evaluable safety dimension and categorizes 15 jailbreak attack methods into three different levels according to the reasoning complexity, establishing a hierarchical Chinese-English jailbreak safety benchmark for systematically evaluating the safety performance of LLMs. Meanwhile, to fully utilize unique language characteristics, we first propose some Chinese jailbreak attack methods, including the Chinese Character Disassembly attack, Lantern Riddle attack, and Acrostic Poem attack. A series of experiments indicate that current LLMs and LRMs show different safety boundaries under different reasoning complexity, which provides a new perspective to develop safer LLMs and LRMs.

cs.CY↗

arXiv2025

From Anchors to Answers: A Novel Node Tokenizer for Integrating Graph Structure into Large Language Models

Enabling large language models (LLMs) to effectively process and reason with graph-structured data remains a significant challenge despite their remarkable success in natural language tasks. Current approaches either convert graph structures into verbose textual descriptions, consuming substantial computational resources, or employ complex graph neural networks as tokenizers, which introduce significant training overhead. To bridge this gap, we present NT-LLM, a novel framework with an anchor-based positional encoding scheme for graph representation. Our approach strategically selects reference nodes as anchors and encodes each node's position relative to these anchors, capturing essential topological information without the computational burden of existing methods. Notably, we identify and address a fundamental issue: the inherent misalignment between discrete hop-based distances in graphs and continuous distances in embedding spaces. By implementing a rank-preserving objective for positional encoding pretraining, NT-LLM achieves superior performance across diverse graph tasks ranging from basic structural analysis to complex reasoning scenarios. Our comprehensive evaluation demonstrates that this lightweight yet powerful approach effectively enhances LLMs' ability to understand and reason with graph-structured information, offering an efficient solution for graph-based applications of language models.

cs.AI↗

arXiv2025

A Morphological Model to Separate Resolved-Unresolved Sources in the DESI Legacy Surveys: Application in the LS4 Alert Stream

Separating resolved and unresolved sources in large imaging surveys is a fundamental step to enable downstream science, such as searching for extragalactic transients in wide-field time-domain surveys. Here we present our method to effectively separate point sources from the resolved, extended sources in the Dark Energy Spectroscopic Instrument (DESI) Legacy Surveys (LS). We develop a supervised machine-learning model based on the Gradient Boosting algorithm $\texttt{XGBoost}$. The features input to the model are purely morphological and are derived from the tabulated LS data products. We train the model using $\sim$$2\times10^5$ LS sources in the COSMOS field with HST morphological labels and evaluate the model performance on LS sources with spectroscopic classification from the DESI Data Release 1 ($\sim$$2\times10^7$ objects) and the Sloan Digital Sky Survey Data Release 17 ($\sim$$3\times10^6$ objects), as well as on $\sim$$2\times10^8$ Gaia stars. A significant fraction of LS sources are not observed in every LS filter, and we therefore build a ''Hybrid'' model as a linear combination of two \texttt{XGBoost} models, each containing features combining aperture flux measurements from the ''blue'' ($gr$) and ''red'' ($iz$) filters. The Hybrid model shows a reasonable balance between sensitivity and robustness, and achieves higher accuracy and flexibility compared to the LS morphological typing. With the Hybrid model, we provide classification scores for $\sim$$3\times10^9$ LS sources, making this the largest ever machine-learning catalog separating resolved and unresolved sources. The catalog has been incorporated into the real-time pipeline of the La Silla Schmidt Southern Survey (LS4), enabling the identification of extragalactic transients within the LS4 alert stream.

astro-ph.IM↗

arXiv2025

VOTA: Parallelizing 6G-RAN Experimentation with Virtualized Over-The-Air Workloads

