arXiv subjects

Kexin Zhang

Publications and source records attributed to Kexin Zhang.

At least 19 recordsLinked to original sources

arXiv2026

TimeBraid: Unifying Time Series and Language for Understanding and Forecasting

We present TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation models through interleaved global residual attention layers. Each model inherits knowledge, instruction following, and reasoning from one side, continuous-signal perception and zero-shot forecasting from the other, and fuses the two in a shared representation space where both modalities are understood and generated. We study the design choices that make such unified modeling work: where to align the two representation spaces, how to ground language in temporal structure, how to balance understanding with generation, and how to keep joint optimization stable. The resulting recipe combines a unified prompting scheme for diverse time-series and text tasks, stabilized joint training, and supervision from 2.2M curated series--text pairs and 4.9M instruction-tuning samples. Across benchmarks spanning time-series perception, understanding, reasoning, and both context-aided and unimodal forecasting, TimeBraid remains competitive with far larger general-purpose models and task-specific counterparts.

cs.CL↗

arXiv2026

From the Task Boundaries of Narrative Text to Structural Anchoring, Uncertainty Triggers, and Cross-Calibration

Causal graphs represent structural relationships among variables, yet users must still interpret direction, mechanism, and adjustment conditions in relation to the task at hand. Prior work often compares explanation formats as fixed conditions and pays less attention to how users distribute reasoning across graphs, direct explanations, and stories. We developed CoNS-Explorer, which uses reviewed instructional DAGs/SCMs to maintain a shared causal-fact ledger and generate fact-matched direct explanations and contextualized stories. A controlled survey experiment ($N=240$) compared the two texts as complete presentation packages. In the primary GLMM, the Story condition had a positive but uncertain overall association with accuracy (OR $=1.55$, 95\% CI $[0.34,7.10]$, $p=.572$); a population-averaged GEE showed a significant positive effect (OR $=1.89$, 95\% CI $[1.02,3.48]$, $p=.042$). Task-type interactions localized the clearest advantage to total-effect adjustment. Story also significantly increased situational presence. In a separate system-task and interview study ($N=24$), participants freely used graphs, direct explanations, and stories across three causal models. They established structural anchors with graphs and numerical results, consulted text when direction was unclear, mechanisms were unfamiliar, or multiple paths competed, and checked their judgments against other representations or external evidence. Integrating the two studies, we develop a process framework of structural anchoring, uncertainty triggering, explanation routing, and cross-calibration, together with four testable design propositions for adaptive causal explanation.

cs.HC↗

arXiv2026

Solution for UCF UrbanTwin LUMPI Track: Sim-to-Real Urban LiDAR 3D Object Detection

We present our solution to the LUMPI track of the UCF UrbanTwin Sim2Real LiDAR Challenge at the 6th DriveX Workshop, ECCV 2026. The detector must be trained only on synthetic data and is evaluated on 50 held-out real LiDAR frames; a separate 50-frame synthetic submission is evaluated for point-cloud realism. Our method addresses the Sim2Real gap at three levels. First, we align synthetic scans to the 50k-point test density and build a 30k-record training pool using UT-LUMPI geometry, RangeLDM-based sampling diversification, rare-class copy-paste, and pedestrian-oriented augmentation. Second, complementary DSVT detectors and Car/Bus PointPillars specialists are trained under the same synthetic-only constraint. Third, predictions are integrated by class-aware routing, asymmetric agreement fusion, constrained residual-recall supplementation, class-coverage auditing, and selective box-size calibration. The realism branch is optimized independently with radial-density matching, weak affine calibration, and calibrated set mixing. The final submission obtains a Combined Score of 0.4692, a Detection Score of 0.1797, a Realism Score of 0.9035, and 3D mAP@0.5 of 0.1258.

cs.CV↗

arXiv2026

Solution for UCF UrbanTwin V2X-Real Track: Sim-to-Real Urban LiDAR 3D Object Detection

