Search arXiv⌕ Search

arXiv subjects

Yang Zhang

Publications and source records attributed to Yang Zhang.

At least 91 records · Page 5Linked to original sources
arXiv2026

SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning

The unprecedented surge in Earth observation data volume and diversity has exposed a critical bottleneck for traditional manual workflows, catalyzing the emergence of Remote Sensing (RS) Agents. However, the practical deployment of these advanced agents is severely hindered by their heavy reliance on large-scale general-purpose LLMs, which lack deep domain expertise and impose prohibitive infrastructure demands. To resolve this, we propose SimCRAFT, a model-agnostic framework that distills sophisticated RS orchestration capabilities into a compact 7B-scale model. Addressing data scarcity, we first pair a multiagent synthesis engine with a Mock Execution Engine that checks schema correctness, inter-tool dependencies, and sensor/tool compatibility, producing SimRS-14k, a large-scale, constraint-validated workflow planning corpus. Second, we propose Contextual Retrieval-Augmented Fine-Tuning (CRAFT) that finetunes the model to reason analogically by adapting retrieved Standard Operating Procedures to novel queries under a noise-robust objective, generalizing RAFT to multi-step RS workflow planning without mechanical copying. Extensive experiments demonstrate that SimCRAFT-7B significantly outperforms openweights LLMs and rivals advanced closedsource models and specialized RS agents, while reproducing across three 7B backbones. This work contributes a competitive open-weights baseline for lightweight RS intelligence, enabling efficient autonomous deployment under resource-constrained or resource-conserving conditions.

cs.AI↗
arXiv2026

The Analyst in the Prompt: Role, Retrieval, and Memory Biases in LLM Financial Analysis

Large Language Models (LLMs) increasingly use user context such as memory, profiles, and role prompts to personalize their responses. This personalization can affect evidence-based judgment: the same evidence may lead to different conclusions under different user contexts. Finance provides a high-stakes setting to study this problem because decisions often depend on interpreting long and complex documents. We test this using 3,575 SEC filings across twelve LLMs. We compare persona-conditioned retrieval, neutral retrieval, and memory-framed context to separate the effect of evidence selection from the effect of interpretation. We find that most user-context spillover comes from how models interpret the same evidence under different roles, rather than from retrieving different evidence. We then test two simple mitigation strategies: expressing the same investor mindset as a user profile instead of an assistant role, and separating evidence-based and personalized outputs. Both reduce spillover, but neither removes it completely, and their effectiveness varies substantially across models.

cs.CL↗
arXiv2026

GazeTune: Facilitating Precise Gaze-Driven Interactions with Cascaded Touch Input

Eye gaze has become an essential input for spatial computing, but its coarse targeting and saccadic nature limit precision and complicate continuous interactions such as dragging, especially under user motion. Gaze+pinch has also become standard in XR for its convenience, yet mid-air gestures remain imprecise, fatiguing, and socially unacceptable. These limitations underscore the need for an approach that preserves the speed of gaze while enabling stable, fine control. We present GazeTune, a cascaded multimodal interaction technique combining gaze and touch to refine gaze-based selection and manipulation. Touch serves as a refinement channel within gaze pointing, allowing precise cursor and target control. Our work investigates how gaze-and-touch enhances dragging and mitigates Motion-Induced instability. In a study (N=20), we compared GazeTune against gaze-only and gaze-pinch methods in 2D dragging. Results show that GazeTune achieves significantly lower error with comparable execution time, validating its effectiveness and balanced trade-off between time and accuracy.

cs.HC↗
arXiv2026

SemPOI-RL: Aligning LLM Semantic Reasoning for Interpretable Out-of-Town POI Sequential Generation

Large language models (LLMs) exhibit strong semantic reasoning and open-ended generation abilities, but aligning these abilities with structured sequential generation remains challenging. This challenge is particularly evident in out-of-town (OOT) POI sequence generation, where a model must infer transferable travel intent from a user's hometown behaviors, adapt to cross-city interest drift, and generate a coherent destination trajectory under structural constraints. Existing approaches either rely on latent ID-based transfer with limited interpretability or directly use LLMs for sequence generation without explicitly grounding inferred semantics into position-aware predictions. To address this gap, we propose SemPOI-RL, a framework that aligns LLM semantic reasoning with structured sequence generation for interpretable OOT recommendation. Specifically, we first fine-tune an LLM to infer destination-oriented travel styles from users' hometown trajectories, using natural language as an interpretable semantic intermediate. We then introduce a Semantic POI Alignment Module (SPAM) to ground these inferred styles into a style-conditioned masked autoencoder for position-aware trajectory generation. Finally, we apply reinforcement learning with recommendation-oriented rewards to align LLM-generated styles with downstream sequence quality. Experiments on two real-world datasets show that SemPOI-RL consistently outperforms both traditional recommenders and direct LLM baselines, while providing interpretable style attribution across different phases of a trip. The code is available at https://github.com/Wind-Flipped/SemPOI-RL .

