Searcharxiv⌕ Search

arXiv subjects

Xiaopeng Li

Publications and source records attributed to Xiaopeng Li.

At least 19 recordsLinked to original sources
arXiv2026

Feeling of Knowing in Large Language Models

Post-training updates change what large language models (LLMs) can answer, but may leave their answerability judgments misaligned. We study this knowledge-judgment desynchronization through functional feeling of knowing (FoK), which supports selective generation, retrieval triggering, and model routing without implying subjective experience. We propose two trainable channels: a knowledge channel that changes answerability and a FoK channel that judges the current knowledge state. Three stages train them: on-policy supervised fine-tuning (OP-SFT) updates knowledge from corrected on-policy answers; knowledge-delta FoK training (K$Δ$-FT) adapts judgments across intermediate knowledge states; and FoK-guided policy optimization (FGPO) trains the subsequent answer or explanation. Factual-QA experiments, cross-dataset evaluation, and three sequential updates show that explicit FoK alignment improves judgment quality on updated knowledge. MMLU and ARC-Easy separately assess capability preservation.

cs.AI↗
arXiv2026

GUI-Lens: Enabling Precise GUI Grounding for Off-the-Shelf VLMs via Coarse-to-Fine Cropping

GUI grounding maps natural-language instructions to click locations and is essential for reliable GUI agents. The task remains difficult on high-resolution, densely populated interfaces because a vision-language model (VLM) may recognize a requested control without locating it precisely enough for interaction. Most existing methods provide various forms of localization assistance, but still rely on a direct click prediction, allowing visual ambiguity or an inaccurate initial estimate to propagate to the final result. In this paper, we introduce GUI-Lens, a coarse-to-fine grounding framework that allows a general-purpose VLM to determine the target through active visual observations. Specifically, GUI-Lens extracts OCR text and detected UI components from the screenshot and presents their positions as coordinate references. Using the instruction, the current view, and these references, the VLM selects the region and scale of the next view, which is cropped and enlarged to provide finer visual details. This process continues over successively focused views until the target is determined. Proposed crops and clicks are checked against the instruction throughout the process, and the final local position is mapped back to the original screen coordinates. Experiments on five GUI grounding benchmarks and six general-purpose base models show that GUI-Lens consistently improves grounding accuracy, achieving up to 9.3 times the accuracy of direct grounding on ScreenSpot-Pro.

cs.CV↗
arXiv2026

Efficient Quantum Optimization via Dissipative False Vacuum Decay

Efficient quantum solvers for computationally hard problems are highly desirable for near-term quantum platforms. Here, we propose a cavity-based dissipative quantum solver for a class of NP-hard combinatorial optimization problems encoded in atomic-spin Hamiltonians with a few discrete single-spin-flip transition energies. We show that the cavity-based quantum solver exploits dissipative false-vacuum decay in configuration space to facilitate escape from metastable local minima in rugged energy landscapes. Numerical studies of MaxCut and Maximum Independent Set identify favorable parameter regions for ground-state preparation. Based on the finite-size scalings of the median mixing time and instance-averaged ground-state preparation probability, we estimate time complexities for our solver that are more favorable than those of standard Grover search. These results highlight cavity dissipation as a controllable resource for quantum optimization.

quant-ph↗
arXiv2026

Efficient Exploration for Iterative Nash Preference Optimization

Preference alignment is central to improving large language models (LLMs), but reward-based formulations can be restrictive when human preferences are non-transitive. Nash learning from human feedback (NLHF) addresses this limitation by modeling alignment as a preference game and seeking a Nash equilibrium. However, the learning-theoretic foundations of scalable NLHF remain limited: existing regret guarantees rely on explicit preference-model estimation and minimax oracles, whereas simpler iterative methods lack such guarantees. We study online iterative NLHF and identify exploration as a key obstacle. First, we show that standard iterative NLHF can incur an exponential dependence on the inverse KL-regularization parameter, demonstrating that implicit exploration through policy updates can be insufficient. We then propose Exploratory Nash Preference Optimization (ENPO), which combines a SFT-type regularization with adversarial policy exploration. ENPO eliminates this exponential dependence without requiring minimax oracles or explicit preference-model estimation. We further introduce Bonus-Explorer ENPO (BENPO), which uses additional oracles to achieve an $O(\log T)$ regret bound. Finally, we develop Direct ENPO (DENPO), a practical variant of ENPO for fine-tuning LLMs. Experiments with Llama-3-8B-Instruct demonstrate consistent improvements over the evaluated RLHF and NLHF baselines across multiple benchmarks.

