arXiv subjects

Xin Zhao

Publications and source records attributed to Xin Zhao.

At least 19 recordsLinked to original sources

arXiv2026

One Assistant, Many Memories: Benchmarking Real-World Group Assistance When Recall Is Not Enough

The value of memory lies not only in recall but in using it to provide appropriate assistance. Recent benchmarks test memory use in personalisation and agentic tasks, but seldom evaluate assistance without fixed answers or integration across multiple participants. Group chats make both challenges more acute: an assistant must integrate information from multiple members, track revisions and conflicts over time, and produce one response for the group. Yet existing group memory benchmarks rely on synthetic conversations and inherit constrained evaluation from general memory benchmarks, focusing on recall against fixed answers or decisions over a closed set. We introduce GroupAssistBench, the first memory benchmark from real-world group conversations with a deployed group assistant, covering 80,299 messages in 50 groups and costing over $53K. Over the same histories, GroupAssistBench evaluates memory recall (L1) with reference answers and memory use (L2) with service requests without fixed answers across single, distributed, and conflicting memories (M1--M3). Requests are verified to require group history, memories are anchored to their sources, and L2 uses tailored rubrics with penalties derived from real user feedback. Across evaluations of frontier models with full context, retrieval methods, and memory systems, the strongest memory system rivals full context on recall but falls far behind on use, especially for distributed and conflicting memories. Together, two additions that relate retrieved memories and bind remembered facts as response constraints bring consistent gains, showing that group memory systems must improve use, not recall alone.

cs.CL↗

arXiv2026

MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model

Molecular structure elucidation from tandem mass spectra (MS/MS) is a central inverse problem in analytical chemistry. Most existing approaches to MS/MS identification remain tied to reference libraries or predefined candidate sets, whereas de novo methods aim to generate structures directly from spectra. A common de novo route predicts a molecular fingerprint from the spectrum and then decodes structures from it, enabling decoder pretraining on large molecule-only corpora. However, this paradigm creates a training-inference mismatch: the decoder is trained on oracle fingerprints computed from molecules, but at inference it is queried with a noisy spectrum-induced fingerprint posterior that is typically collapsed to a single thresholded fingerprint. We introduce MS-GPT, which recasts fingerprint-mediated de novo elucidation as spectrum-induced posterior querying of a conditional molecule-language model. MS-GPT conditions a molecule-language model on fingerprints and formulas, then converts the spectrum-induced posterior into a band of fingerprint queries near the oracle-fingerprint manifold through active-bit density calibration. Candidates sampled across this band are pooled and ranked by generation frequency and posterior similarity. A lightweight LoRA adapter further mitigates domain-specific posterior bias while preserving the pretrained molecular prior. On NPLIB1 and MassSpecGym, MS-GPT sets a new state of the art, reaching Top-1/Top-10 exact-match accuracy of 17.1%/27.6% and 10.2%/13.2%, respectively, and candidate-pool scaling improves recovery with a near-linear increase in inference cost. The source code and model checkpoints are available at https://github.com/VIKI623/MS-GPT.

cs.LG↗

arXiv2026

Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs

Remote sensing multimodal large language models (RS-MLLMs) have advanced aerial-image understanding, but scenario specialization remains constrained by scarce high-quality supervision and incomplete capability coverage. We propose filling before advancing (FBA), a capability-gap-driven post-training route that develops prerequisite capabilities before scenario-specific adaptation. For coastal harbor understanding, we construct CPRS (Coastal-Port Remote Sensing), a three-layer dataset covering RGB, SAR, PAN, and NIR imagery. FBA organizes supervision into RS semantic anchoring, multi-source bridging, and evidence-grounded scenario tuning. We also introduce HarborEval, an eight-track benchmark assessing perception, spatial understanding, robustness, and generation. Using the same final-task supervision pool, FBA raises the HarborEval score from 57.95 to 70.29 on LLaVA-v1.5 and from 81.09 to 83.37 on Qwen3-VL compared with Direct-SFT. It also outperforms collapsed training and leads the evaluated comparisons on harbor-related VRSBench and RSVQA subsets and expert-scored OpenEval. Stage-wise and supervision-replacement analyses examine the contributions of the supervision roles. A lightweight urban instantiation further supports cross-scenario applicability, with the proposed stage order achieving stronger overall performance than the tested alternatives. Project resources and release updates are available at https://github.com/Z0ngL1ng/filling-before-advancing.

cs.CV↗

arXiv2026

pper and Lower Bounds for Blow-up Times in Coupled Reaction--Diffusion Systems with Nonlocal Sources

