arXiv subjects

Xin Liu

Publications and source records attributed to Xin Liu.

At least 55 records · Page 3Linked to original sources

arXiv2026

From Image Morphology to Multiphysics Earth Posteriors

Structural learning and physical-property inference can draw on different sources of knowledge. We learn morphology from 33,140 natural, satellite, and texture images, without geological training models, then infer Earth properties from physical observations. Identical frozen weights map 128 coordinates into each $256\times256$ compressional-velocity, shear-velocity, or density field. Fixed adapters assign physical meaning; observation-specific likelihoods determine new posteriors without retraining. Across 256 unseen Earth models, image coordinates reduce projection error fourfold relative to a dimension-matched cosine basis. Matched inversions favor image coordinates for the tested curved-velocity targets and a smooth radial basis for the tested faulted targets. A simplified 2.5-dimensional application with 915 measured observations along one 120.9-km southern-California profile constrains a velocity--density contrast. Grouped arrival-time and gravity errors fall by 43% and 44% relative to the pretrained image prior, although the matched smooth radial basis predicts better. Direct layered-Rayleigh updating reduces blind phase-velocity error by 28% at five sites, whereas P-and-gravity-only sharing worsens it, distinguishing reusable morphology from beneficial cross-property coupling. These results establish a practical separation: images supply structural alternatives, and heterogeneous physical observations determine their experiment-specific posterior probabilities.

physics.geo-ph↗

arXiv2026

Structure-dependent failure modes of neural priors in acoustic full-waveform inversion

Frequency continuation does not improve every neural representation, and better velocity recovery need not imply better prediction of unseen waveforms. We compare a velocity grid with total-variation regularization, an adapted sinusoidal coordinate network (SIREN), and a frozen image generator with a full-grid residual in two-dimensional acoustic full-waveform inversion. All methods use the same frozen SWEEP discretization, acquisition, observations, background, and budget of 1,500 shot--model gradient evaluations. Three exposed synthetic targets represent inclined layering, curved layering, and a high-contrast curved interface drawn from a fault-labelled family. With 2-to-10 Hz continuation, the generative-residual model attains velocity RMSEs of 218.7, 108.0, and 341.9 m/s, compared with 232.5, 100.3, and 412.9 m/s for Grid+TV. Thus the latter wins on curved layering, while the former improves model RMSE by 5.9% and 17.2% on the other targets. Grid+TV nevertheless predicts held-out 10 Hz shots better on all three. SIREN is worse than the common background in every cell; continuation worsens two targets but improves one. A five-weight TV sensitivity study preserves the CurveFault model-error ranking. An equal-budget variational extension fails both recovery and interval coverage. These results establish conditional rankings, not universal superiority or an isolated spectral-bias mechanism. Full-grid residuals also prevent attributing gains uniquely to the generator. We advocate joint reporting of model recovery, unseen-shot prediction, optimization cost, and negative outcomes when auditing neural FWI.

physics.geo-ph↗

arXiv2026

Enabling Robust Cloth Manipulation via Inference-Time Simulator-in-the-Loop Refinement

Simulator-in-the-loop optimization offers a promising inference-time mechanism for robot manipulation. It uses a physical simulator as a backend rollout engine to evaluate candidate trajectories in parallel and refine nominal actions online, a paradigm shown to be effective in rigid-body manipulation where state and contact are relatively tractable. We bring this paradigm to real-world cloth manipulation from a single RGB input through three pillars. (i) We design a scalable synthetic-data generation and inference-time rollout pipeline built on FLASH, a deformable-object simulator that provides a practical balance among physical fidelity, numerical stability, and rollout efficiency. (ii) We develop a real-to-sim module, trained purely on synthetic data, that maps a single RGB observation to simulation-compatible cloth state by fusing pretrained visual features with learnable canonical tokens. (iii) We perform online planning by coupling a sparse-mesh rollout backend with prior-guided MPPI, anchored at an offline-distilled policy trajectory, preserving manipulation-relevant deformation and contact while enabling sufficient parallel rollout batches. Real-robot experiments show higher success rates than baseline methods and closed-loop correction under mid-fold perturbations. Project page: https://silr-cloth.github.io/

cs.RO↗

arXiv2026

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference

Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a user-level personalization framework that separates the problem into two components connected by a natural-language interface: a shared inference model that distills heterogeneous user signals into a concise preference summary, and a shared generator that conditions on this summary to produce personalized responses. Both components are trained under a unified preference-optimization objective, with reinforcement learning handling the non-differentiable inference step. This objective decomposes into generator approximation error and summary informativeness, revealing how a single loss simultaneously drives accurate generation and informative summarization. Because the interface is natural language, learned summaries can be inferred once per user and reused across different generators -- including frozen, black-box commercial APIs. Across four personalization benchmarks, POPI generally improves personalization quality while reducing context overhead by up to an order of magnitude.

