arXiv subjects

Jiawen Zhang

Publications and source records attributed to Jiawen Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2026

Magnetic states of the Kondo lattice Ce$_2$PdSi$_3$ and their pressure evolution

Frustrated Kondo lattices are ideal platforms for exploring unconventional forms of quantum criticality, as well as magnetism and other emergent phases. Here we report the magnetic properties of the candidate frustrated heavy fermion compound Ce$_2$PdSi$_3$, and map their evolution upon applying magnetic fields and hydrostatic pressure. We find that at ambient pressure Ce$_2$PdSi$_3$ exhibits two distinct magnetic phase transitions, a ferromagnetic-like transition at $T_{\mathrm{M1}}=3.8$ K and an incommensurate antiferromagnetic transition at $T_{\mathrm{M2}}=2.9$ K. Upon applying pressure, $T_{\mathrm{M1}}$ is continuously suppressed and becomes undetectable above 4.2 GPa, whereas $T_{\mathrm{M2}}$ increases and remains robust up to at least 7.5 GPa. The observed pressure evolution of magnetic order in Ce$_2$PdSi$_3$ suggests the presence of competing magnetic orders, and cannot be simply encapsulated by the Doniach phase diagram, motivating further investigations for its origin, including discerning the role of geometric frustration.

cond-mat.str-el↗

arXiv2026

Understanding and Preserving Safety in Fine-Tuned LLMs

Fine-tuning is an essential and pervasive functionality for applying large language models (LLMs) to downstream tasks. However, it has the potential to substantially degrade safety alignment, e.g., by greatly increasing susceptibility to jailbreak attacks, even when the fine-tuning data is entirely harmless. Despite garnering growing attention in defense efforts during the fine-tuning stage, existing methods struggle with a persistent safety-utility dilemma: emphasizing safety compromises task performance, whereas prioritizing utility typically requires deep fine-tuning that inevitably leads to steep safety declination. In this work, we address this dilemma by shedding new light on the geometric interaction between safety- and utility-oriented gradients in safety-aligned LLMs. Through systematic empirical analysis, we uncover three key insights: (I) safety gradients lie in a low-rank subspace, while utility gradients span a broader high-dimensional space; (II) these subspaces are often negatively correlated, causing directional conflicts during fine-tuning; and (III) the dominant safety direction can be efficiently estimated from a single sample. Building upon these novel insights, we propose safety-preserving fine-tuning (SPF), a lightweight approach that explicitly removes gradient components conflicting with the low-rank safety subspace. Theoretically, we show that SPF guarantees utility convergence while bounding safety drift. Empirically, SPF consistently maintains downstream task performance and recovers nearly all pre-trained safety alignment, even under adversarial fine-tuning scenarios. Furthermore, SPF exhibits robust resistance to both deep fine-tuning and dynamic jailbreak attacks. Together, our findings provide new mechanistic understanding and practical guidance toward always-aligned LLM fine-tuning.

cs.LG↗

arXiv2026

Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance

Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many safety samples or calibration sets, which not only incur significant computational overhead during realignment but also lead to noticeable degradation in model utility. Contrary to this belief, we show that safety alignment can be fully recovered with only a single safety example, without sacrificing utility and at minimal cost. Remarkably, this recovery is effective regardless of the number of harmful examples used in fine-tuning or the size of the underlying model, and convergence is achieved within just a few epochs. Furthermore, we uncover the low-rank structure of the safety gradient, which explains why such efficient correction is possible. We validate our findings across five safety-aligned LLMs and multiple datasets, demonstrating the generality of our approach.