cs.CL↗
arXiv2026

ACE-Align: Attribute Causal Effect Alignment for Cultural Values under Varying Persona Granularities

Ensuring that large language models (LLMs) reflect diverse cultural values is important for globally deployed NLP systems. However, existing approaches often treat cultural groups as homogeneous and overlook within-group heterogeneity arising from intersecting demographic attributes, leading to unstable behavior under varying persona granularity. To address this gap, we propose ACE-Align (Atribute Causal Effect Alignment), a causally inspired framework based on controlled persona edits that aligns how specific demographic attributes shift different cultural values, rather than treating each culture as a homogeneous group. We evaluate ACE-Align across 14 countries spanning five continents, with personas specified by subsets of four attributes (gender, education, residence, and marital status) and granularity instantiated by the number of specified attributes. Across all persona granularities, ACE-Align consistently outperforms baselines. Moreover, in within-survey comparisons, it reduces the average Global North--South alignment gap from 3.40 to 1.11 points on WVS and from 2.53 to 0.85 points on ISSP. Code and dataset are released at https://github.com/Wells-Luo/ACE-Align.

cs.CY↗
arXiv2026

Remarks on the Complex Structures on $\mathbb P^3$ and $S^2\times S^4$

Assuming the validity of the recently proposed \textit{``A compact complex threefold fibred by tori over the projective line, and the six-sphere''}, we construct an exotic complex structure on $\mathbb P^{3}$, distinct from the point-blowup structures of Huckleberry, Kebekus, and Peternell. Then we perform an Atiyah flop to produce a complex structure on the standard smooth manifold $S^{2}\times S^{4}$.

math.DG↗
arXiv2026

Chiral superconductors and competing states across a Lifshitz transition in rhombohedral pentalayer graphene

Rhombohedral multilayer graphene hosts a distinctive low-energy electronic structure in which strong Coulomb interactions and nontrivial quantum geometry intertwine to generate exotic quantum states. Recent experiments reported signatures of chiral superconductivity in electron-doped rhombohedral multilayer graphene within the spin- and valley-polarized regime. Here we map the normal-state fermiology surrounding chiral superconductivity in rhombohedral pentalayer graphene. Quantum oscillation measurements reveal an electrically controlled Lifshitz transition between a simply-connected circular quarter-metal Fermi surface and an annular quarter-metal Fermi surface. The Lifshitz boundary itself shifts with perpendicular magnetic field, consistent with the strongly momentum-dependent orbital magnetic moment of the low-energy band. Approaching the transition from either side, the electron effective mass becomes strongly enhanced, implying the formation of a nearly dispersionless band bottom and a strongly reduced kinetic-energy scale. This singular electronic structure produces a regime of exceptionally strong instability in which chiral superconductivity competes with Wigner crystalline phases and reentrant quantum Hall states. In particular, two superconducting regions with signatures of orbital time-reversal-symmetry breaking lie on opposite sides of the Lifshitz boundary and have comparable transition temperatures, yet the annular-side state is suppressed by a substantially smaller perpendicular magnetic field. Our calculation finds comparable chiral pairing tendencies on the two parent Fermi surfaces while producing a much lower orbital-Zeeman pair-breaking scale and an additional finite-momentum pairing tendency for the annular state. These results identify Fermi-surface topology as a key control parameter for chiral superconductivity in rhombohedral graphene.