In this paper, we consider the following reaction-diffusion system \begin{equation*} \begin{cases} u_t=Δu+F\bigl(x,t,u,v,V(t)\bigr), & (x,t)\in\Om\times(0,T), v_t=Δv+G\bigl(x,t,u,v,U(t)\bigr), & (x,t)\in\Om\times(0,T), \mathcal B u=\mathcal B v=0, & (x,t)\in\partial\Om\times(0,T), u(x,0)=u_0(x),\quad v(x,0)=v_0(x), & x\in\Om, \end{cases} \end{equation*} where \begin{equation*} U(t)=\int_{\Om}u(x,t)\dd x,\qquad V(t)=\int_{\Om}v(x,t)\dd x, \end{equation*} and the boundary operator $\mathcal B$ is either \[ \mathcal B_D w=w \qquad\text{or}\qquad \mathcal B_N w=\partial_νw, \] $\Om\subset\R^N$ be a bounded domain with sufficiently smooth boundary, $N\ge 1$, and $ν$ is the outward unit normal on $\partial\Om$. Under certain conditions, we obtain the upper and lower bounds for the blowup time of the solution to the system.

math.AP↗

arXiv2026

Spectra: Exact Component Transport for Test-Time Prior Adaptation in Simulation-Based Inference

Simulation-based inference (SBI) has become a powerful approach to Bayesian inference in complex scientific models whose likelihoods are difficult or impossible to evaluate. Amortized SBI learns reusable inference models from simulated data, enabling rapid posterior inference for new observations, and modern generative models have made these models increasingly expressive. However, this reuse is limited to the prior distribution chosen during training, whereas scientific analyses often need revised priors as knowledge accumulates or alternative assumptions are tested. We introduce Spectra, a test-time adaptation method for diffusion-based SBI. Spectra uses an exact score-transport identity to obtain the adapted score from a frozen diffusion model in closed form for structured prior changes, without additional simulation or training. Across six SBI benchmarks, Spectra achieves accurate adaptation under strong prior shifts at low online sampling cost. This enables pretrained SBI models to incorporate updated prior information at test time.

cs.LG↗

arXiv2026

Agentic ML Exploration (A-MLE) for Ads Ranking

Modern industrial ads ranking stacks are increasingly bottlenecked not by model capacity or training compute, but by the throughput of human ML iteration - the cycles of research, implementation, training, debugging, evaluation, and launch required to surface a single statistically significant improvement. A typical ranking stack contains numerous differentiated models with heterogeneous data, architectures, and infrastructure constraints, and each cycle takes days to weeks of senior engineer attention per model. As a result, techniques that have proven effective on one model diffuse into others slowly and unevenly, leaving substantial recoverable signal unexplored. We present Agentic ML Exploration (A-MLE), an autonomous LLM-agent system that systematically explores ML techniques across a portfolio of ads ranking models. A-MLE decomposes ML iteration into five stages involving hypothesis generation, exploration strategy, experiment execution, result analysis and shared knowledge substrate which are orchestrated by a single agent that invokes domain-specific skills and agentic workflows against a sandboxed execution layer, with human-in-the-loop checkpoints at each stage boundary. We deploy A-MLE across a representative set of large-scale ads ranking models and evaluate it along a tiered capability framework (tool availability, autonomous workflow execution, and open-ended exploration). We further report a controlled cross-LLM study using a fixed agent loop, which surfaces qualitative differences in execution reliability and exploration aggressiveness across the Claude Sonnet, Gemini, and GPT families. We discuss failure modes and the design choices that govern reliability. Our findings suggest that agentic exploration is a practical force multiplier for ML engineers in industrial recommenders, especially for the long tail of models that rarely receive expert attention.

cs.AI↗

arXiv2026

AdoDAS: A Privacy-Preserving Multimodal Challenge for Adolescent Depression, Anxiety, and Stress Assessment

Adolescent depression, anxiety, and stress (D/A/S) call for scalable tools that complement, rather than replace, professional evaluation. Under a privacy-preserving policy, the AdoDAS Grand Challenge withholds minors' raw recordings and distributes anonymized audio-visual representations and ASR-derived text. Its 6,000 participants provide 24,000 segments across one scripted-reading and three open-response sessions. Two tracks assess multi-task binary D/A/S screening and ordinal prediction of 21 DASS-21 item responses. From 191 registrations, the final leaderboards included 95 eligible screening teams and 64 item-prediction teams. Audio-visual baselines achieved 0.4604 mean F1 and 0.2675 mean Quadratic Weighted Kappa; leading submissions reached 0.5921 and 0.2776. Representative systems emphasize cross-session modelling, temporal multimodal fusion, psychometric structure, and task-aware calibration.