Bridging the simulation-to-reality gap in roadside LiDAR requires addressing several coupled discrepancies, including scene geometry, sampling density, return patterns, and pedestrian scale. This report presents a multi-source collaborative training and class-aware fusion framework for Sim2Real 3D detection. The method organizes digital-twin scans, diffusion-redrawn scans, density-stabilized scans, and pedestrian morphology-aligned samples into a unified training pool with complementary roles. Within a common DSVT detection formulation, source-specialized expert branches preserve those roles while optimizing for the same detection objective. At inference, a predefined class-aware fusion pathway integrates geometry-stable and calibration-aware branches for vehicles, sampling-complementary branches for trucks, and morphology-consistent evidence for pedestrians. A label-free point-cloud center blend then refines geometric localization. On the UrbanTwin V2X-Real hidden test set, the unified system achieves a combined score of 0.7421, with 3D mAP@0.5 of 0.4518 and a realism score of 0.8871. The results indicate that a stable, interpretable collaboration among data sources is more valuable than unconstrained aggregation of model outputs.

cs.CV↗

arXiv2026

Report of the 8th LSVOS Challenge: Complex and Multimodal Video Object Segmentation

This report summarizes the 8th Large-scale Video Object Segmentation (LSVOS) Challenge, held in conjunction with ECCV 2026. The challenge evaluates video segmentation in three complementary settings: complex semi-supervised video object segmentation on MOSEv2, text-guided referring video object segmentation on MeViSv2-Text, and audio-guided referring video object segmentation on MeViSv2-Audio. We describe the tasks and evaluation protocols and review the methods of the top three teams in each track. Across the nine leading solutions, foundation segmentation models are combined with target-aware memory, multimodal reasoning, explicit target-existence verification, agentic interaction, and corrective tracking. These systems illustrate a broader transition from single-model mask propagation toward modular pipelines that reason about object identity, query validity, and temporal reliability.

cs.CV↗

arXiv2026

ProtLingo: Efficient Protein Language Modeling via Conditional Memory and Expert Routing

Proteins perform diverse cellular functions, and even single amino-acid substitutions can alter stability, activity, or molecular interactions. Protein language models (PLMs) provide a scalable approach for modeling such sequence--function relationships from unlabeled sequences, but increasing the size of dense Transformer backbones often brings substantial computational cost without consistently improving mutation-sensitive prediction. We introduce ProtLingo, an efficient PLM framework that augments a pretrained single-sequence backbone with conditional local memory and sparse expert routing. ProtLingo maps contextual residue representations into route-specific discrete codes, composes centered local windows into latent $N$-gram addresses, and retrieves reusable residual signals associated with recurring local sequence contexts. In parallel, selected feed-forward blocks are upcycled into sparse Mixture-of-Experts layers with shared and routed experts, enabling residue-dependent computation while activating only a subset of parameters. Experiments on protein fitness prediction, FLIP benchmarks, and supervised contact prediction show that ProtLingo achieves competitive performance with a 150M-scale backbone, including strong parameter efficiency on mutation-effect prediction and preserved long-range structural representations.

cs.AI↗

arXiv2026

CompEvo: Competition-Induced Evolution for Multi-Agent in News-Driven Time Series Forecasting

News-driven time series forecasting uses evolving textual events together with historical observations to predict future values, supporting applications such as market risk monitoring and resource scheduling. In multi-agent settings, two challenges still remain. The first is degeneration of thought, where agents converge to similar evidence-seeking behaviors. The second is insufficient theoretical grounding, where strategy updates are often heuristic and lack a principled formulation. To address the above challenges, we propose CompEvo, a competition-induced evolution framework for multi-agent news-driven time series forecasting. For theoretical grounding, we introduce an evolutionary game formulation to guarantee equilibrium existence and optimization convergence. Building on this formulation, we construct a trainable multi-agent evolution framework that integrates strategy execution, fitness-based differentiable selection, and competition-induced strategy evolution. CompEvo enables heterogeneous agents to explore diverse news evidence, converts forecasting feedback into differentiable influence weights, and evolves agent strategies under competitive pressure to preserve effective logic while maintaining diversity. Experiments on four real-world datasets show that CompEvo reduces RMSE by 27.3% and MAPE by 26.2% on average over strong baselines. Further analysis indicates that CompEvo successfully maintains diverse and specialized agent behaviors.

cs.NE↗

arXiv2026

Superconducting gap in covalent bismuth dihydride BiH$_2$ under extreme conditions

