Search arXiv⌕ Search

arXiv subjects

Yifan Zhu

Publications and source records attributed to Yifan Zhu.

At least 37 records · Page 2Linked to original sources
arXiv2026

Chiral Landau levels induced by two in-plane pseudomagnetic fields in underwater acoustic metamaterials

The chiral zeroth Landau levels (LLs) constitute topologically protected bulk states that enable robust control of acoustic wave propagation. Given the central role of underwater acoustics in marine engineering, realizing such Landau-level physics in underwater acoustic systems is highly desirable. Nevertheless, existing studies have primarily been limited to airborne acoustic systems, and the implementation of chiral zeroth LLs in underwater acoustics remains a challenge due to the unavoidable fluid-solid interactions. In this study, we realize two kinds of chiral LLs in an open underwater spoof surface acoustic wave (SSAW) platform by introducing two perpendicular in-plane artificial pseudomagnetic fields (PMFs), oriented along the x and y directions, respectively, and reveal that scalar acoustic fields in water and vectorial elastic vibrations in solids can be jointly manipulated within a unified framework. Specifically, by strategically opening bandgaps at the Dirac points, position-dependent effective mass terms are introduced into the Dirac Hamiltonians, thereby synthesizing two in-plane PMFs. This results in the emergence of chiral LLs, which is confirmed both numerically and experimentally. The unidirectional propagation of the chiral LLs and their robustness against defects are also demonstrated. In addition, we achieve flexible manipulation of underwater ultrasonic energy carried by SSAWs, including beam splitting and arbitrary wave steering. Dual-band chiral LLs are also observed in small-scale underwater topological metamaterials. Our work provides a new route toward SSAW-based underwater ultrasonic control, opening opportunities for multiband underwater acoustic signal processing and detection, as well as underwater acoustic energy harvesting.

physics.app-ph↗
arXiv2026

A GPU-Accelerated Framework for Multi-Attribute Range Filtered Approximate Nearest Neighbor Search

Range-filtered approximate nearest neighbor search (RFANNS) is increasingly critical for modern vector databases. However, existing solutions suffer from severe index inflation and construction overhead. Furthermore, they rely exclusively on CPUs for the heavy indexing and query processing, significantly restricting the throughput due to the limited memory bandwidth and parallelism. In this paper, we present Garfield, a GPU-accelerated framework for multi-attribute range filtered ANNS that overcomes these bottlenecks through designing a lightweight index structure and hardware-aware execution pipeline. Garfield introduces the GMG index, which partitions data into cells and builds local graph indexes. It guarantees linear storage and indexing overhead by adding a constant number of cross-cell edges. For queries, Garfield utilizes a cluster-guided ordering strategy that reorders query-relevant cells, enabling a highly efficient cell-by-cell traversal on the GPU that aggressively reuses candidates as entry points across cells. To handle datasets exceeding GPU memory, Garfield features a cell-oriented out-of-core pipeline. It dynamically schedules cells to minimize the number of active queries per batch and overlaps GPU computation with CPU-to-GPU index streaming. Extensive evaluations demonstrate that Garfield reduces index size by 4.4x, while delivering 119.8x higher throughput than state-of-the-art RFANNS methods.

cs.DB↗
arXiv2026

Experimental Realization of Type-II Quadrupole Topological Insulator

The discovery of quadrupole topological insulators (QTIs) has spurred extensive research into higher-order topological phases. Recently proposed type-II QTIs exhibit unconventional topological behaviors with 1/2 edge polarization \operatorname{p}_x and zero edge polarization \operatorname{p}_y, due to the inequivalence between Wannier-band and edge-spectrum gap closures, yet their experimental realization remains challenging owing to the long-range and complex off-site hopping terms in their tight-binding model (TBM). Here, we circumvent this difficulty via an optimized Householder tridiagonalization (OHT) mapping that reduces the complex two-dimensional lattices to one-dimensional chains with only negative-real-valued nearest-neighbor hopping terms, greatly facilitating experimental sample fabrication. Using this strategy, we experimentally verify the type-II QTI phase, type-I QTI phase and trivial phase in elastic wave platforms via simple aperiodic plate-beam chain structures, where the plates reflect the on-site potential terms and beams correspond to the off-site hopping terms in the TBM. Our approach provides a versatile route for experimentally exploring more complex and richer topological phenomena based on TBM.

physics.app-ph↗
arXiv2026

Prior Diffusiveness and Regret in the Linear-Gaussian Bandit

We prove that Thompson sampling exhibits $\tilde{O}(σd \sqrt{T} + d r \sqrt{\mathrm{Tr}(Σ_0)})$ Bayesian regret in the linear-Gaussian bandit with a $\mathcal{N}(μ_0, Σ_0)$ prior distribution on the coefficients, where $d$ is the dimension, $T$ is the time horizon, $r$ is the maximum $\ell_2$ norm of the actions, and $σ^2$ is the noise variance. In contrast to existing regret bounds, this shows that to within logarithmic factors, the prior-dependent ``burn-in'' term $d r \sqrt{\mathrm{Tr}(Σ_0)}$ decouples additively from the minimax (long run) regret $σd \sqrt{T}$. Previous regret bounds exhibit a multiplicative dependence on these terms. We establish these results via a new ``elliptical potential'' lemma, and also provide a lower bound indicating that the burn-in term is unavoidable.