cs.LG↗

arXiv2025

Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains

Time-Series Foundation Models (TSFMs) are rapidly transitioning from research prototypes to core components of critical decision-making systems, driven by their impressive zero-shot forecasting capabilities. However, as their deployment surges, a critical blind spot remains: their fragility under adversarial attacks. This lack of scrutiny poses severe risks, particularly as TSFMs enter high-stakes environments vulnerable to manipulation. We present a systematic, diagnostic study arguing that for TSFMs, robustness is not merely a secondary metric but a prerequisite for trustworthy deployment comparable to accuracy. Our evaluation framework, explicitly tailored to the unique constraints of time series, incorporates normalized, sparsity-aware perturbation budgets and unified scale-invariant metrics across white-box and black-box settings. Across six representative TSFMs, we demonstrate that current architectures are alarmingly brittle: even small perturbations can reliably steer forecasts toward specific failure modes, such as trend flips and malicious drifts. We uncover TSFM-specific vulnerability patterns, including horizon-proximal brittleness, increased susceptibility with longer context windows, and weak cross-model transfer that points to model-specific failure modes rather than generic distortions. Finally, we show that simple adversarial fine-tuning offers a cost-effective path to substantial robustness gains, even with out-of-domain data. This work bridges the gap between TSFM capabilities and safety constraints, offering essential guidance for hardening the next generation of forecasting systems.

cs.LG↗

arXiv2025

Accurate humidity and pH synchronized measurement with temperature compensation based on polarization maintaining fiber

Real-time and accurate monitoring of humidity and pH is of great significance in daily life and industrial production. Existing humidity and pH measurement suffer from limitations such as low sensitivity, signal crosstalk, complex system structures, and inability to achieve real-time monitoring. In this work, the surface of a polarization maintaining fiber (PMF) was functionalized with a composite humidity-sensitive polymer composed of polyvinyl alcohol (PVA) and carbon nanosheets (CNs). A humidity-sensitive film with a microporous structure was prepared on the PMF cladding through high-temperature rapid film formation and laser processing, enhancing humidity sensitivity and stability. To enable pH sensing, poly(allylamine hydrochloride) (PAH) and poly (acrylic acid) (PAA) were successively adsorbed onto the PMF surface via electrostatic self-assembly, forming a pH-sensitive nanofilm structure. By connecting a temperature-compensated PMF within the same Sagnac loop and combining it with a multi-wavelength matrix, simultaneous real-time monitoring of humidity, pH, and temperature was achieved, effectively solving the issue of temperature crosstalk and extending toward a universal optical fiber multi-parameter measurement platform.

physics.app-ph↗

arXiv2025

Scale-bridging dislocation plasticity in MgO at room temperature

Dislocations in ceramics have recently gained renewed research interest, in contrast to the traditional belief that ceramics are inherently brittle. Understanding dislocation mechanics in representative oxides is beneficial for effective dislocation engineering. Here, we use MgO single crystals with mechanically seeded dislocation densities from about 10 to the power of 12 to about 10 to the power of 15 per square meter to investigate the mechanical behavior such as yield and fracture. Micro-pillar compression tests reveal a dislocation density dependent yield strength, mediated by the varying dominating dislocation mechanisms from nucleation to multiplication/motion. In situ TEM compression measurements highlight the dislocation-seeded samples can achieve a much-improved compressive plastic strain beyond about 70%, with a high yield strength of about 2.35 GPa (diameter of about 400 nm), indicating size effect. Complementary bulk compression tests, along with digital image correlation (DIC), demonstrate a consistent dislocation-mediated deformation and a notable size effect, with bulk samples exhibiting much reduced yield strength (about 120 MPa) compared to the nano-/micro-pillars. Using three-dimensional Discrete Dislocation Dynamics (3D-DDD) simulation, we further qualitatively analyze the collective dislocation activities (slip events) and work hardening during compression. This study provides new insights into dislocation-mediated plasticity in MgO, across different length scales, by systematically tuning dislocation density.