Hydride superconductors at megabar pressures provide a promising platform for exploring room-temperature superconductivity. However, their superconducting gaps remain largely inaccessible to conventional spectroscopic due to diamond anvil cell constraints and minute sample dimensions. Here we develop a pulsed current method and apply it to covalent BiH$_2$ synthesized at 157--176 GPa. BiH$_2$ exhibits superconductivity at 58--70 K and upper critical fields of 11--17 T, substantially lower than those of many clathrate superhydrides, corresponding to a relatively long coherence length and an experimentally accessible critical current density. Short rectangular pulses minimize sustained Joule heating and enable currents up to 160 mA, allowing $J_c(T)$ to be measured in the low-temperature regime down to 2 K at 176 GPa. The normalized critical-current response remains reproducible between two measurement runs and is better described by a two-scale $s$-wave model than by single-gap $s$- or $d$-wave models, yielding effective energy scales of approximately 6.9 and 1.5 meV. Fully anisotropic Migdal--Eliashberg calculations yield a single highly anisotropic gap, suggesting that the two-gap behavior observed experimentally originates from gap anisotropy rather than two independent gaps. These results establish pulsed critical-current measurements as a practical gap-sensitive transport probe under extreme pressure and, with further increases in peak-current capability, provide a route toward investigating room-temperature hydrides such as La--Sc--H.

cond-mat.supr-con↗

arXiv2026

Beyond Harassment: Exploring the Harm Experienced by People with Disabilities in Social Virtual Reality

People with disabilities (PWD) are increasingly engaging in social virtual reality (VR) platforms, where immersive and embodied interactions can intensify negative experiences. While prior work has examined harassment in VR, little is known about the harms experienced by PWD and the perceived severity associated with different harassment and disability types. Unlike harassment, which represents behaviors, harm is more critical to designing effective protections, as it reflects the consequences and impact; the realism of VR and the vulnerability resulting from disability identity can further amplify such impact. To characterize and model harms for PWD, we conducted a literature review, followed by an online survey with 67 PWD to understand participants' harassment experiences and resulting harms in social VR. We identified 19 types of harm in 5 categories, and reported the severity perception of each type of harm. Finally, we analyzed our results from the critical disability theory perspective, summarized the uniqueness of harm in social VR, and discussed design implications for specialized safety mechanisms that mitigate harm for PWD.

cs.HC↗

arXiv2026

Asymptotics of the principal eigenvalue of an elliptic operator on closed and orientable Riemannian manifolds: small diffusion

This paper is concerned with the asymptotic behavior of the principal eigenvalue $λ(D)$ of the elliptic eigenvalue problem \[ -DΔ_{M}u - a\langle \nabla_M f, \nabla_M u\rangle_g + c u = λ(D)u, \] posed on a closed orientable Riemannian manifold $(M,g)$, in the small-diffusion limit $D \to 0^+$. Under the assumption that $f$ is a Morse function on $M$, we establish that the limiting value $\lim_{D\to 0}λ(D)$ is completely characterized by the critical points of $f$ and the associated Riemannian Hessian, specifically through the values of $c$ and the Riemannian Hessian eigenvalues at those points.

math.AP↗

arXiv2026

What to Distinguish and How? Opportunities and Challenges of Augmenting Multiple, Cluttered Objects in Complex Scenes for People with Low Vision

People with low vision (PLV) struggle to perceive complex scenes like busy kitchens and crowded streets, which contain many objects, visual clutter, and dynamic elements. Prior AR systems for low vision either enhance low-level visual features or augment task-relevant objects for single tasks in simple settings, leaving multi-object augmentation in complex scenes underexplored. Informed by a formative study characterizing important objects and their perceived importance for PLV, we built SceneGlance, a wearable AR system that recognizes important objects and visually distinguishes them by importance level. Through a controlled lab study with 12 PLV in a mock-up kitchen scene and a free-form think-aloud study with 13 PLV navigating an outdoor route, we found that AR distinction on object importance shifted PLV's attention toward objects of higher importance, and supported perception strategies such as building mental snapshots from the augmentation distribution and hierarchical scanning by importance. However, this attention shift came with a tradeoff of reduced overall scene recall. The studies also surfaced challenges posed by AR augmentations in complex scenes, such as adjacent augmentations blending or interfering with each other, yielding design implications for more practical AR vision enhancement systems in the complex real world.

cs.HC↗

arXiv2026

NavSight in the Wild: Understanding Real-World Use of a Mobile Augmented Reality Application for People with Low Vision in Outdoor Navigation

