arXiv subjects

Yan Zhang

Publications and source records attributed to Yan Zhang.

At least 145 records · Page 8Linked to original sources

arXiv2026

M^4olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraints

Generating molecules that satisfy precise numeric constraints over multiple physicochemical properties is critical and challenging. Although large language models (LLMs) are expressive, they struggle with precise multi-objective control and numeric reasoning without external structure and feedback. We introduce \textbf{M olGen}, a fragment-level, retrieval-augmented, two-stage framework for molecule generation under multi-property constraints. Stage I : Prototype generation: a multi-agent reasoner performs retrieval-anchored, fragment-level edits to produce a candidate near the feasible region. Stage II : RL-based fine-grained optimization: a fragment-level optimizer trained with Group Relative Policy Optimization (GRPO) applies one- or multi-hop refinements to explicitly minimize the property errors toward our target while regulating edit complexity and deviation from the prototype. A large, automatically curated dataset with reasoning chains of fragment edits and measured property deltas underpins both stages, enabling deterministic, reproducible supervision and controllable multi-hop reasoning. Unlike prior work, our framework better reasons about molecules by leveraging fragments and supports controllable refinement toward numeric targets. Experiments on generation under two sets of property constraints (QED, LogP, Molecular Weight and HOMO, LUMO) show consistent gains in validity and precise satisfaction of multi-property targets, outperforming strong LLMs and graph-based algorithms.

cs.AI↗

arXiv2026

Memory in the Age of AI Agents

Memory has emerged, and will continue to remain, a core capability of foundation model-based agents. As research on agent memory rapidly expands and attracts unprecedented attention, the field has also become increasingly fragmented. Existing works that fall under the umbrella of agent memory often differ substantially in their motivations, implementations, and evaluation protocols, while the proliferation of loosely defined memory terminologies has further obscured conceptual clarity. Traditional taxonomies such as long/short-term memory have proven insufficient to capture the diversity of contemporary agent memory systems. This work aims to provide an up-to-date landscape of current agent memory research. We begin by clearly delineating the scope of agent memory and distinguishing it from related concepts such as LLM memory, retrieval augmented generation (RAG), and context engineering. We then examine agent memory through the unified lenses of forms, functions, and dynamics. From the perspective of forms, we identify three dominant realizations of agent memory, namely token-level, parametric, and latent memory. From the perspective of functions, we propose a finer-grained taxonomy that distinguishes factual, experiential, and working memory. From the perspective of dynamics, we analyze how memory is formed, evolved, and retrieved over time. To support practical development, we compile a comprehensive summary of memory benchmarks and open-source frameworks. Beyond consolidation, we articulate a forward-looking perspective on emerging research frontiers, including memory automation, reinforcement learning integration, multimodal memory, multi-agent memory, and trustworthiness issues. We hope this survey serves not only as a reference for existing work, but also as a conceptual foundation for rethinking memory as a first-class primitive in the design of future agentic intelligence.

cs.CL↗

arXiv2026

AMAP Agentic Planning Technical Report

We present STAgent, an agentic large language model tailored for spatio-temporal understanding, designed to solve complex tasks such as constrained point-of-interest discovery and itinerary planning. STAgent is a specialized model capable of interacting with ten distinct tools within spatio-temporal scenarios, enabling it to explore, verify, and refine intermediate steps during complex reasoning. Notably, STAgent effectively preserves its general capabilities. We empower STAgent with these capabilities through three key contributions: (1) a stable tool environment that supports over ten domain-specific tools, enabling asynchronous rollout and training; (2) a hierarchical data curation framework that identifies high-quality data like a needle in a haystack, curating high-quality queries by retaining less than 1\% of the raw data, emphasizing both diversity and difficulty; and (3) a cascaded training recipe that starts with a seed SFT stage acting as a guardian to measure query difficulty, followed by a second SFT stage fine-tuned on queries with high certainty, and an ultimate RL stage that leverages data of low certainty. Initialized with Qwen3-30B-A3B to establish a strong SFT foundation and leverage insights into sample difficulty, STAgent yields promising performance on TravelBench while maintaining its general capabilities across a wide range of general benchmarks, thereby demonstrating the effectiveness of our proposed agentic model.