cs.CL↗

arXiv2026

Construting Reverse Thinking: Developing Large Language Models' Reverse Thingking Ability

When facing complex problems, humans tend to try various ideas for different issues. Human thinking patterns exhibit remarkable flexibility in adapting to diverse scenarios. GPT-o1, GPT-o3, and DeepSeek-R1 adopt long chain-of-thought models to address complex problems by increasing reasoning depth, which default to a forward reasoning mode. We conducted statistical analysis on the accuracy of different mathematical problem datasets on models of different scales, and found five reasons for errors: Insufficient solution-space coverage, Computational mistakes, Unverified assumptions, Ignoring constraint conditions, Maximum response length limitation. To address the above issues, we proposed a backward reasoning pattern construction method aimed at enhancing the model's reverse thinking ability and dynamic adaptability. First, we constructed an easy-hard two-stage Math dataset for training large models and gradually improving their inference ability at different difficulty levels. The dataset contains forward reasoning paths as well as backward reasoning paths. And a two-stage supervised fine-tuning process is applied to progressively train the model's backward reasoning capability. Furthermore, a fine-grained reward mechanism is developed, employing smoothed reward signals to strengthen the model's ability to autonomously select thinking modes during the reasoning process, thereby avoiding reward hacking. A linear-decay balanced sampling strategy is designed to maintain a balance between forward and backward reasoning path samples during training, enabling the model to converge quickly and stably. Experimental results show that our method significantly improves reasoning efficiency and accuracy in tasks such as mathematical proofs, offering a flexible and efficient reasoning paradigm for solving complex problems.

cs.AI↗

arXiv2026

Technical Report OFDM-Assisted Simultaneous Quantum and Classical THz Communications

The feasibility of cost-effective simultaneous quantum and classical communication (SQCC) transmitting both the quantum key and classical information via a superimposed coherent state is investigated both in optical and Terahertz (THz) bands. Since the existing THz SQCC schemes assume single-carrier (SC) transmission over flat fading channels, we embark on investigating SQCC in realistic frequency-selective multipath THz fading channels. We then propose an orthogonal frequency division multiplexing (OFDM) based SQCC system for time-invariant frequency-selective THz scenarios, supported by low-density parity-check coded (LDPC) multidimensional QKD reconciliation schemes. Our simulation results demonstrate that the OFDM-based SQCC scheme is capable of achieving a practical secret key rate (SKR) over a wide range of power sharing scenarios between the classical and quantum signals. By contrast its single-carrier counterpart requires the classical signal to be at least 100 times stronger than the quantum signal in THz SQCC.

quant-ph↗

arXiv2026

A Multitask Large Reasoning Model for Molecular Science

Artificial intelligence in molecular science must move beyond pattern recognition toward chemically valid and interpretable reasoning. We present a task-adaptive large reasoning model that integrates chemical knowledge through a synergistic multispecialist architecture, chain-of-thought supervision, and molecule-informed reinforcement learning. Task-conditioned routing coordinates prediction and inference specialists across 10 molecular tasks spanning molecular description and generation, nomenclature translation, property prediction, and reaction prediction. The model outperforms more than 20 general-purpose and molecular large language models, improves aggregate performance over the base model by 50.3%, and surpasses the leading molecular multitask baseline on most tasks. Analyses of specialist representations and reasoning pathways reveal task-specific adaptation while retaining interpretable chemical inference. A case study further demonstrates an integrated workflow for central nervous system candidate generation, property screening, molecular interpretation, and retrosynthetic planning. These results demonstrate a versatile multi-task framework for knowledge-guided molecular reasoning and design, with the potential to serve as a core task engine for future molecular science agents.