The ability to navigate outdoors safely and independently is crucial yet challenging for people with low vision (PLV). While various augmented reality (AR) systems for low vision have been designed and evaluated in ideal lab environments, no research has investigated their real-world feasibility and challenges. We present NavSight, a mobile AR application that assists PLV in outdoor navigation by recognizing important outdoor objects (e.g., curb, vehicle) and rendering real-time visual augmentations. Through a seven-day diary study with 12 PLV in real-world settings, we characterize the impact of NavSight on scene perception, users' configuration strategies on what objects to augment and how to augment them across scenarios, how users made sense of and responded to recognition errors, and the social acceptability of using NavSight in public. We further identify environmental factors affecting recognition, such as weather conditions, lighting and shadows, and nonstandard road markings and textures, as well as usability issues in daily use. We discuss these real-world challenges and derive design implications for future AI-powered assistive AR systems for outdoor use.

cs.HC↗

arXiv2026

Safety vs. Social Image: Co-Designing Protection Mechanisms Against Ableist Harassment with People with Disabilities in Social Virtual Reality

People with disabilities (PWD) increasingly use avatars to express disability identities in social virtual reality (VR), but greater visibility also invites targeted harassment. Existing safety features are often insufficient, overlooking PWD's experiences and needs. To address this gap, we co-designed protection mechanisms with 11 PWD to reveal their values and needs. Our research employed a social lens to interpret harassment behaviors and protection mechanisms. Inspired by Hall's Proxemics Theory that interpersonal distances indicate social intent and boundaries, we divided social VR spaces into four proxemic zones (Intimate, Personal, Social, and Public) and used them to structure our protection mechanism co-design. We also provided different protection mechanism probes (Inform, Educate, Consent, and Combat) to elicit participant preferences. Our study highlighted the role of social proximity in shaping PWD's harassment perception and protection preferences and revealing PWD's unique social values and needs (e.g., managing harassment with optimism and resilience, prioritizing social image over safety). We proposed design recommendations for protection mechanisms that protect PWD while maintaining their desired social images.

cs.HC↗

arXiv2026

Agreement-Based Audio-Visual Segmentation:Champion Report for the MeViS-Audio Track in the 8th LSVOS Challenge

The MeViS-Audio track asks a system to segment the objects described by a spoken motion expression throughout a video and to return empty masks when the described target is absent. We present a simple staged solution. Qwen3-ASR first converts speech into text. Several video mask tracks are then produced with complementary grounding and segmentation models. Instead of trusting a single prediction, we select the track that has the highest average mask agreement with the other candidates. A small set of explicit direction, count, and plural rules corrects queries that require more than ordinary single-object tracking. Finally, a video-level classifier combines visual, audio-visual, and within-video query scores to decide whether any target is present. The submitted system obtains 0.5952 J &F, 0.7931 no-target accuracy, 0.9205 target accuracy, and a final score of 0.769589. The challenge organizers notified our team that this result ranked first in the track.

cs.CV↗

arXiv2026

Evolution-Aware MSA Reasoning for Subsampling via Factor Graphs

Multiple Sequence Alignments (MSAs) provide protein language models with explicit evolutionary context, but their large depth makes subsampling unavoidable under limited token budgets. Existing strategies, including random selection, identity-based filtering, and diversity-driven sampling, are effective heuristics, yet provide limited control over the evolutionary signals retained in the subset. In this work, we recast MSA subsampling as an explicit optimization problem, where key evolutionary measures, including query identity and diversity, are treated as controllable objectives. Building on this view, we introduce AP-REASONER, an Affinity-Propagation-based factor-graph approach. With evolution-aware unary factors, exemplar-consistency factors, and two control knobs, AP-REASONER performs factor-graph reasoning through message passing to infer a fixed-budget MSA subset. Experiments on long-range contact prediction and conformational ensemble prediction show that AP-REASONER outperforms baseline subsamplers on structure-sensitive downstream tasks and enables controllable recovery of alternative protein conformations. These results highlight the value of modeling MSA subsampling as a controllable optimization problem, where factor-graph reasoning offers an effective alternative to heuristic selection.

cs.LG↗

arXiv2026

Intrinsically low thermal conductivity of stoichiometric lithium niobate:Experimental measurement and microscopic origin