cs.AI↗

arXiv2026

Multigap nodeless superconductivity in Dirac semimetal PdTe

PdTe has recently been reported to be a type-II Dirac semimetal while a bulk nodal and surface nodeless superconductivity (SC) has been claimed to coexist. In this work, we applied point-contact spectroscopy (PCS) method to systematically study the superconducting gap in PdTe single crystals with a SC transition temperature $T_{c}=4.3$ K. The obtained differential conductance curves show a common deviation from a single-gap superconducting behavior and can be better fitted by a two-gap Blonder-Tinkham-Klapwijk model, suggesting the larger gap $Δ_{L}$ with $2Δ_{L}$=3.7 $k_{B}T_{c}$ and the smaller gap $Δ_S$ yielding $2Δ_{S}$=1.1-2.2 $k_{B}T_{c}$ with a weak interband scattering. The variations of conductance spectra among different contacts are proposed to be caused by the anisotropy of Fermi surface topology associated with different gaps.

cond-mat.supr-con↗

arXiv2025

Dynamic Bayesian Optimization Framework for Instruction Tuning in Partial Differential Equation Discovery

Large Language Models (LLMs) show promise for equation discovery, yet their outputs are highly sensitive to prompt phrasing, a phenomenon we term instruction brittleness. Static prompts cannot adapt to the evolving state of a multi-step generation process, causing models to plateau at suboptimal solutions. To address this, we propose NeuroSymBO, which reframes prompt engineering as a sequential decision problem. Our method maintains a discrete library of reasoning strategies and uses Bayesian Optimization to select the optimal instruction at each step based on numerical feedback. Experiments on PDE discovery benchmarks show that adaptive instruction selection significantly outperforms fixed prompts, achieving higher recovery rates with more parsimonious solutions.

cs.LG↗

arXiv2025

ReaSeq: Unleashing World Knowledge via Reasoning for Sequential Modeling

Industrial recommender systems face two fundamental limitations under the log-driven paradigm: (1) knowledge poverty in ID-based item representations that causes brittle interest modeling under data sparsity, and (2) systemic blindness to beyond-log user interests that constrains model performance within platform boundaries. These limitations stem from an over-reliance on shallow interaction statistics and close-looped feedback while neglecting the rich world knowledge about product semantics and cross-domain behavioral patterns that Large Language Models have learned from vast corpora. To address these challenges, we introduce ReaSeq, a reasoning-enhanced framework that leverages world knowledge in Large Language Models to address both limitations through explicit and implicit reasoning. Specifically, ReaSeq employs explicit Chain-of-Thought reasoning via multi-agent collaboration to distill structured product knowledge into semantically enriched item representations, and latent reasoning via Diffusion Large Language Models to infer plausible beyond-log behaviors. Deployed on Taobao's ranking system serving hundreds of millions of users, ReaSeq achieves substantial gains: >6.0% in IPV and CTR, >2.9% in Orders, and >2.5% in GMV, validating the effectiveness of world-knowledge-enhanced reasoning over purely log-driven approaches.

cs.IR↗

arXiv2025

Discrete Scale-invariant Metric Learning for Efficient Collaborative Filtering

Metric learning has attracted extensive interest for its ability to provide personalized recommendations based on the importance of observed user-item interactions. Current metric learning methods aim to push negative items away from the corresponding users and positive items by an absolute geometrical distance margin. However, items may come from imbalanced categories with different intra-class variations. Thus, the absolute distance margin may not be ideal for estimating the difference between user preferences over imbalanced items. To this end, we propose a new method, named discrete scale-invariant metric learning (DSIML), by adding binary constraints to users and items, which maps users and items into binary codes of a shared Hamming subspace to speed up the online recommendation. Specifically, we firstly propose a scale-invariant margin based on angles at the negative item points in the shared Hamming subspace. Then, we derive a scale-invariant triple hinge loss based on the margin. To capture more preference difference information, we integrate a pairwise ranking loss into the scale-invariant loss in the proposed model. Due to the difficulty of directly optimizing the mixed integer optimization problem formulated with \textit{log-sum-exp} functions, we seek to optimize its variational quadratic upper bound and learn hash codes with an alternating optimization strategy. Experiments on benchmark datasets clearly show that our proposed method is superior to competitive metric learning and hashing-based baselines for recommender systems.

cs.IR↗

arXiv2025

Collaborative Group-Aware Hashing for Fast Recommender Systems

The fast online recommendation is critical for applications with large-scale databases; meanwhile, it is challenging to provide accurate recommendations in sparse scenarios. Hash technique has shown its superiority for speeding up the online recommendation by bit operations on Hamming distance computations. However, existing hashing-based recommendations suffer from low accuracy, especially with sparse settings, due to the limited representation capability of each bit and neglected inherent relations among users and items. To this end, this paper lodges a Collaborative Group-Aware Hashing (CGAH) method for both collaborative filtering (namely CGAH-CF) and content-aware recommendations (namely CGAH) by integrating the inherent group information to alleviate the sparse issue. Firstly, we extract inherent group affinities of users and items by classifying their latent vectors into different groups. Then, the preference is formulated as the inner product of the group affinity and the similarity of hash codes. By learning hash codes with the inherent group information, CGAH obtains more effective hash codes than other discrete methods with sparse interactive data. Extensive experiments on three public datasets show the superior performance of our proposed CGAH and CGAH-CF over the state-of-the-art discrete collaborative filtering methods and discrete content-aware recommendations under different sparse settings.