cs.LG↗
arXiv2026

GEMS-RAG: Graph-grounded Engineering Multimodal Standards Retrieval-Augmented Generation

Engineering standards are challenging knowledge sources for large language models (LLMs) because they are hierarchical, multimodal, and densely connected through figures, tables, cross-references, and normative rules. Existing retrieval-augmented generation (RAG) methods often rely on unstructured text retrieval and struggle with questions requiring joint reasoning over textual provisions, visual specifications, and document structure. We propose GEMS-RAG (Graph-grounded Engineering Multimodal Standards Retrieval-Augmented Generation), a framework for grounded reasoning over engineering standards. GEMS-RAG combines hierarchical parsing, fine-grained visual entity extraction, multimodal knowledge graph construction, and graph-grounded hybrid retrieval. Instead of treating figures as monolithic images, it decomposes them into meaningful visual entities linked to textual provisions, engineering concepts, and regulatory rules. During inference, dense, sparse, and visual retrieval are combined with graph expansion to identify relevant evidence across text, figures, and document structure. We evaluate GEMS-RAG on the Manual on Uniform Traffic Control Devices (MUTCD), a large engineering standard containing egulations, technical drawings, and standardized traffic-control devices. Results show that graph-grounded multimodal retrieval improves retrieval effectiveness and question-answering performance over text-only, multimodal, and graph-based RAG baselines. Beyond MUTCD, GEMS-RAG offers a general framework for reasoning over engineering codes, technical manuals, regulatory documents, and scientific standards in safety-critical applications.

cs.AI↗
arXiv2026

SAGE: A hybrid vision-language and geometry framework for work-zone pathway prediction under temporary traffic control

Temporary traffic control redirects vehicles through work zones, requiring automated vehicles to connect an interpretation of the visible devices to a continuous passing path. Geometric predictors can provide several plausible paths, yet selecting the one consistent with the temporary control remains difficult. We propose SAGE (Semantic-to-Action Grounded Execution), a read-decide-execute-check framework that separates path construction, path preference, and control compliance within a shared candidate space. The central idea is to use a vision-language model's (VLM's) trajectory as a preference over intact geometric candidates. A role-decoupled generator constructs the candidates, and rank fusion combines each candidate's geometric score with its agreement with the VLM trajectory. Supervision structured around the Manual on Uniform Traffic Control Devices (MUTCD) trains SAGE-VLM to state the lane status and hazard side before its passage decision and trajectory. The predicted hazard side enters image-space predicates derived from MUTCD provisions, which support a final intervention bounded in score and displacement. On 2,306 real-world ROADWork validation episodes, the candidates include a path within 10 px of the human demonstration in 87% of episodes, yet selection regret accounts for 53% of the geometric ranker's error. SAGE reduces average and final displacement errors by 8.3% and 12.0% relative to the ranker, mostly in the far field, and hard-constraint violations by 37%. The trajectory opinion improves all four tested generator-selector combinations. SAGE is comparable to state-of-the-art VLM modules in accuracy, with a faster-responding VLM, and outperforms four other adapted driving VLMs in displacement error and safety measures. Project page: https://hhjj233.github.io/SAGE-page/.

cs.CV↗
arXiv2026

Physics-Informed Koopman Learning for Data-Efficient System Identification of Automated Vehicle Dynamics