cond-mat.mtrl-sci↗

arXiv2025

Magnetic properties of $R$Rh$_6$Ge$_4$ ($R$ = Pr, Nd, Sm, Gd-Er) single crystals

Single crystals of $R$Rh$_6$Ge$_4$ ($R$ = Pr, Nd, Sm, Gd - Er) were synthesized using a Bi flux and their physical properties were characterized by magnetization, resistivity, and specific heat measurements. These compounds crystallize in the noncentrosymmetric LiCo$_6$P$_4$-type structure (space group $P\bar{6}m2$), where rare-earth atoms form a triangular lattice in the $ab$-plane and chains along the $c$-axis. PrRh$_6$Ge$_4$ and ErRh$_6$Ge$_4$ do not exhibit magnetic transitions above 0.4 K. NdRh$_6$Ge$_4$ and SmRh$_6$Ge$_4$ are ferromagnets, while GdRh$_6$Ge$_4$ and DyRh$_6$Ge$_4$ show antiferromagnetic transitions, \red{whereas HoRh$_6$Ge$_4$ is a ferrimagnet}. In addition, DyRh$_6$Ge$_4$ shows multiple transitions and magnetization plateaus when a magnetic field is applied along the $c$-axis. In SmRh$_6$Ge$_4$, like the Ce counterpart, the crystalline-electric field (CEF) effect leads to an easy plane anisotropy, while in other compounds it gives rise to a pronounced uniaxial anisotropy.

cond-mat.str-el↗

arXiv2025

Critical fluctuations and conserved dynamics in a strange ferromagnetic metal

The origin of the strange metallic behavior observed in a wide range of quantum materials is an open challenge to condensed matter physics. Historically, strange metals were uniquely associated with antiferromagnetic quantum critical points (QCPs), but a new generation of materials reveals their association with uniform order parameters, such as ferromagnetism, valley or nematic order, suggesting a deeper common denominator. At a QCP, order parameter fluctuations are characterized by the dynamical critical exponent $z$, which quantifies the space-time scaling asymmetry. Here, we report the observation of a divergence in the Grüneisen ratio at the QCP of the strange-metal ferromagnet CeRh$_6$Ge$_4$ with a dynamical critical exponent $z=3$, signaling that the underlying quantum singularity involves a conserved degree of freedom. Yet the magnetization of this easy-plane ferromagnet is not conserved. We argue that the $z=3$ strange criticality requires a description beyond the Landau paradigm, proposing a link with the gauge modes of the small-to-large Fermi surface transition and the associated gauge charge of the delocalizing heavy electrons.

cond-mat.str-el↗

arXiv2025

Token-Level Inference-Time Alignment for Vision-Language Models

Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence, yet their outputs remain prone to hallucination-plausible text misaligned with visual inputs. Existing alignment approaches often rely on expensive fine-tuning with annotated preference data or sequence-level inference strategies that provide only coarse, delayed feedback. To overcome these limitations, we present TITA (Token-level Inference-Time Alignment), a lightweight framework that freezes the base VLM and instead trains a reward model to approximate its distribution. During inference, implicit preference signals are extracted as log-probability ratios between the reward model and the target VLM, yielding dense autoregressive feedback. This formulation can be viewed as an inference-time variant of Direct Preference Optimization (DPO), providing token-level corrective signals without retraining the backbone. Extensive evaluations on LLaVA-1.5-7B and 13B show consistent gains across 12 benchmarks, with improvements of 8.6% on MMVet and 6.7% on POPE, indicating stronger general understanding and reduced hallucinations. Additional experiments on Qwen2.5-VL-7B and DeepSeek-VL2-27.5B show comparable gains, especially in hallucination reduction and VQA accuracy, while incurring negligible inference overhead.

cs.CV↗

arXiv2025

Toughening beta-Ga2O3 via mechanically seeded dislocations

\b{eta}-Ga2O3 is a promising candidate for next-generation semiconductors, but is limited by its intrinsic brittleness, which hinders its application in flexible electronics and high-precision devices. This study explores a new approach to improving the damage tolerance of (001)-oriented \b{eta}-Ga2O3 by introducing mechanically seeded dislocations via surface scratching. By applying a Brinell indenter to scratch the surface along the [100] direction, we effectively generate edge-type dislocations belonging to the (011)[01-1] and/or (0-11)[011] slip systems within a mesoscale wear track. Through a combination of nanoindentation tests, surface morphology analysis, and microstructural characterization using scanning electron microscopy (SEM) and transmission electron microscopy (TEM), we reveal that the introduction of dislocations significantly mitigates the formation of cleavage cracks during indentation, in contrast to that observed in as-received \b{eta}-Ga2O3. The mechanically seeded dislocations in the subsurface layers play an important role in preventing brittle fracture by facilitating stable plastic deformation.