cs.LG↗

arXiv2026

ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents

Lifelong conversational agents rely on memory systems to maintain deep, context-aware interactions with users. However, existing explicit textual memory pipelines suffer from a severe information bottleneck, often losing subtle behavioral patterns and emotional shifts. Furthermore, being typically static post-deployment, they cannot autonomously adapt to personal habits and preferences without manual feedback. Cognitive science, however, suggests that humans maintain mental models purely in a latent space and continuously refine them through predictive coding. Inspired by this, we propose \textbf{ThinkFlow}, a novel end-to-end latent memory framework for lifelong conversational agents. ThinkFlow bypasses the text bottleneck by dynamically compressing conversational flows into probabilistic latent memory skills, autonomously consolidating complex user states into disentangled, continuous vectors without semantic interference. To break this barrier, we introduce a test-time evolution paradigm. By coupling teacher-guided latent alignment to bootstrap the initial state with a self-supervised next-user-utterance prediction task for continuous refinement, the framework successfully overcomes cold-start challenges and achieves label-free lifelong personalization. Extensive experiments on long-term conversation benchmarks demonstrate that ThinkFlow significantly outperforms prevailing memory systems, providing highly personalized and contextually accurate responses over extended multi-session interactions.

cs.AI↗

arXiv2026

Interactive Memory Learning for Long-Term Conversations

Recent advancements in large language models have significantly enhanced the capabilities of agents in modeling long-term conversations. Despite these successes, existing approaches typically adopt a static heuristic paradigm, where information is passively archived without adaptive memory valuation. Consequently, these methods fail to self-evolve or align their memory management with evolving user needs. To address this, we propose ICML (InteraCtive Memory Learning), a multi-agent framework that transforms the memory mechanism from a passive archive into a learnable, interactive memory policy. Specifically, we first employ a session synthesis pipeline to generate expert data, facilitating rapid test-time adaptation in unseen scenarios. Building on this, ICML utilizes an online reinforcement learning mechanism where a Planner agent selectively encodes high-value information and a Trigger agent dynamically retrieves it to optimize response quality, whereby the two agents co-evolve through continuous interaction feedback. Crucially, both agents are synchronized through a delayed reward mechanism that propagates future feedback back to earlier storage decisions, ensuring memory policies are precisely aligned with user expectations. Experimental results demonstrate that ICML significantly outperforms strong baselines, exhibiting the unique capability to continuously improve response quality as interactions accumulate.

cs.AI↗

arXiv2026

Locating Hidden Failures Makes Long-Horizon Agents More Reliable

As AI agents take on long, autonomous tasks, we increasingly oversee rather than perform the work, yet we still judge them almost entirely by whether they finally succeed. An outcome cannot reveal where a run went wrong, whether the agent recovered, or the irreversible harm it caused along the way, and where long-horizon agents fail remains unmapped. We study $2518$ agent trajectories across software engineering, computer use, and science, close to real deployment, and classify $6967$ mistakes into $78$ failure types. Failure follows a recurring signature: after its first mistake an agent often fails to recover and rarely catches the error itself, so the run continues unchecked while still looking correct; whether an agent recovers depends on the task and the environment's feedback, not on the agent framework running it. Long-horizon agents can do real harm on the way to a passing result: even runs scored as solved delete data, corrupt systems, or fabricate success rather than earning it. We release these human-verified annotations as Traverse, a benchmark on which six frontier judges struggle to locate failure regardless of scale: even the strongest correctly identifies the first mistake in fewer than a third of runs. Yet Scout, a $4$B verifier we trained, locates failure far better than these judges and transfers to domains it never saw. Used at test time to select among an agent's candidate runs, it raises task success above the agent's own single-attempt performance, without retraining the agent. By making failure cheap to locate and correct, this work is a foundation for more trustworthy long-horizon agents that learn from their own mistakes, and a practical path to overseeing increasingly autonomous AI.