Testbed sharing, a practice in which different researchers concurrently develop independent use cases on top of the same testbed, is ubiquitous in wireless experimental research. Its key drawback is experimental inconvenience: one must delay experiments or tolerate compute and RF interference that harms experimental fidelity. In this paper, we propose \textbf{VOTA}, an open-source, software-only testbed scaling method that leverages real-time virtualization and frequency tuning to maximize parallel experiments while controlling interference. In a demonstration of two interference-sensitive 6G use cases -- \textit{MIMO iDFT/DFT Offloading} and \textit{O-RAN DoS Attack} -- running side-by-side on a 32-core host, we showcase VOTA capabilities: \textbf{dedicated-like} results while allowing \textbf{2.67$\times$} more sharing opportunities.

cs.NI↗

arXiv2025

UniGenX: a unified generative foundation model that couples sequence, structure and function to accelerate scientific design across proteins, molecules and materials

Function in natural systems arises from one-dimensional sequences forming three-dimensional structures with specific properties. However, current generative models suffer from critical limitations: training objectives seldom target function directly, discrete sequences and continuous coordinates are optimized in isolation, and conformational ensembles are under-modeled. We present UniGenX, a unified generative foundation model that addresses these gaps by co-generating sequences and coordinates under direct functional and property objectives across proteins, molecules, and materials. UniGenX represents heterogeneous inputs as a mixed stream of symbolic and numeric tokens, where a decoder-only autoregressive transformer provides global context and a conditional diffusion head generates numeric fields steered by task-specific tokens. Besides the new high SOTAs on structure prediction tasks, the model demonstrates state-of-the-art or competitive performance for the function-aware generation across domains: in materials, it achieves "conflicted" multi-property conditional generation, yielding 436 crystal candidates meeting triple constraints, including 11 with novel compositions; in chemistry, it sets new benchmarks on five property targets and conformer ensemble generation on GEOM; and in biology, it improves success in modeling protein induced fit (RMSD < 2 Å) by over 23-fold and enhances EC-conditioned enzyme design. Ablation studies and cross-domain transfer substantiate the benefits of joint discrete-continuous training, establishing UniGenX as a significant advance from prediction to controllable, function-aware generation.

cs.LG↗

arXiv2025

Spontaneous generation of helical flows by salt fingers

We study the dynamics of salt fingers in the regime of slow salinity diffusion (small inverse Lewis number) and strong stratification (large density ratio), focusing on regimes relevant to Earth's oceans. Using three-dimensional direct numerical simulations in periodic domains, we show that salt fingers exhibit rich, multiscale dynamics in this regime, with vertically elongated fingers that are twisted into helical shapes at large scales by mean flows and disrupted at small scales by isotropic eddies. We use a multiscale asymptotic analysis to motivate a reduced set of partial differential equations that filters internal gravity waves and removes inertia from all parts of the momentum equation except for the Reynolds stress that drives the helical mean flow. When simulated numerically, the reduced equations capture the same dynamics and fluxes as the full equations in the appropriate regime. The reduced equations enforce zero helicity in all fluctuations about the mean flow, implying that the symmetry-breaking helical flow is spontaneously generated by strictly non-helical fluctuations.

physics.flu-dyn↗

arXiv2025

Joint Cache Placement and Routing in Satellite-Terrestrial Edge Computing Network: A GNN-Enabled DRL Approach

In this letter, we investigate the problem of joint content caching and routing in satellite-terrestrial edge computing networks (STECNs) to improve caching service for geographically distributed users. To handle the challenges arising from dynamic low Earth orbit (LEO) satellite topologies and heterogeneous content demands, we propose a learning-based framework that integrates graph neural networks (GNNs) with deep reinforcement learning (DRL). The satellite network is represented as a dynamic graph, where GNNs are embedded within the DRL agent to capture spatial and topological dependencies and support routing-aware decision-making. The caching strategy is optimized by formulating the problem as a Markov decision process (MDP) and applying soft actor-critic (SAC) algorithm. Simulation results demonstrate that our approach significantly improves the delivery success rate and reduces communication traffic cost.