Understanding how a particular automated vehicle reacts to nearby traffic can improve motion prediction, control development, traffic simulation, and safety evaluation. However, commercial automated driving systems are proprietary, and single encounters may provide only a few seconds of noisy data. Standard physical models are interpretable but inflexible, whereas neural models are often data-hungry. We propose a physics-informed Koopman framework that combines a calibrated car-following law with a correction learned from the observations. A weak-form estimator learns this correction from velocity measurements integrated over time, avoiding noise-sensitive numerical differentiation. The resulting continuous-time model predicts the follower's response and provides interpretable measures of driving behavior. Experiments on OpenACC and CATS-CF evaluate 5-, 7-, and 11-second histories. Averaged over these histories, the constant-time-headway branch reduces speed prediction error by 16.0% and 15.4% on OpenACC and CATS-CF, respectively, relative to the best neural baselines. The PI-Koopman branches achieve the lowest mean speed and gap errors among the physical and neural comparators. Weak-form estimation reduces acceleration-field reconstruction error by 74.5% in noisy known-law simulations and noise-induced field perturbation by 91.6% in paired real-vehicle measurements. The same PI-Koopman system identification supports following-mode recognition with an approximately eleven-fold difference in median residual variance between human drivers and automated vehicles, and a single residual threshold achieves 85.4% balanced accuracy. The branch informed by the intelligent driver model takes a median 17 to 26 ms for identification and forecasting on the tested central processing units, supporting frequent target adaptation.

eess.SY↗
arXiv2026

ReuF2F: Benchmarking Coding Agents on Formalized Undergraduate Research Problems

As AI systems begin to resolve open research problems, reliable verification becomes increasingly important. Formal mathematics provides a trusted framework for mathematical reasoning, enabling agents to produce machine-checkable proofs while conducting mathematical exploration. Existing formal mathematics benchmarks often focus on known results or a small set of prominent open problems, which can become difficult to evaluate reliably once solutions are discovered and widely disseminated. Existing evaluation protocols are also not always aligned with how modern coding agents operate. We therefore introduce ReuF2F, a Lean 4 benchmark of 244 formalized open problems drawn from Research Experiences for Undergraduates (REU), spanning entry-level open research problems across a broad range of mathematical subfields. We expect these less prominent open problems, which tend to attract less attention and may remain unsolved for longer, to be better suited for held-out evaluation of end-to-end open problem resolution in Lean. We adopt a standard coding-agent evaluation setting, placing each problem and its logical negation into a Lean project in a Docker container. We also build Leanimum-agent on mini-SWE-agent to provide a unified harness for fair comparisons across models. Our evaluation finds that even the best-performing model resolves only ~40% of the problems, leaving substantial room for improvement on formalized open research problems.

cs.AI↗
arXiv2026

Learning Higher-Order Interactions from Incomplete Spatiotemporal Data with Mixtures of Hypergraph Laplacians

Traffic sensor data exhibit strong temporal and cross-sensor dependencies, yet long gaps erase both a sensor's local history and the joint observations needed to learn its relationships with other sensors. We introduce MoHL, a mixture of hypergraph Laplacians that learns group-wise relational structure directly from incomplete spatiotemporal data. MoHL discovers overlapping sensor groups from observed co-variation, constructs a Laplacian component for each interaction order, and learns their mixture through holdouts that mimic the missingness pattern. By sharing weights across group-induced couplings, MoHL pools scattered evidence instead of estimating each coupling independently. We characterize the induced weight-sharing structure and analyze the conditions under which sharing reduces estimation risk. Experiments on three traffic networks show that higher-order groups are most beneficial under long gaps, while support-matched comparisons demonstrate the advantage of shared weights when relational evidence is scarce. MoHL achieves the lowest error among the evaluated baseline methods under day-long gaps, with orders of magnitude fewer learned parameters than deep imputers. These results show how group-wise sharing can sustain reliable reconstruction precisely when missingness depletes the evidence needed to learn cross-sensor dependence.