cs.MM↗

arXiv2026

Holographic SU(3) color superconductivity at finite baryon chemical potential

We present a holographic model of SU(3) color superconductivity (CSC) where a global color symmetry is spontaneously broken by a diquark condensate at finite baryon chemical potential. At $μ_b=0$, a systematic stability analysis over all SU(3) channels recovers the known SU(2) s+p competition. Based on that, the finite $μ_b$ further generalizes the s-wave order to an S1+iS2 structure. We find that $μ_b$ enhances the critical temperature of the S1+iS2 phase while suppressing the p-wave -- the latter vanishes beyond a certain $μ_b$ when backreaction is included. This opposite trend reshapes the phase diagram: with increasing $μ_b$, the balanced S+ phase (S1=S2) takes over the entire color-superconducting region. Our non-Abelian framework provides a concrete holographic description of global SU(3) symmetry breaking, relevant for understanding color-superconducting phases in dense QCD and may offer new insights into the physics of neutron-star interiors.

hep-th↗

arXiv2026

The FLARE Facility

The Facility for Laboratory Reconnection Experiments (FLARE) has been constructed to study magnetic reconnection in multiple X-line regimes relevant to space, astrophysical, and fusion plasmas. Building upon the successful design of the Magnetic Reconnection Experiment (MRX), FLARE features a larger physical volume, stronger magnetic fields, and an independent ohmic heating drive to significantly extend the accessible parameter space, targeting Lundquist numbers up to S ~ 10^5 and normalized system sizes up to λ~ 10^3. This paper details the facility's core engineering components, including the primary vacuum vessel, internal flux cores, highly segmented external coil systems, modular capacitor banks, and the safety interlock and control architecture. An initial diagnostic suite is presented, comprising high-resolution 2D magnetic probe arrays, triple Langmuir probes, a fully fiber-coupled interferometer, ion Doppler spectroscopy, and fast camera imaging. Initial operations demonstrate the device's experimental flexibility and reliability, successfully executing symmetric push-pull reconnection, spheromak merging, and asymmetric downstream configurations. Currently operating within "Stage 2.5" with S ~ 2,500 and λ~ 60 for anti-parallel reconnection, FLARE provides immediate access to the multiple X-line regimes. Planned hardware upgrades, advanced diagnostic additions, and integration with fully kinetic simulations will further expand its capabilities as it transitions into a collaborative user facility for the broader plasma science community.

physics.plasm-ph↗

arXiv2026

SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging personal information scattered across multiple applications (apps) to complete user instructions. However, due to the lack of dedicated benchmarks, their capabilities remain poorly understood. To address this gap, we introduce SPIEval, a human-curated benchmark grounded in five cognitive capabilities (i.e., reasoning, disambiguation, integration, preference inference, and multi-intent decomposition). SPIEval comprises 250 tasks spanning 4,335 personal records distributed across 10 apps and supports multi-turn interaction through 21 tools. Analysis shows that the benchmark exhibits diverse scenarios, challenging tasks, scattered information, controllable environments, and verifiable outcomes. We evaluate nine representative LLMs and find substantial room for improvement. The best-performing model, GPT-5.5 (xhigh), achieves only 57.3% accuracy, while the weakest achieves just 16.4%. Further analysis reveals that 79% of failures stem from inaccurate information localization, as LLMs often commit to plausible but incorrect information instead of continuing retrieval for verification. We also find that fewer than 2% of retrieval actions employ advanced search methods and observe substantial variation in search efficiency across models. These findings expose fundamental limitations of current LLM-based mobile assistants and motivate future research in this direction. Data and code are available at https://huggingface.co/datasets/Junjie-Ye/SPIEval.

cs.CL↗

arXiv2026

DTIF: Robust Loop Closure Detection via Delaunay Triangle Topology in Complex Forests