With the rapid development of integrated electro-optic and nonlinear optical devices based on lithium niobate (LiNbO$_3$, LN), thermal management is becoming a critical area of focus. However, experimental measurement of thermal transport in stoichiometric LiNbO$_3$ (sLN) remains scarce, and the intrinsic microscopic mechanisms remain to be established. Here, we combine the laser pump-probe technique of frequency-domain thermoreflectance (FDTR) with state-of-the-art machine-learned atomistic simulations to comprehensively investigate thermal transport in sLN. The measured and simulated room-temperature thermal conductivity ($κ$) values of sLN agree well, which are orders-of-magnitude lower than that of many classic and emerging semiconductors such as silicon. Furthermore, the temperature-dependent $κ$ exhibits a $T^{-α}$ scaling with $α$ near unity, suggesting that thermal transport is dominated by intrinsic phonon-phonon scattering. By comparing sLN with cubic boron arsenide (cBAs) which serves as an ultrahigh-$κ$ benchmark, we reveal that harmonic properties are not responsible for the low $κ$ of sLN, which feature phonon heat capacity and group velocities that are either higher than or comparable to those in cBAs. Instead, the low $κ$ originates from substantially stronger anharmonicity and larger scattering phase space. These two factors collectively suppress phonon lifetimes by 1-2 orders of magnitude, leading to a maximum phonon mean free path of approximately 140 nm. As a result, notable size effects emerge in thin-film sLN below 1 $μ$m, with $κ$ dropping to half the bulk value at 10 nm. Altogether, our findings establish a fundamental understanding of thermal transport in sLN and provide atomistic insights for thermal management in advanced lithium niobate technologies.

cond-mat.mtrl-sci↗

arXiv2026

Parallel Complex Diffusion for Scalable Time Series Generation

Diffusion models learn data distributions indirectly through denoising, making the difficulty of generative modeling closely tied to the dependency structure of data. For time series, strong temporal dependence forces the noise / score estimator to recover highly entangled cross-time relationships, leading to the curse of entanglement. We mitigate this burden by changing the topology of the diffusion space: the Discrete Fourier Transform (DFT) decomposes temporal dependencies into spectral modes, diagonalizing second-order dependency structure and better aligning the data manifold with isotropic Gaussian noise and homogeneous diffusion dynamics. However, existing frequency-aware diffusion methods mainly use the DFT to design estimator blocks under temporal DDPM/SDE frameworks, while frequency-native diffusion paths face a mathematical barrier from complex-valued dynamics. We propose PaCoDi (Parallel Complex Diffusion), a frequency-native diffusion framework that constructs the diffusion path in the spectral domain while replacing the complex-valued estimator with parallel real-valued estimators for real and imaginary components. Theoretically, we prove the statistical orthogonality of spectral Gaussian noise, establish quadrature forward transitions and conditional reverse factorization, and extend discrete PaCoDi to continuous-time spectral SDEs through a Spectral Wiener Process. We further introduce a Mean Field Theory approximation with an Interactive Correction Branch to handle marginal coupling, and exploit Hermitian symmetry to reduce 50% attention FLOPs without information loss. Extensive experiments on unconditional and conditional time series generation demonstrate superior generative quality and computational efficiency against 5 SOTA baselines in 5 benchmarks, respectively. Code is available at https://github.com/RongyaoCai/PaCoDi.

cs.LG↗

arXiv2026

From Observations to States: Latent Time Series Forecasting

Deep learning has achieved strong performance in Time Series Forecasting (TSF). However, we identify a critical representation paradox, termed Latent Chaos: models with accurate predictions often learn latent representations that are temporally disordered and lack continuity. We attribute this to the dominant observation-space forecasting paradigm, where minimizing point-wise errors on noisy and partially observed data encourages shortcut solutions instead of the recovery of underlying system dynamics. To address this, we propose Latent Time Series Forecasting (LatentTSF), a paradigm that shifts TSF from observation regression to latent state prediction. LatentTSF employs an AutoEncoder to project each observation into a learned latent state space and performs forecasting entirely in this space, allowing the model to focus on learning structured temporal dynamics. We provide an information-theoretic analysis showing that the latent objectives can be motivated as surrogates for maximizing mutual information between predicted and ground-truth latent states and future observations. Extensive experiments on widely-used benchmarks confirm that LatentTSF effectively mitigates latent chaos, yielding consistent improvements in both forecasting accuracy and representation quality. Our code is available at https://github.com/Muyiiiii/LatentTSF.

cs.LG↗