cond-mat.mtrl-sci↗

arXiv2025

Fibring structures of ideals in Roe algebras and their $K$-theories

In this paper, we investigate the ideal structure of Roe algebras for metric spaces beyond the scope of Yu's property A. Using the tool of rank distributions, we establish fibring structures for the lattice of ideals in Roe algebras and draw the border of each fibre by introducing the so-called ghostly ideals together with geometric ideals. We also provide coarse geometric criteria to ensure the coincidence of geometric and ghostly ideals and calculate their $K$-theories, which can be helpful to analyse obstructions to the coarse Baum-Connes conjecture on the level of ideals.

math.OA↗

arXiv2025

Dislocation-enhanced piezoelectric catalysis of KNbO3 crystal for water splitting

Dislocations in oxides with ionic/covalent bonding hold the potential of harnessing versatile functionalities. Here, high-density dislocations in a large plastic zone in potassium niobate (KNbO3) crystals are mechanically introduced by room-temperature cyclic scratching to enhance piezocatalytic hydrogen production. Unlike conventional energy-intensive, time-consuming deformation at high temperature, this approach merits efficient dislocation engineering. These dislocations induce local strain and modify the electronic environment, thereby improving surface reactivity and charge separation, which are critical for piezocatalysis. This proof-of-concept offers a practical and sustainable alternative for functionalizing piezoelectric ceramics. Our findings demonstrate that surface-engineered dislocations can effectively improve the piezocatalysis, paving the way for efficient and scalable piezocatalytic applications.

cond-mat.mtrl-sci↗

arXiv2025

Nodeless superconductivity in 4H$_{b}$-TaS$_{2}$ with broken time reversal symmetry

The transition metal dichalcogenide 4H$_{b}$-TaS$_{2}$ exhibits characteristics of topological edge modes and two-component superconductivity with time-reversal symmetry breaking (TRSB). The nature of the superconducting order parameter is a crucial issue that requires experimental investigation. Here, we report measurements of the magnetic penetration depth using a tunnel-diode-oscillator based technique, as well as the specific heat. Both the specific heat and the change in magnetic penetration depth ($Δ$$λ$(T)) display an exponentially-activated temperature dependence, providing evidence for nodeless superconductivity in 4H$_{b}$-TaS$_{2}$. Moreover, the deduced superfluid density can be well described by a two-gap $s$-wave model, and such multigap superconductivity is consistent with there being multiple bands crossing the Fermi energy. These results constrain the possible pairing symmetries of 4H$_{b}$-TaS$_{2}$.

cond-mat.supr-con↗

arXiv2025

Effective reduction in thermal conductivity by high-density dislocations in SrTiO3

Decreasing thermal conductivity is important for designing efficient thermoelectric devices. Traditional engineering strategies have focused on point defects and interface design. Recently, dislocations as line defects have emerged as a new tool for regulating thermal conductivity. In ceramics-based thermoelectric materials, the key challenge lies in achieving sufficiently high-density dislocations to effectively scatter phonons, as the typical dislocation density in ceramics after bulk deformation is constrained to 10 to the power of 12 per square meter. In this work, we adopted the mechanical imprinting method and achieved a dislocation density of 10 to the power of 15 per square meter in single-crystal SrTiO3, which is known for its room-temperature plasticity and acts as a promising material for thermoelectric applications. Using the time-domain thermoreflectance (TDTR) method, we measured about a 50% reduction in thermal conductivity over a broad temperature range (80 to 400 K) with the engineered high-density dislocations. These results suggest that tuning dislocations could offer a new path to minimizing thermal conductivity for engineering thermoelectric materials.