cs.LG↗
arXiv2026

An Exact Branch-Price-and-Cut Algorithm for a Truck-as-Hub Vehicle Routing Problem with Drones

Rural last-mile logistics remains challenging because of sparse demand, limited road infrastructure, and long travel distances. We study a Truck-as-Hub Vehicle Routing Problem with Drones in Rural Areas, in which multiple trucks each carry a dedicated fleet of drones. Drone launch and retrieval are restricted to predesignated passive synchronization pads, where a visiting truck temporarily acts as a mobile hub, may dispatch multiple drones simultaneously, and must wait until all launched drones return before continuing its route. We formulate a mixed-integer quadratic programming model that jointly accounts for customer delivery delays, truck return times, and operating costs. To solve the problem exactly, we transform the original truck--drone network so that each feasible route can be represented as a single path and develop a branch-price-and-cut algorithm with tailored pricing, cutting, branching, and parallel-computing procedures. Computational experiments show that the proposed algorithm proves optimality for most large-scale test cases and achieves optimality gaps of no more than 4% for the remaining cases, whereas Gurobi reaches the 1,800-second time limit on all large-scale instances when applied directly to the compact formulation. Sensitivity analyses show that drone operating costs and managerial priorities substantially affect drone utilization and customer delays, providing practical guidance for balancing service quality and operating cost in rural delivery systems.

math.OC↗
arXiv2026

Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies

The memory capabilities of Large Language Models (LLMs) have garnered increasing attention recently. Despite great success achieved, existing retrieval-based memory approaches typically overlook the differences between memories and employ a unified strategy to process all memories, leading to suboptimal performance. Thus, an intuitive question arises: can we categorize memory into different types and select appropriate strategies? However, given the topic-rich, scenario-complex, and boundary-blurred nature of memory scenarios, achieving precise classification of memories is not easy. To address this challenge, we propose a memory multi-class dataset in this paper, termed TriMEM, which provides precise annotations for memory types across diverse scenarios. Building upon this foundation, we propose a novel memory framework, named MemoType, which can adaptively recognize each memory and query type with the learned router model. With the memory and query routing, MemoType can retrieve the memory with corresponding query types and design tailored retrieval strategies, thereby enhancing the retrieval performance. Moreover, we theoretically prove that any single retrieval strategy is subject to a fundamental upper bound on its expected retrieval precision in multi-class corpora, leading to systematic precision degradation. Extensive experiments on three datasets demonstrate that MemoType consistently outperforms existing methods, achieving up to 16.18% improvement in Recall@1.

cs.AI↗
arXiv2026

Generative AI for Autonomous Driving: Frontiers and Opportunities

Generative Artificial Intelligence (GenAI) constitutes a transformative technological wave that reconfigures industries through its unparalleled capabilities for content creation, reasoning, planning, and multimodal understanding. This revolutionary force offers the most promising path yet toward solving one of engineering's grandest challenges: achieving reliable, fully autonomous driving, particularly the pursuit of Level 5 autonomy. This survey delivers a comprehensive and critical synthesis of the emerging role of GenAI across the autonomous driving stack. We begin by distilling the principles and trade-offs of modern generative modeling, encompassing VAEs, GANs, Diffusion Models, and Large Language Models (LLMs). We then map their frontier applications in image, LiDAR, trajectory, occupancy, video generation as well as LLM-guided reasoning and decision making. We categorize practical applications, such as synthetic data workflows, end-to-end driving strategies, high-fidelity digital twin systems, smart transportation networks, and cross-domain transfer to embodied AI. We identify key obstacles and possibilities such as comprehensive generalization across rare cases, evaluation and safety checks, budget-limited implementation, regulatory compliance, ethical concerns, and environmental effects, while proposing research plans across theoretical assurances, trust metrics, transport integration, and socio-technical influence. By unifying these threads, the survey provides a forward-looking reference for researchers, engineers, and policymakers navigating the convergence of generative AI and advanced autonomous mobility. An actively maintained repository of cited works is available at https://github.com/taco-group/GenAI4AD.