cond-mat.mes-hall↗
arXiv2026

Gate Parameter Lee-Yang Zeros and Dynamical Phases in Quantum Circuits

We propose gate-parameter Lee-Yang zeros of Loschmidt amplitudes as probes of dynamical phases in finite quantum circuits. We study Floquet circuits constructed from two-qubit fSim gates with identical parameters, for which the Loschmidt amplitude becomes a rational function of the gate parameters after a suitable change of variables. At fixed system size and large circuit depth, the zeros in one complexified gate parameter, with the other held fixed, condense onto limiting curves. In contrast to conventional Loschmidt or Fisher zeros in complex time, these zeros live directly in the complex plane of a tunable gate parameter. We show that the limiting set has two origins: a state-dependent component controlled by overlaps with Floquet eigenstates, and a universal component fixed by the Floquet spectrum. As the remaining gate parameter is varied, the universal zero set reorganizes abruptly, providing a finite-qubit diagnostic of a dynamical phase transition. We demonstrate this behavior in a Bethe ansatz solvable brickwork circuit and in longer-range fSim circuits outside this solvable structure. The mechanism follows from the Beraha-Kahane-Weiss theorem together with local unitarity, and is therefore spectral rather than a special consequence of integrability.

quant-ph↗
arXiv2026

MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching

Existing action quality assessment (AQA) datasets and methods rely primarily on visual inputs such as RGB and pose, overlooking physiological dynamics such as muscle mechanics and often modeling actions as monolithic patterns. These limitations hinder fine-grained, biomechanically grounded feedback. We introduce MyoMechanix, a multimodal ecosystem for weight-loaded actions that aligns motion with muscle activity. Expert-annotated, it contains 7,500+ samples of 20 actions from 38 subjects, with synchronized multiview RGB video, 3D pose, sEMG, and additional physiological signals, forming the largest multimodal AQA benchmark to date. We further construct the Fitness Knowledge Graph (FKG), which organizes expert annotations into structured relationships among actions, phases, key steps, errors, and corrective feedback, enabling compositional scoring and interpretable assessment. Building on these representations, we develop CUBIST (Compositional Ontological Reasoning Engine), which performs decomposition-analysis-recomposition for fine-grained error attribution and feedback generation. We also establish MyoMechanix-AQA, MyoMechanix-VideoQA, and a novel MyoMechanix-Video2EMG task. Experiments show that multimodal sensing and structured representations improve performance, interpretability, and error attribution, with CUBIST achieving state-of-the-art results; VideoQA enhances language-grounded action understanding; and Video2EMG suggests video-based alternatives to costly EMG sensing. MyoMechanix advances skilled activity understanding toward biomechanically grounded, multimodal, and compositional reasoning for Physical AI applications in fitness, rehabilitation, healthcare, and machine learning. Project page: https://haoyin116.github.io/MyoMechanix/

cs.CV↗
arXiv2026

ReLog: Execution-Aware Logging with Runtime Feedback for LLM-Oriented Debugging

Logging statements are essential for software debugging and maintenance. However, existing approaches to automatic logging generation rely on static analysis and produce statements in a single pass without considering runtime behavior. They are also typically evaluated by similarity to developer-written logs, assuming these logs form an adequate gold standard. This assumption is increasingly limiting in the LLM era, where logs are consumed not only by developers but also by LLMs for downstream tasks. As a result, optimizing logs for human similarity does not necessarily reflect their practical utility. To address these limitations, we introduce ReLog, an iterative logging generation framework guided by runtime feedback. ReLog leverages LLMs to generate, execute, evaluate, and refine logging statements so that runtime logs better support downstream tasks. Instead of comparing against developer-written logs, we evaluate ReLog through downstream debugging tasks, including defect localization and repair. We construct a benchmark based on Defects4J under both direct and indirect debugging settings. Results show that ReLog consistently outperforms all baselines, achieving an F1 score of 0.520 and repairing 97 defects in the direct setting, and the best F1 score of 0.408 in the indirect setting where source code is unavailable. Additional experiments across multiple LLMs demonstrate the generality of the framework, while ablations confirm the importance of iterative refinement and compilation repair. Overall, our work reframes logging as a runtime-guided, task-oriented process and advocates evaluating logs by their downstream utility rather than textual similarity.

cs.SE↗
arXiv2026

Visualizing flat-band spatial renormalization in rhombohedral graphene superlattices

Rhombohedral graphene/hBN moiré superlattices exhibit flat-band-driven emergent phases, including superconductivity and the fractional quantum anomalous Hall effect (FQAHE), yet the microscopic role of the moiré potential remains unclear. Here, using scanning tunneling microscopy, we visualize moiré-modulated spatial renormalization of flat bands in rhombohedral pentalayer and tetralayer graphene/hBN superlattices. We observe spatially hierarchical filling, manifested as periodic energy shifts of the flat bands at the moiré scale, leading to spatial reshaping of correlated states in the interacting regime. Remarkably, this modulation vanishes below a ~10 nm moiré period--the same threshold below which the FQAHE is absent. Theoretical modeling attributes this mechanism to atomic-corrugation-induced charge redistribution. Our work provides real-space visualization of moiré-engineered flat-band reconstruction, resolving a key link between moiré periodic potential and emergent topological order.