cs.IR↗

arXiv2025

Search for Light Neutral Scalar in the Georgi-Machacek Model with Forward Detectors at the LHC

Long-lived particle (LLP) is one of the well-motivated targets for current collider experiments searching for the physics beyond the Standard Model. In recent years, many dedicated detectors have been developed for such scenarios which are designed to extend the sensitivity to weakly coupled particles with macroscopic $cτ$. In this work, we investigate the LLP signatures of the neutral component of the fermiophobic fiveplet $H_5^0$ in the Georgi-Machacek model. Due to its fermiophobic nature at tree level, it possesses suppressed decay widths in the low mass region and can naturally be long-lived over a wide region of parameter space. We show that $H_5^0$ can be produced with an appreciable flux in the forward region from the meson decay through loop-induced couplings leading to observable LLP signatures in forward detectors. We evaluate the sensitivity of representative forward detectors to this scenario and compare the result with existing constraints from terrestrial experiments and astrophysical observations. Our results demonstrate that the forward detectors can probe the $s_H$ down to $\mathcal{O}(10^{-5})$ for sub-GeV scalar masses, and hence providing a powerful and complementary probe of the extended Higgs sectors that is inaccessible to conventional searches.

hep-ph↗

arXiv2025

Electronic Phonons in a Moiré Electron Crystal

Collective quantum phenomena, such as the excitation of composite fermions1, spin waves2, and exciton condensation3,4, can emerge in strongly correlated systems like the fractional quantum Hall states5, spin liquids6, or excitonic insulators7. Two-dimensional (2D) moiré superlattices have emerged as a powerful platform for exploring such correlated phases and their associated collective excitations8,9. Specifically, electron crystals stabilized by longrange Coulomb interactions may host collective vibrational excitations emerging from electron correlations10, termed electronic phonons, which are fundamentally distinct from atomic lattice phonons. Despite theoretical prediction of their existence in moiré electron crystals11, direct experimental evidence has remained elusive. Here we report the observation of electronic phonons in the Mott insulating and stripe phases of a WS2/WSe2 moiré superlattice, achieved through light scattering measurements. The phonon energies, temperature and filling factor dependencies, along with theoretical modeling, corroborate their origin as collective vibrations of a correlated electron crystal. Polarization-resolved measurements further indicate rotational symmetry breaking in the Mott state. Notably, these electronic phonons exhibit strong tunability in energy, intensity, and polarization under external electric or magnetic fields, highlighting rich and controllable lattice dynamics of the electron crystal. These findings provide direct spectroscopic evidence for the electronic crystalline nature of correlated phases, opening avenues for probing and manipulating collective excitations in correlated electron systems.

cond-mat.str-el↗

arXiv2025

FID-Net: A Feature-Enhanced Deep Learning Network for Forest Infestation Detection

Forest pests threaten ecosystem stability, requiring efficient monitoring. To overcome the limitations of traditional methods in large-scale, fine-grained detection, this study focuses on accurately identifying infected trees and analyzing infestation patterns. We propose FID-Net, a deep learning model that detects pest-affected trees from UAV visible-light imagery and enables infestation analysis via three spatial metrics. Based on YOLOv8n, FID-Net introduces a lightweight Feature Enhancement Module (FEM) to extract disease-sensitive cues, an Adaptive Multi-scale Feature Fusion Module (AMFM) to align and fuse dual-branch features (RGB and FEM-enhanced), and an Efficient Channel Attention (ECA) mechanism to enhance discriminative information efficiently. From detection results, we construct a pest situation analysis framework using: (1) Kernel Density Estimation to locate infection hotspots; (2) neighborhood evaluation to assess healthy trees' infection risk; (3) DBSCAN clustering to identify high-density healthy clusters as priority protection zones. Experiments on UAV imagery from 32 forest plots in eastern Tianshan, China, show that FID-Net achieves 86.10% precision, 75.44% recall, 82.29% mAP@0.5, and 64.30% mAP@0.5:0.95, outperforming mainstream YOLO models. Analysis confirms infected trees exhibit clear clustering, supporting targeted forest protection. FID-Net enables accurate tree health discrimination and, combined with spatial metrics, provides reliable data for intelligent pest monitoring, early warning, and precise management.