cs.CV↗
arXiv2026

How corner is a corner case? Percentile control for highway scenario generation

Generating corner-case scenarios with appropriate adversity in a simulation environment is critical for testing an autonomous vehicle (AV) software stack's safety performance before deployment. Existing autonomous-driving scenario generators can enforce specific behavior, adversity, or feasibility conditions, but they provide limited control over how extreme a generated scenario is relative to plausible futures in the same traffic context. This study represents the adversity of a generated scenario as its percentile in the conditional distribution of future risk given the observed history. This view supports calibrated answers to two questions: how "corner" a generated corner-case scenario is and how its "cornerness" can be fine-tuned. To this end, we formulate history-conditioned risk-percentile requests and learn a reference risk distribution that maps each requested percentile to a physical risk target. We then use a percentile-conditioned joint diffusion model with sampling-time risk guidance to generate multi-agent futures, together with a reference-based criterion for evaluating percentile realization. Experiments use the minimum post-encroachment time (PET) between the ego and its surrounding vehicles as the risk surrogate on highD. On the primary evaluation set, our method realizes 1,422 of 1,440 requests within a 0.05 percentile tolerance (98.75%), with mean percentile error 0.00673 and PET-target error 0.00991 seconds. The resulting interface connects context-relative risk specification, physical realization, and evaluation through a common risk scale. Project website and videos of generated scenarios are available at https://hhj233.github.io/CornerPercentile/.

cs.AI↗
arXiv2026

Theory of the Edge-of-Chaos Advantage in Quantum Reservoir Computing

Numerical studies suggest that quantum reservoir computing performs optimally near the edge of chaos, a behavior commonly attributed to a balance between memory retention and nonlinear information processing. Here we develop an explicit quantum reservoir model and rigorously analyze its chaotic regime and integrable point. In the chaotic regime, we show that Gaussian-unitary-ensemble statistics lead to rapid memory loss: learning performance decays exponentially with the storage time required by a temporal task. This decay limits the ability of chaotic reservoirs to learn long-range temporal dependencies. At the integrable point, described by a free-fermion model, we prove that amplitude encoding and a linear readout of fermionic two-point correlations cannot learn a representative class of nonlinear tasks coupling present and past inputs. Introducing interactions alleviates this obstruction. By identifying distinct limitations on memory retention in the chaotic regime and nonlinear processing at the integrable point, our analysis provides a theoretical basis for the observed edge-of-chaos advantage and guides the design of quantum reservoirs for temporal learning.

quant-ph↗
arXiv2026

Entanglement-Induced Resilience of Quantum Dynamics

Quantum many-body devices suffer from imperfections that destabilize dynamics and limit scalability. We show that the dynamical growth of entanglement can intrinsically protect generic quantum dynamics against coherent and perturbative noise. Through rigorous theoretical analysis of general quantum dynamics and numerical simulations of spin chains and fermionic lattices, we prove that entanglement-entropy growth confines the influence of local Hamiltonian perturbations, thereby suppressing errors in dynamical errors. The degree of protection correlates quantitatively with the entanglement entropy of subsystems on which the perturbations act, and applies broadly to both analog quantum simulators and real-time control protocols. This entanglement-induced resilience is conceptually distinct from quantum error correction or dynamical decoupling: it passively leverages native many-body correlations without additional qubits, measurements, or control overhead. Our results reveal a generic mechanism linking entanglement growth to dynamical stability and provide practical guidelines for designing noise-resilient quantum devices.