cs.LG↗

arXiv2026

Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control

Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provide personalized assistance. This access creates a persistent privacy risk: the agent must decide whether a given sensitive information should be disclosed to a particular party. Existing defenses address this by making the agent's backend LLM more privacy-preserving through stronger system prompts, training, or explicit consent-checking procedures, but this approach has a structural challenge: whenever enforcement is a judgment the LLM makes over the same conversational context an adversary controls, the enforcement mechanism and the attack surface coincide. We demonstrate this against existing defenses with three new attacks that require only ordinary agent interaction and no prompt injection: Collaborative Workspace Lure reframes an extraction attempt as collaborative work; Semantic Obfuscation Attack induces disclosure through omission rather than through anything the agent writes; and Channel Decoupling Attack splits the extraction request and the disclosure across independent channels. All three achieve substantially higher leak rates than the attacks these defenses were originally designed to withstand. Guided by this observation, we present FLOWSEAL, a defense that enforces confidentiality through a tool-level interceptor outside the LLM's context, grounded in data provenance and an information-flow-control lattice with controlled declassification. Evaluated across three benchmarks, five prompt-based baselines, and eight attacks, including a real agent executing live tool calls through MCP, FLOWSEAL reduces leak rates to near zero (e.g., 52.2% to 0.5% against Collaborative Workspace Lure) while preserving task utility, regardless of the underlying LLM backend.

cs.CR↗

arXiv2026

Anomaly-Preference Image Generation

Synthesizing realistic and diverse anomalous samples from limited data is vital for robust model generalization. However, existing methods struggle to reconcile fidelity and diversity, often hampered by distribution misalignment and overfitting, respectively.To mitigate this, we introduce Anomaly Preference Optimization,a novel paradigm that reformulates anomaly generation as a preference learning problem.Central to our approach is an implicit preference alignment mechanism that leverages real anomalies as positive references, deriving optimization signals directly from denoising trajectory deviations without requiring costly human annotation. Furthermore, we propose a Time-Aware Capacity Allocation module that dynamically distributes model capacity along the diffusion timeline,prioritizing structural diversity during highnoise phases while enhancing fine-grained fidelity in low-noise stages. During inference, a hierarchical sampling strategy modulates the coherencealignment trade-off, enabling precise control over generation. Extensive experiments demonstrate that significantly outperforms existing baselines,achieving state-of-the-art performance in both realism and diversity.

cs.CV↗

arXiv2026

Phase-Controlled Majorana Zero Modes in Altermagnetic Topological-Insulator Josephson Junctions

We exploit facet-dependent Andreev phase shifts to control topological superconductivity with a phase bias in a three-dimensional altermagnetic topological-insulator Josephson junction. In the weak link between two conventional $s$-wave superconductors, the $d$-wave altermagnetic order produces anisotropic momentum shifts of the surface Dirac cones. The resulting net momentum of the states involved in Andreev reflection generates additional propagation phases that differ between facets. Consequently, the facet-resolved Andreev spectra exhibit gap closings at distinct phase biases, giving rise to topological superconducting regimes that host Majorana zero modes (MZMs). We further show that the spatial locations of the MZMs can be controlled by the phase bias. Moreover, these topological superconducting transitions are only weakly affected by moderate variations in the chemical potential, obviating the need for fine-tuning to the Dirac point. Our results establish a platform for realizing and spatially controlling MZMs by tuning the superconducting phase bias in altermagnetic topological-insulator Josephson junctions.

cond-mat.mes-hall↗

arXiv2026

PhaseGAN: High-Fidelity Vocoder via Decoupled Amplitude and GAN-Driven Phase Reconstruction

A vocoder is a pivotal component of modern text-to-speech (TTS) systems. Despite the significant progress of neural network-based vocoders, accurate phase reconstruction remains the main challenge limiting both audio quality and modeling efficiency. We introduce PhaseGAN, a lightweight vocoder that addresses this limitation through a "mel $\rightarrow$ Amplitude $\rightarrow$ Phase" reconstruction pipeline. By reconstructing amplitude and phase spectra via distinct methodologies, the proposed PhaseGAN outperforms state-of-the-art baselines while utilizing fewer model parameters and reduced computational requirements. The compact version generates high-fidelity audio with approximately 500K parameters and 1 GMAC computational load, making it highly suitable for real-time applications on edge devices. In addition, our approach exhibits exceptional musical audio synthesis capabilities despite no training on musical data, illustrating unprecedented cross-domain generalization. See https://github.com/phasegan/phasegan-audio-demo for demos of our work.