Accurate forest inventory and large-scale mapping are essential for ecosystem monitoring and sustainable forest management. Multiple low-cost edge platforms enable efficient large-area data acquisition, but merging independently constructed local maps in GNSS-denied understory environments still requires initialization-free loop closure detection and global registration. This task is challenging because low-cost LiDAR point clouds are sparse and noisy, while repetitive trunk layouts and the lack of distinctive geometric landmarks lead to severe perceptual aliasing and false correspondences. To address these issues, we propose DTIF (Delaunay Triangulation in Forests), a lightweight trunk-topology-based framework for forest loop closure detection and global registration. Tree trunks are first extracted as stable landmarks and encoded using a Delaunay topology for compact scene representation. Candidate submaps are then screened using edge-length and radius statistics, followed by edge--radius consistency verification and strong/weak vertex support aggregation to construct weighted vertex correspondences. Finally, topology-derived reliability weights are incorporated into a decoupled robust pose estimator that separately estimates yaw, horizontal translation, and elevation translation under gravity alignment. Experiments on simulated and real-world forest datasets demonstrate that DTIF achieves accurate registration with low computational overhead, providing a favorable balance among robustness, efficiency, and deployability on resource-constrained edge platforms.

cs.CV↗

arXiv2026

Support Thresholds, Not Algorithms, Limit Rare-Association Recovery in Co-Purchase Networks

The support threshold of the Apriori algorithm involves a trade-off in conducting market basket analysis: the associations that occur frequently are noted with high threshold; however, the low ones lead to generating the large amount of rules. The paper compares five methods for co-purchase edge filtration on two grocery datasets: i.e., Instacart (3.2 million baskets) and Dunnhumby (208 thousand baskets), including Apriori, Apriori + lift post-filtering, top-$K$ ranking based on lift, and two methods based on networks, noise-corrected (NC) and disparity filter (DF). The top-$K$ method ensures the maximum average lift, while the NC achieves similar lift level by means of a single value of the significance parameter ($α$). These two methods recover substantially more rare high-lift associations than Apriori (80-100% against 22-28%). NC and top-$K$ select meaningfully different edges (18-29% non-overlapping): NC retains statistically validated pairs, while top-$K$ retains rare pairs with high lift but low statistical significance. A rolling-origin holdout evaluation shows that top-$K$ edges recur at higher rates at every split, but NC edges are ~12 pp more likely to remain statistically significant in the held-out network.

cs.LG↗

arXiv2026

Re-Sonance: A Dysarthric Asynchronous Real-Time Speech Conversion System Based on a Three-Stage Cascaded ASR-LLM-TTS Architecture

Individuals with dysarthria face significant challenges in professional speaking scenarios such as conferences, presentations, and meetings, where real-time communication is crucial. While existing Augmentative and Alternative Communication (AAC) systems provide basic support, they often fail to meet the demands of professional speaking environments due to high latency and unnatural speech patterns. This paper presents Re-Sonance, a novel LLM-enhanced speech-driven AAC system designed for real-time professional speaking scenarios. By integrating Whisper ASR, Qwen LLM, and CosyVoice TTS, Re-Sonance achieves improved speech intelligibility and naturalness while maintaining real-time performance. Both subjective and objective evaluations using a Mandarin dysarthric speech dataset demonstrate that our speech reconstruction approach significantly improved intelligibility while preserving semantic coherence for speakers with mild to moderate dysarthria. Although performance remains limited for severe dysarthria cases, our findings validate the potential of LLM-based methods for enhancing speech-driven AAC systems, paving the way for more effective and accessible communication technologies.

cs.SD↗

arXiv2026

AE-UAV: An Air-to-Air Event-Based UAV Tracking Benchmark and a Real-Time Frequency-Domain Tracker

Air-to-air (A2A) unmanned aerial vehicle (UAV) tracking is fundamental to airborne remote sensing of low-altitude aerial targets. However, the deployment of continuous, real-time tracking systems on UAVs presents significant challenges. In A2A scenarios, traditional frame-based cameras suffer from severe performance degradation under low illumination, overexposure, and high-speed motion owing to their limited dynamic range and fixed temporal sampling. Although event cameras offer a promising alternative with microsecond temporal resolution and a high dynamic range, current research is bottlenecked by two primary issues: 1) the absence of dedicated A2A event-based datasets, and 2) the heavy reliance of existing trackers on GPU acceleration and extensive training data, rendering them impractical for resource-constrained UAVs. To bridge these gaps, we introduce AE-UAV, an air-to-air event-based UAV tracking benchmark. To the best of our knowledge, this is the first airborne-captured event camera dataset for A2A tracking, comprising 178 flight sequences with continuous-time cubic B-spline annotations. Furthermore, we propose the Fast-Slow Frequency-domain Tracking (FSFT) method. This lightweight, training-free framework seamlessly integrates frequency-domain template matching with search region prediction and detection-based drift correction. Extensive experiments demonstrate that FSFT operates at an ultra-fast 420 frames per second (FPS) on CPU-only hardware. It retains 93.97% of the accuracy of state-of-the-art GPU-dependent methods while delivering a 5.32-fold effective speedup and exhibiting superior temporal resolution generalization, thereby providing a highly efficient and robust solution for airborne remote sensing of aerial targets. The dataset and source code are available at https://github.com/MSP-xEN/AE-UAV.