cond-mat.mes-hall↗
arXiv2026

Helical jets driven by a ring of laser irradiation

Plasma jets are formed in various astrophysical systems as plasma is rapidly ejected from a source, with a subset of these jets being magnetized and having a helical structure. Here, we demonstrate that helical jets may be formed using a ring of laser pulses that arrive on planar foils sequentially with increasing energy. The formation of the jets and their properties, including kinetic helicity, are studied through a set of three-dimensional magneto-hydrodynamics simulations with conditions informed by the parameters of the OMEGA laser facility. We find that jets with a higher degree of helicity may be generated under realistic experimental conditions when compared to a uniform jet. Synthetic x-ray and Thomson scattering diagnostics computed from simulated data demonstrate that the helical jet provides a unique fingerprint in both its morphology and plasma parameters. This laboratory helical jet platform may allow for controlled experimental study of the dynamics of helical plasma structures and, through interaction with other jets or targets, can allow for studies of shear-driven turbulence and mixing relevant to interactions between astrophysical jets and ambient clouds or crosswind.

physics.plasm-ph↗
arXiv2026

Lexical Perturbations Disrupt LLM Reasoning: An Empirical Study of Attention Diversion

Large Language Models (LLMs) achieve strong reasoning performance, but their robustness to realistic lexical corruption remains poorly understood. We evaluate four open-weight instruction-tuned models and frontier models across four reasoning benchmarks under keyboard noise, character swaps, and filler insertion. Character-level perturbations substantially degrade accuracy, especially on multi-step reasoning tasks, while filler insertion has little effect. We trace this asymmetry to Attention Diversion: lexical corruption fragments subword tokenization, and the resulting fragments attract disproportionate attention mass, concentrated in middle and final transformer layers. Length-matched controls confirm that fragmentation, not prompt length, drives the loss. A factorial intervention then shows why the damage is hard to undo: fragmentation corrupts token content and attention allocation together, and the two are coupled. Restoring clean attention while the content remains corrupted is actively harmful, restoring content alone is insufficient, and only restoring both recovers a substantial share of the gap. This coupling explains why inference-time strategies, including chain-of-thought prompting, spell-checking, self-repair, and stronger repair models, fail to consistently recover performance: each addresses one channel at a time. Code and data are available at https://github.com/Jiaqian-Janelle/Attention-Diversion

cs.CL↗
arXiv2026

Towards Faithful Simulation of Human Shopping Behavior

Simulating realistic user shopping behavior underpins offline evaluation and reinforcement learning in e-commerce scenarios. While recent LLM- and VLM-based simulators have made encouraging progress, reproducing a real browsing session remains difficult for two reasons. (i) Memory Challenge: a shopping session spans dozens of pages, yet existing agents either discard long-range observation histories, losing the evolving user state, or naively concatenate them, overwhelming the context window and even degrading simulation quality. (ii) Optimization Challenge: current user simulators are typically supervised to match each logged action via imitation or step-level rewards; the resulting sessions often display unrealistic patterns, such as over-exploration or excessive passivity, which per-step supervision can neither detect nor correct. To address the above challenges, we present RecVerse, a GUI-grounded simulation agent that perceives pages through screenshots and produces faithful multi-turn trajectories. For the memory challenge, RecVerse adopts a cognitive-inspired hierarchical memory: Working Memory for short-term focus, Episodic Memory for in-session traces, and Preference Memory for high-level intent, with memory updates treated as actions so that the agent adaptively learns when and what to memorize. For the optimization challenge, RecVerse is optimized with a trajectory-level RL objective that scores entire sessions, aligning both macro-level action-type distributions and micro-level shopping intent with real users. We further release USB (User Simulation Benchmark), an interactive e-commerce GUI trajectory dataset for multi-turn user simulation. Experiments show that RecVerse significantly outperforms existing baselines in both behavioral fidelity and intent consistency.