cond-mat.mtrl-sci↗

arXiv2025

Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

Quantized large language models (LLMs) have gained increasing attention and significance for enabling deployment in resource-constrained environments. However, emerging studies on a few calibration dataset-free quantization methods suggest that quantization may compromise the safety capabilities of LLMs, underscoring the urgent need for systematic safety evaluations and effective mitigation strategies. In this paper, we present comprehensive safety evaluations across various mainstream quantization techniques and diverse calibration datasets, utilizing widely accepted safety benchmarks. To address the identified safety vulnerabilities, we propose a quantization-aware safety patching framework, Q-resafe, to efficiently restore the safety capabilities of quantized LLMs while minimizing any adverse impact on utility. Extensive experimental results demonstrate that Q-resafe successfully re-aligns the safety of quantized LLMs with their pre-quantization counterparts, even under challenging evaluation scenarios. Project page is available at: https://github.com/Thecommonirin/Qresafe.

cs.LG↗

arXiv2025

Asymptotic expansion for groupoids and Roe type algebras

In this paper, we introduce a notion of expansion for groupoids, which recovers the classical notion of expander graphs by a family of pair groupoids and expanding actions in measure by transformation groupoids. We also consider an asymptotic version for expansion and establish structural theorems, showing that asymptotic expansion can be approximated by domains of expansions. On the other hand, we introduce dynamical propagation and quasi-locality for operators on groupoids and the associated Roe type algebras. Our main results characterise when these algebras possess block-rank-one projections by means of asymptotic expansion, which generalises the crucial ingredients in previous works to provide counterexamples to the coarse Baum-Connes conjecture.

math.OA↗

arXiv2025

Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense

Large Language Models (LLMs) have showcased remarkable capabilities across various domains. Accompanying the evolving capabilities and expanding deployment scenarios of LLMs, their deployment challenges escalate due to their sheer scale and the advanced yet complex activation designs prevalent in notable model series, such as Llama, Gemma, Mistral. These challenges have become particularly pronounced in resource-constrained deployment scenarios, where mitigating inference bottlenecks is imperative. Among various recent efforts, activation approximation has emerged as a promising avenue for pursuing inference efficiency, sometimes considered indispensable in applications such as private inference. Despite achieving substantial speedups with minimal impact on utility, even appearing sound and practical for real-world deployment, the safety implications of activation approximations remain unclear. In this work, we fill this critical gap in LLM safety by conducting the first systematic safety evaluation of activation approximations. Our safety vetting spans seven state-of-the-art techniques across three popular categories (activation polynomialization, activation sparsification, and activation quantization), revealing consistent safety degradation across ten safety-aligned LLMs. To overcome the hurdle of devising a unified defense accounting for diverse activation approximation methods, we perform an in-depth analysis of their shared error patterns and uncover three key findings. We propose QuadA, a novel safety enhancement method tailored to mitigate the safety compromises introduced by activation approximations. Extensive experiments and ablation studies corroborate QuadA's effectiveness in enhancing the safety capabilities of LLMs after activation approximations.

cs.CR↗

arXiv2025

$3d$ flat bands and coupled $4f$ moments in the kagome-honeycomb permanent magnet Sm$_{2}$Co$_{17}$

Rare earth permanent magnets (REPMs) with both localized moments and itinerant conduction bands are not only important for fundamental research but also have significant technological applications. In particular, Sm$_{\rm 2}$Co$_{\rm 17}$ is a prototypical high-temperture REPM, where the Co atoms form a kagome-honeycomb stacked lattice. Here we report synthesis of epitaxial Sm$_{\rm 2}$Co$_{\rm 17}$ films using molecular beam epitaxy and measurements of their momentum-resolved electronic structure from \textit{in-situ} angle-resolved photoemission spectroscopy. Our results unveil two flat bands from Co $3d$ orbitals near the Fermi level ($E_F$), one at $\sim$\,--300\,meV and another right at $E_F$, which arise from orbital-selective destructive interference and strong electron correlations, respectively. In addition, our results reveal that Sm $4f$ states are far away from $E_F$ (hence mostly localized) and exhibit an anomalous temperature dependence, caused by the $3d$-$4f$ magnetic coupling. Our findings provide direct spectroscopic insights to understand the strong uniaxial ferromagnetism in Sm$_{\rm 2}$Co$_{\rm 17}$ (and REPMs alike). Our work also opens avenues to explore flat-band physics near $E_F$ and emergent phenomena in correlated kagome-honeycomb lattices.

cond-mat.str-el↗