cs.CV↗

arXiv2025

Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning

The widespread adoption of the "Games as a Service" model necessitates frequent content updates, placing immense pressure on quality assurance. In response, automated game testing has been viewed as a promising solution to cope with this demanding release cadence. However, existing automated testing approaches typically create a dichotomy: code-centric methods focus on structural coverage without understanding gameplay context, while player-centric agents validate high-level intent but often fail to cover specific underlying code changes. To bridge this gap, we propose SMART (Structural Mapping for Augmented Reinforcement Testing), a novel framework that synergizes structural verification and functional validation for game update testing. SMART leverages large language models (LLMs) to interpret abstract syntax tree (AST) differences and extract functional intent, constructing a context-aware hybrid reward mechanism. This mechanism guides reinforcement learning agents to sequentially fulfill gameplay goals while adaptively exploring modified code branches. We evaluate SMART on two environments, Overcooked and Minecraft. The results demonstrate that SMART significantly outperforms state-of-the-art baselines; it achieves over 94% branch coverage of modified code, nearly double that of traditional reinforcement learning methods, while maintaining a 98% task completion rate, effectively balancing structural comprehensiveness with functional correctness.

cs.AI↗

arXiv2025

Suspended waveguide-enhanced near-infrared photothermal spectroscopy for ppb-level molecular gas sensing on a chalcogenide chip

On-chip waveguide sensors have attracted significant attention recently due to their potential for high level integration. However, so far on-chip gas sensing based on traditional laser absorption spectroscopy has demonstrated low detection sensitivity, due to weak light-gas interaction over a limited interaction distance. On-chip photothermal spectroscopy (PTS) appears to be a powerful technique to achieve higher sensitivity, its performance is yet constrained to parts-per-million (ppm)-level due to small fraction of evanescent field in the light-gas interaction zone and fast thermal dissipation through the solid substrate. Herein, we demonstrated suspended chalcogenide glass waveguide (ChGW)-enhanced PTS that overcomes these limitations, enabling highly sensitive parts-per-billion (ppb)-level molecular gas sensing. We fabricated a nanoscale suspended ChGW with low loss of 2.6 dB/cm using CMOS-compatible two-step patterning process. By establishing an equivalent PTS model to guide the optimization of the ChGW geometry, we achieved a 4-fold increase in the absorption-induced heat source power and a 10.6-fold decrease in the equivalent heat conductivity, resulting in a 45-fold enhancement in photothermal phase modulation efficiency over the non-suspended waveguides. Combining with a high-contrast waveguide facet-formed Fabry-Perot interferometer, we achieved an unprecedented acetylene detection limit of 330 ppb, a large dynamic range close to 6 orders of magnitude, and a fast response of less than 1 s. The overall system exhibits a noise-equivalent absorption coefficient of 3.8x10-7 cm-1, setting a new benchmark for photonic waveguide gas sensors to the best of our knowledge. This work provides a key advancement towards prototyping an integrated sensor-on-a-chip for highly sensitive and background-free photonic sensing applications.

physics.optics↗

arXiv2025

Reframing Music-Driven 2D Dance Pose Generation as Multi-Channel Image Generation

Recent pose-to-video models can translate 2D pose sequences into photorealistic, identity-preserving dance videos, so the key challenge is to generate temporally coherent, rhythm-aligned 2D poses from music, especially under complex, high-variance in-the-wild distributions. We address this by reframing music-to-dance generation as a music-token-conditioned multi-channel image synthesis problem: 2D pose sequences are encoded as one-hot images, compressed by a pretrained image VAE, and modeled with a DiT-style backbone, allowing us to inherit architectural and training advances from modern text-to-image models and better capture high-variance 2D pose distributions. On top of this formulation, we introduce (i) a time-shared temporal indexing scheme that explicitly synchronizes music tokens and pose latents over time and (ii) a reference-pose conditioning strategy that preserves subject-specific body proportions and on-screen scale while enabling long-horizon segment-and-stitch generation. Experiments on a large in-the-wild 2D dance corpus and the calibrated AIST++2D benchmark show consistent improvements over representative music-to-dance methods in pose- and video-space metrics and human preference, and ablations validate the contributions of the representation, temporal indexing, and reference conditioning. See supplementary videos at https://hot-dance.github.io