cs.CV↗

arXiv2026

Chaotic particle dynamics near a traversable wormhole throat

This study investigates the nonlinear dynamics of a test particle near the traversable wormhole throat under an external harmonic potential. One-dimensional radial perturbation analysis shows that the particle is locally linearly stable at the equilibrium position. However, for two-dimensional and high-energy cases, the system exhibits a nonlinear response, leading to large-scale chaos. The analysis indicates that, if the particle is confined on one side of the wormhole, the Poincare section will still retain Kolmogorov-Arnold-Moser (KAM) tori under extremely high-energy conditions, which is distinct from the chaos caused by the event horizon in the black hole. By studying another set of shape functions, the universality of this phase space structure is confirmed. This research clarifies the unique nonlinear dynamical mechanism of a traversable wormhole. It provides a new criterion, based on chaotic dynamics, for identifying black hole mimickers in strong-field astrophysical observations.

gr-qc↗

arXiv2026

A Task-State Representation for Long-Horizon Mobile GUI Agents

While long-horizon mobile GUI agents typically rely on thought-action-observation loops, they struggle to separate persistent task states from transient screen observations. As execution histories grow, this entanglement imposes a severe context burden, causing agents to forget initial requirements, hallucinate progress, or repeatedly interact with stale interfaces. To address this, we introduce Task-State Representation (TSR), a training-free framework that explicitly decouples task state from sensory input. Acting as a lightweight external wrapper, TSR maintains three structured components: a global instruction summary, a dynamic progress tracker for subgoals, and a transition-aware action verifier. By continuously updating through pre- and post-action visual comparisons, TSR effectively guides the agent's reasoning without requiring architectural modifications. Experiments across four mobile GUI benchmarks validate TSR's effectiveness, yielding up to a 12 absolute point increase in success rate on complex cross-application and memory-intensive tasks.

cs.CL↗

arXiv2026

Metric Aggregation Divergence: A Hidden Validity Threat in Agent-Based Policy Optimization and a Contractual Remedy

Metric aggregation divergence (MAD) is the silent inconsistency that arises when distinct pipeline stages in an agent-based model coupled with a multi-objective evolutionary algorithm (ABM+MOEA) independently re-implement how an outcome metric is extracted from simulation trajectories. Unlike deliberate analytical choices, MAD operates at the level of pipeline architecture: each stage is internally coherent, and the inconsistency becomes visible only when cross-stage outputs are compared. Code inspection of EpidemiOptim, a JAIR-published epidemic policy toolbox, reveals three structurally independent aggregation paths in peer-reviewed code. A faithful replication of this structure produces champion disagreement in 64.2% of independent runs (n=500, 95% CI: [59.9%, 68.3%]). In a 300-seed policy-flip experiment, divergent aggregation causes the optimizer to recommend the wrong champion in 83% of replications, with a mean welfare gap of 2.19 units and a Gini inequality gap of 0.050 units. In a follow-up inference audit, 3 of 249 flipped seeds cross the significance boundary itself. A complementary enterprise follow-up produces the predicted null under near-commensurable rankings (rho = 0.991), while a public upstream rerun of the Lake Problem DPS workflow shows that the archived published-path recommendation reaches joint-threshold success 0.401 whereas a shared contract-path rule reaches 0.552. We introduce the metric contract - a single shared callable enforced at dispatch time across all pipeline stages - as the remedy. Framed as standard engineering discipline applied to the cross-stage metric interface, the contract eliminates divergence by construction with approximately 3% runtime overhead.

cs.MA↗

arXiv2026

HEAS: Hierarchical Evolutionary Agent-Based Simulation Framework for Multi-Objective Policy Search

HEAS is a Python framework that connects agent-based simulation, evolutionary search, and scenario-based evaluation in a single reproducible pipeline. It is designed for researchers who study systems where local interactions produce system-level outcomes-ecosystems, organizations, markets, or regulatory environments-and who need to search over candidate strategies and compare them across uncertain scenarios. HEAS combines three modules: a hierarchy runtime for composing simulations from reusable process layers, an evolutionary tuner for single- or multi-objective search backed by DEAP, and a game module for evaluating strategies across scenario ensembles. Its central design principle is the "metric contract": the same outcome function is shared by optimization, evaluation, and validation, so that different parts of an analysis cannot silently rank strategies by different quantities.

cs.MA↗