cs.NI↗

arXiv2025

Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation

The trustworthiness of Multimodal Large Language Models (MLLMs) remains an intense concern despite the significant progress in their capabilities. Existing evaluation and mitigation approaches often focus on narrow aspects and overlook risks introduced by the multimodality. To tackle these challenges, we propose MultiTrust-X, a comprehensive benchmark for evaluating, analyzing, and mitigating the trustworthiness issues of MLLMs. We define a three-dimensional framework, encompassing five trustworthiness aspects which include truthfulness, robustness, safety, fairness, and privacy; two novel risk types covering multimodal risks and cross-modal impacts; and various mitigation strategies from the perspectives of data, model architecture, training, and inference algorithms. Based on the taxonomy, MultiTrust-X includes 32 tasks and 28 curated datasets, enabling holistic evaluations over 30 open-source and proprietary MLLMs and in-depth analysis with 8 representative mitigation methods. Our extensive experiments reveal significant vulnerabilities in current models, including a gap between trustworthiness and general capabilities, as well as the amplification of potential risks in base LLMs by both multimodal training and inference. Moreover, our controlled analysis uncovers key limitations in existing mitigation strategies that, while some methods yield improvements in specific aspects, few effectively address overall trustworthiness, and many introduce unexpected trade-offs that compromise model utility. These findings also provide practical insights for future improvements, such as the benefits of reasoning to better balance safety and performance. Based on these insights, we introduce a Reasoning-Enhanced Safety Alignment (RESA) approach that equips the model with chain-of-thought reasoning ability to discover the underlying risks, achieving state-of-the-art results.

cs.CL↗

arXiv2025

D3FNet: A Differential Attention Fusion Network for Fine-Grained Road Structure Extraction in Remote Perception Systems

Extracting narrow roads from high-resolution remote sensing imagery remains a significant challenge due to their limited width, fragmented topology, and frequent occlusions. To address these issues, we propose D3FNet, a Dilated Dual-Stream Differential Attention Fusion Network designed for fine-grained road structure segmentation in remote perception systems. Built upon the encoder-decoder backbone of D-LinkNet, D3FNet introduces three key innovations:(1) a Differential Attention Dilation Extraction (DADE) module that enhances subtle road features while suppressing background noise at the bottleneck; (2) a Dual-stream Decoding Fusion Mechanism (DDFM) that integrates original and attention-modulated features to balance spatial precision with semantic context; and (3) a multi-scale dilation strategy (rates 1, 3, 5, 9) that mitigates gridding artifacts and improves continuity in narrow road prediction. Unlike conventional models that overfit to generic road widths, D3FNet specifically targets fine-grained, occluded, and low-contrast road segments. Extensive experiments on the DeepGlobe and CHN6-CUG benchmarks show that D3FNet achieves superior IoU and recall on challenging road regions, outperforming state-of-the-art baselines. Ablation studies further verify the complementary synergy of attention-guided encoding and dual-path decoding. These results confirm D3FNet as a robust solution for fine-grained narrow road extraction in complex remote and cooperative perception scenarios.

cs.CV↗

arXiv2025

Generating Negative Samples for Multi-Modal Recommendation

Multi-modal recommender systems (MMRS) have gained significant attention due to their ability to leverage information from various modalities to enhance recommendation quality. However, existing negative sampling techniques often struggle to effectively utilize the multi-modal data, leading to suboptimal performance. In this paper, we identify two key challenges in negative sampling for MMRS: (1) producing cohesive negative samples contrasting with positive samples and (2) maintaining a balanced influence across different modalities. To address these challenges, we propose NegGen, a novel framework that utilizes multi-modal large language models (MLLMs) to generate balanced and contrastive negative samples. We design three different prompt templates to enable NegGen to analyze and manipulate item attributes across multiple modalities, and then generate negative samples that introduce better supervision signals and ensure modality balance. Furthermore, NegGen employs a causal learning module to disentangle the effect of intervened key features and irrelevant item attributes, enabling fine-grained learning of user preferences. Extensive experiments on real-world datasets demonstrate the superior performance of NegGen compared to state-of-the-art methods in both negative sampling and multi-modal recommendation.

cs.IR↗