cs.CV↗

arXiv2025

Mass spectrum of the $Ω\barΩ$ states

In this study, we investigate the mass spectrum of the $Ω\barΩ$ states with quantum numbers $J^{PC}=0^{-+}$, $1^{--}$, $0^{++}$, and $1^{++}$ within the framework of QCD sum rules. Employing suitably constructed interpolating currents, the analyses are carried out with the operator product expansion (OPE) including condensate contributions up to dimension $12$. Our results indicate the existence of four possible baryonium states with masses $m_{0^{-+}}=(3.22\pm0.07)$ GeV, $m_{1^{--}}=(3.28\pm0.08)$ GeV, $m_{0^{++}}=(3.46\pm0.09)$ GeV, and $m_{1^{++}}=(3.54\pm0.11)$ GeV. For the $0^{-+}$ and $1^{--}$ states, the predicted masses lie below the corresponding dibaryon thresholds, suggesting possible bound-state configurations. In contrast, the $0^{++}$ and $1^{++}$ states are found above the respective thresholds, implying resonance-like behavior. Potential decay channels for these baryonium candidates are discussed, with emphasis on those accessible to current experimental facilities such as BESIII, Belle II, and LHCb.

hep-ph↗

arXiv2025

Phase-locked amplification enhanced by spin squeezing

Quantum lock-in amplification raises the detection sensitivity of magnetic fields to unprecedented levels by phase-locked pumping the Zeeman levels of a single trapped atom. However, random spin precessions limits the useful detection range of arming times for locking high-contrast signals. To extend this range imposed by the uncertainty limit, quadrature spin squeezing can be introduced, on top of the phase-locking mechanism. We propose a detection scheme using an atomic ensemble whose collected spin is pumped by two lasers for simultaneous squeezing and phase locking. We derive the optimal $π/2$-pulse and $π$-pulse schemes that accomplishes this concurrent action and prove that the resulting phase sensitivity is enhanced while the usable detection window for phase locking is widened.

quant-ph↗

arXiv2025

SynPlay: Large-Scale Synthetic Human Data with Real-World Diversity for Aerial-View Perception

We introduce SynPlay, a large-scale synthetic human dataset purpose-built for advancing multi-perspective human localization, with a predominant focus on aerial-view perception. SynPlay departs from traditional synthetic datasets by addressing a critical but underexplored challenge: localizing humans in aerial scenes where subjects often occupy only tens of pixels in the image. In such scenarios, fine-grained details like facial features or textures become irrelevant, shifting the burden of recognition to human motion, behavior, and interactions. To meet this need, SynPlay implements a novel rule-guided motion generation framework that combines real-world motion capture with motion evolution graphs. This design enables human actions to evolve dynamically through high-level game rules rather than predefined scripts, resulting in effectively uncountable motion variations. Unlike existing synthetic datasets-which either focus on static visual traits or reuse a limited set of mocap-driven actions-SynPlay captures a wide spectrum of spontaneous behaviors, including complex interactions that naturally emerge from unscripted gameplay scenarios. SynPlay also introduces an extensive multi-camera setup that spans UAVs at random altitudes, CCTVs, and a freely roaming UGV, achieving true near-to-far perspective coverage in a single dataset. The majority of instances are captured from aerial viewpoints at varying scales, directly supporting the development of models for long-range human analysis-a setting where existing datasets fall short. Our data contains over 73k images and 6.5M human instances, with detailed annotations for detection, segmentation, and keypoint tasks. Extensive experiments demonstrate that training with SynPlay significantly improves human localization performance, especially in few-shot and data-scarce scenarios.

cs.CV↗

arXiv2025

Tunable dual-band atomic mirror based on subwavelength atomic arrays under electromagnetically induced transparency

Subwavelength atomic arrays offer a powerful platform for engineering cooperative light-matter interactions and enabling quantum metasurfaces. We demonstrate that a two-dimensional array of three-level atoms operating under electromagnetically induced transparency can function as a tunable dual-band atomic mirror, where two independently controllable reflection bands emerge from the collective optical responses mediated by dipole-dipole interactions. These resonances yield dual reflection bands with asymmetric linewidths, whose spectral positions and bandwidths can be tuned through the control-field parameters, dipole orientation, incident geometry, and lattice constant. We further identify the conditions under which additional diffraction orders emerge, which delineate the operational and tunable range of the atomic mirror via its collective-mode structure. This scheme provides a fully tunable dual-band atomic mirror operating across broad frequency and angular ranges, offering a practical and experimentally accessible pathway toward reconfigurable photonic elements in atomic-array platforms at low energy levels.

quant-ph↗