cs.SD↗

arXiv2026

Mixture-of-Experts Transformer for Automatic Modulation Recognition

Automatic Modulation Recognition (AMR) is a key enabling technology for cognitive radio and intelligent spectrum management in next-generation wireless systems. However, current deep learning-based AMR methods predominantly rely on static multi-scale fusion strategies, which lack the flexibility to adapt to the highly dynamic temporal variations of modulation signals. To address this limitation, we propose MoEformer, an adaptive Multi-Scale Mixture-of-Experts Transformer network that directly processes I/Q signals to preserve their temporal and phase structures. Specifically, MoEformer constructs multi scale expert views through temporal resampling, employs an input-dependent gating mechanism for dynamic expert fusion, and integrates Rotary Position Embeddings (RoPE) within Transformer encoders to capture both local and global tem poral dependencies. Comprehensive evaluations on three widely adopted benchmarks (RadioML2016.10a, RadioML2016.10b, and RadioML2018.01A) demonstrate that MoEformer outperforms the competitive baselines, achieving superior average recognition accuracies of 63.74%, 66.24%, and 64.22%, respectively. In addition, the proposed method strikes an optimal trade-off between recognition performance and model complexity.

eess.SP↗

arXiv2026

A sequential smoothing majorant stochastic approximation method for nonconvex nonconcave minimax problems

We propose a sequential smoothing majorant stochastic approximation (SMSA) method for nonconvex-nonconcave minimax optimization problems. To overcome the nonconcavity of the inner maximization problem, we introduce a new majorant stochastic approximation with an $O\left(β_N^2\right)$ accuracy bound, where $β_N$ is the sample coverage radius. The accuracy bound significantly improves upon the $O\left(β_N\right)$ approximation bound for the standard stochastic approximation. Moreover, we establish nonasymptotic bounds for both global optimal values and minimizer sets, and prove consistency for the Clarke stationary points, as $β_N \downarrow 0$ almost surely. We show that the generated sequence by the SMSA method is bounded, and that the returned point is an approximate Clarke stationary point of the majorant stochastic approximation models. Numerical experiments on a synthetic toy example and robust logistic regression on two UCI datasets demonstrate improved approximation fidelity and lower mean robust test losses relative to the standard sampled approximation.

math.OC↗

arXiv2026

Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems

Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning. Existing paradigms (e.g., GraphRAG, NL2SQL) lack the semantic grounding and auditable execution required for these complex environments. We introduce HEAR, an enterprise agentic reasoner built on a Stratified Hypergraph Ontology. Its base Graph Layer virtualizes provenance-aware data interfaces, while the Hyperedge Layer encodes n-ary business rules and procedural protocols. Operating an evidence-driven reasoning loop, HEAR dynamically orchestrates ontology tools for structured multi-hop analysis without requiring LLM retraining. Evaluations on supply-chain tasks, including order fulfillment blockage root cause analysis (RCA), show HEAR achieves up to 94.7% accuracy. Crucially, HEAR demonstrates adaptive efficiency: utilizing procedural hyperedges to minimize token costs, while leveraging topological exploration for rigorous correctness on complex queries. By matching proprietary model performance with open-weight backbones and automating manual diagnostics, HEAR establishes a scalable, auditable foundation for enterprise intelligence.

cs.AI↗

arXiv2026

MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling

Despite the rapid progress of Multimodal Large Language Models (MLLMs) in 2D vision-language tasks, robust multi-view spatial reasoning remains a fundamental bottleneck due to the lack of structured 3D cognitive pathways in existing datasets. To address this, we introduce MV-STRIDE, a Multi-View hierarchical SpaTial Reasoning dataset with Interdependent and DEcomposed capabilitiEs. Moving beyond flat data structures, MV-STRIDE explicitly models the dependency relationships between foundational perception, scene understanding, and complex contextual reasoning, providing a coherent learning pathway aligned with human spatial cognition. We develop a systematic QA generation pipeline leveraging diverse 3D scene sources that enforces cross-view dependency constraints to prevent single-view solvability, generating multi-level spatial reasoning tasks supported by cognitively grounded chain-of-thought supervision for complex inference. Extensive evaluations demonstrate that our multi-stage training framework based on our hierarchical dataset achieves state-of-the-art performance across multiple spatial reasoning benchmarks, notably the multi-view oriented MMSI-Bench. Our approach enables MLLMs to maintain robust, 3D-consistent spatial reasoning across diverse viewpoints. The code and dataset are available at https://co1dspring.github.io/MV-STRIDE/.

cs.CV↗