quant-ph↗
arXiv2026

EvoSkillRec: Skill-Genome Evolution for Recommender Architecture Discovery

Modern recommender systems advance not only by scaling data and parameters, but also by encoding task-specific inductive biases through architecture, including sparse feature interactions for click-through rate (CTR) prediction, temporal attention for sequential recommendation, and expert routing for multi-task learning. However, these biases are typically human expert designed or searched within predefined operator spaces. Although Recent LLM-driven code evolution expands this space, unconstrained edits often produce invalid or ineffective architectures, underuse established architecture design knowledge, and fail to preserve successful innovations for reuse. We introduce EvoSkillRec, a promotion-and-reuse framework for cumulative recommender architecture evolution. It first decomposes recommenders into atomic executable skills and represents architectures as typed skill genomes, with each skill equipped with input--output types, semantic annotations, and implementation code. We then evolve models with different tasks through two coupled spaces: a constrained skill--space that mutates, recombines, specializes, and reuses validated skills, and an open-ended code--space in which LLM planners and synthesizers invent new skill modules using prior evolution traces and accumulated experience. An autoresearch controller evaluates candidates, diagnoses failures, retrieves relevant skills, promotes validated innovations into the skill library, and adaptively allocates the proposal budget between the two spaces. Extensive experiments on CTR prediction, multi-task learning, and multi-domain learning, including resource-constrained co-optimization of predictive quality and model FLOPs utilization in generative ranking models, consistently demonstrate the effectiveness of our proposed EvoSkillRec.

cs.IR↗
arXiv2026

Persona Following Is Not Selective Control: The Neutrality Gap in LLM User Simulation

Persona prompting is widely used to construct user simulations with large language models (LLMs), yet it relies on a largely untested assumption: specifying one user attribute should change that attribute alone. We test this assumption and identify a systematic failure of selective control: across all eight black-box LLMs we audit, changing a target attribute also shifts responses on unspecified, non-target attributes. For example, describing a user as more risk-seeking shifts color choices, even though the prompt never mentions color; we term this cross-attribute influence. Semantic, contextual, and internal analyses collectively suggest that models treat a persona prompt as evidence about the user and extend the inferred profile to unspecified preferences, a process we call trait-conditioned completion. We next ask whether explicitly specifying non-target attributes restores selective control. When a non-target attribute is assigned a clear direction, models generally follow the declaration and suppress the target attribute's influence. However, when the same attribute is declared neutral, the target continues to affect choices across all five open-weight checkpoints, even when the model correctly reports the declared state. This disparity, the neutrality gap, demonstrates that successful persona following does not imply selective persona control, which additionally requires keeping non-target attributes stable. We operationalize this distinction with a three-state diagnostic that leaves the non-target attribute unspecified or declares it directional or neutral; because directional tests can be passed by simply following the stated persona, the neutral state reveals failures they miss. In a post hoc analysis of independent items, neutral declarations leave 51-81% of items target-sensitive, against at most 1 of 320 item-pole comparisons under directional ones.

cs.AI↗
arXiv2026

AURORA: A Natural Language-Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air-Ground Co-Simulation

Air-ground transportation research increasingly relies on co-simulation, yet constructing scenarios remains labor-intensive and difficult to validate. More importantly, a generated scenario may execute successfully while failing to realize the spatial, temporal, communication, or behavioral relationships requested by the user. This paper presents AURORA, a natural-language-driven agentic framework that treats air-ground scenario generation as a process of compilation with verification. Central to AURORA is the Air-Ground Scenario Graph (AGSG), a typed intermediate representation that explicitly connects agents, aerial missions, events, communication links, success conditions, and their cross-domain dependencies. This shared representation enables simulator-grounded parsing, joint road-airspace grounding, temporal planning, pre-execution feasibility checking, trace-based runtime verification, failure localization, and bounded repair within a unified workflow. We further introduce AURORA-Bench to evaluate not only whether generated scenarios execute, but whether they faithfully realize the requested interactions. Experiments across multiple language models show that structured execution substantially improves reliability, while runtime verification exposes silent failures that completion-based evaluation overlooks. Localized repair further resolves many violations without regenerating the entire scenario. The results show that reliable scenario generation requires verifying realized behavior, not merely executable code, and demonstrate the value of explicit intermediate representations for verifiable and repairable language-driven co-simulation.

cs.RO↗