cs.IR↗
arXiv2026

GEO-Flag: Detecting and Measuring GEO-Optimized Web Content

Generative Engine Optimization (GEO) modifies web content to increase its likelihood of being selected and cited by generative search engines. This can give strategically optimized pages visibility disproportionate to their authority or relevance and even make weak or false information appear well supported. Unlike conventional search, generative search synthesizes information into direct answers rather than presenting competing sources, which can further amplify these risks, as assessing source provenance and authority requires additional user interaction. Despite these concerns, systematic methods for detecting GEO-optimized webpages remain underexplored. We introduce \texttt{GEOFlagBench}, a benchmark of 3,200 web content instances spanning 400 queries, four domains, and eight GEO optimizer families, and use it to systematically evaluate existing GEO detection methods. Although the strongest baseline achieves an aggregate F1 of 0.880, method-level and authorship-conditioned evaluations reveal substantial weaknesses and potential reliance on authorship-related shortcuts. We therefore propose \emph{Intervention-Paired Training} (IPT), which supervises detector responses to GEO interventions and non-GEO AI polishing; on ModernBERT, IPT improves F1 from 0.862 to 0.944 and worst-group accuracy from 0.725 to 0.883. We develop a GEO-gated Agent system for auditing the Source Tier and verifiability of Citation URLs in detected GEO pages. Finally, we deploy the complete pipeline on released Google Search and Gemini-grounded retrieval results for 1,000 real-user queries. Across 10,095 available pages, we estimate an overall GEO prevalence of 8.90\%, reaching 16.36\% among pages modified in 2026. Our results establish a foundation for systematically detecting, auditing, and measuring GEO in real-world search ecosystems.

cs.LG↗
arXiv2026

EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models

Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether these hidden CoTs can be directly extracted from black-box models remains largely unexplored. In this work, we systematically study whether hidden CoTs can be extracted near-verbatim from black-box LRMs through API interactions. We identify a previously overlooked reasoning replay surface between tool calls and develop EchoCoT, a multi-step attack that iteratively extracts hidden CoTs using API-returned fidelity signals. We further develop an LLM-based optimization framework that automatically searches for an effective universal injection trajectory across various datasets. We evaluate EchoCoT on three open-source and five frontier proprietary LRMs. On open-source LRMs, EchoCoT achieves up to 66.4\% near-verbatim extraction success, with the extracted trace length within 10\% of the target and at least 90\% of tokens exactly matching the target CoT. The same injection trajectory also generalizes to unseen datasets, achieving up to 80\% extraction success under the same criterion. For tested frontier proprietary LRMs, a substantial fraction of extracted CoTs closely align with provider-reported reasoning lengths and available CoT summaries. EchoCoT can also extract very long CoTs: on Gemini-2.5, it extracts 33,463 tokens from a 32,948-token target. These results establish hidden-CoT extraction as a practical security risk and highlight the need to better protect hidden CoT assets.

cs.CR↗
arXiv2026

DynCur-Geo: Dynamic Curiosity Reward Shaping for Multimodal Active Geo-Localization

Active geo-localization enables low-altitude UAVs to search for specified targets from limited local aerial observations, supporting time-sensitive applications such as search and rescue and emergency inspection. However, multimodal target cues, restricted views, and sparse feedback make it difficult to balance exploration with target convergence. Existing curiosity-driven methods assign a fixed intrinsic-reward weight throughout search, which can continue rewarding novelty after the agent nears the target and induce detours. We propose DynCur-Geo, a dynamic curiosity framework that adjusts prediction-error intrinsic reward according to remaining target distance. A distance-aware gate encourages early exploration and shifts the policy toward goal-directed behavior near the target, while potential-based reward shaping supplies dense progress guidance. Experiments across multimodal, cross-scene, disaster-affected, and long-range settings show consistent gains over active geo-localization baselines.

cs.CV↗
arXiv2026

EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction

Predicting the binding sites of target proteins plays a fundamental role in drug discovery. Most existing deep-learning methods consider a protein as a 3D image by spatially clustering its atoms into voxels and then feed the voxelized protein into a 3D CNN for prediction. However, the CNN-based methods encounter several critical issues: 1) defective in representing irregular protein structures; 2) sensitive to rotations; 3) insufficient to characterize the protein surface; 4) unaware of protein size shift. To address the above issues, this work proposes EquiPocket, an E(3)-equivariant Graph Neural Network (GNN) for binding site prediction, which comprises three modules: the first one to extract local geometric information for each surface atom, the second one to model both the chemical and spatial structure of protein and the last one to capture the geometry of the surface via equivariant message passing over the surface atoms. We further propose a dense attention output layer to alleviate the effect incurred by variable protein size. Extensive experiments on several representative benchmarks demonstrate the superiority of our framework to the state-of-the-art methods.

q-bio.BM↗