cs.LG↗
arXiv2026

LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models

Natural Language to SQL (NL2SQL) aims to translate natural language queries into executable SQL statements, offering non-expert users intuitive access to databases. While recent approaches leveraging large-scale private LLMs such as GPT-4 have achieved state-of-the-art results, they face two critical challenges: the lack of openness and reproducibility, and the prohibitive computational cost of test-time scaling. To address these issues, we explore improving the model-level performance of small-scale public LLMs in NL2SQL under resource-constrained settings. Our exploratory experiments reveal the potential of task decomposition for enhancing NL2SQL performance, but also highlight the difficulty of enabling LLMs to decompose queries effectively. Motivated by these findings, we propose LearNAT, a novel framework designed to enhance decomposition capabilities of LLM. LearNAT introduces (1) a Decomposition Synthesis Procedure, which leverages AST-guided search with pruning strategies to generate verifiable and efficient decompositions, and (2) Margin-Aware Reinforcement Learning, which provides fine-grained preference optimization for multi-step reasoning beyond standard DPO. Extensive experiments on benchmark datasets demonstrate that LearNAT significantly improves the performance of small-scale LLMs, achieving results comparable to GPT-4 with only a 7B parameter model. These results validate the effectiveness of verifiable decomposition and fine-grained preference learning in advancing NL2SQL towards openness, transparency, and efficiency. Our code is publicly available at https://github.com/MrBlankness/LearNAT.

cs.CL↗
arXiv2026

BrepLLM: Enabling Large Language Models to Understand Boundary Representations

Current token-sequence-based Large Language Models (LLMs) struggle to directly process 3D Boundary Representation (B-rep) models that contain complex geometric and topological information. To this end, we propose BrepLLM, the first multimodal framework that enables LLMs to directly parse and reason over raw B-rep data. BrepLLM adopts a two-stage training pipeline: cross-modal alignment pre-training and two-stage LLM fine-tuning. In the first stage, we design an adaptive UV sampling strategy to convert B-reps into graph representations that integrate geometric and topological information. Subsequently, we construct a hierarchical BrepEncoder to extract features from geometric elements (faces and edges) and topology, generating a global token and a sequence of node tokens. Then, via contrastive learning, we conduct an initial alignment between this global token and the text embeddings of a frozen CLIP text encoder (ViT-L/14). In the second stage, we integrate the pre-trained BrepEncoder into the LLM and employ a two-stage progressive strategy to align the sequence of node tokens: (1) training an MLP-based semantic mapping network that utilizes the prior knowledge of a 2D-VLM to align the B-rep representation to the 2D visual semantic space; (2) utilizing LoRA for parameter-efficient fine-tuning of the Q-Former and the LLM backbone network to achieve the final 3D-language generation capability. Furthermore, we construct the Brep2Text dataset, which contains 269,444 B-rep and text question-answer pairs. Experiments demonstrate that BrepLLM achieves SOTA performance on 3D object classification and captioning tasks. The project page is available at https://user-deng.github.io/BrepLLM/.

cs.CV↗
arXiv2026

From Propositional to Perceptual Asymmetry: Extending Frictive Policy Optimization to Asymmetric Partial Information Dialogue

Frictive Policy Optimization (FPO; Pustejovsky et al., 2025) treats friction in collaborative dialogue -- misalignment, misunderstanding, repair -- as an epistemic signal essential to common-ground construction, rather than noise to be minimized. However, FPO and its implementations assume shared perceptual contexts, where friction arises from differently interpreted propositions over the same scene, which we define as propositional asymmetry. We extend FPO to perceptual asymmetry, where participants hold asymmetric partial information and the same referring expression yields different denotations depending on whose information state grounds the reference. We evaluate this through cross-corpora analysis and LLM probing on referentially asymmetric dialogue tasks, primarily the HCRC MapTask (Anderson et al., 1991). We find that FPO's friction functional is empirically valid only when evaluated from within each participant's information horizon: different landmark configurations produce qualitatively distinct grounding failure modes, with a small class of ambiguous configurations driving a disproportionate share of misunderstandings through trajectories that appear successful but silently diverge. The LLM probe confirms that having the "right perspective" matters more than having all perspectives: the informed single viewpoint outperforms omniscient access to both participants' contexts. We propose two annotation refinements: subtype decomposition of pending grounding states and accommodation-aware alignment classification.

cs.CL↗
arXiv2026

Generative-Model Predictive Planning for Navigation in Partially Observable Environments

Navigation in partially observable environments presents a significant challenge for autonomous agents, requiring effective decision-making with limited sensory information in unknown environments. Belief-based methods, particularly those using neural networks to approximate the belief space, often fail to capture the inherent multimodality of belief spaces, especially in high-dimensional cases with perceptual aliasing. While generative models present a compelling alternative, they typically require substantial data or expert demonstrations and lack explicit mechanisms for long-term planning. In this paper, we introduce BeliefDiffusion, a novel framework that combines the benefits of both generation and planning. BeliefDiffusion leverages diffusion models to explicitly characterize multimodal belief distributions and utilizes Model Predictive Control (MPC) to simultaneously plan ahead. It consists of two steps: (1) Imagining plausible environment configurations based on observation history and (2) Planning efficient navigation strategies across an aggregated configurations. Through extensive experiments in synthetic map environments, we demonstrate that BeliefDiffusion significantly outperforms both model-free reinforcement learning baselines and other generative approaches in navigation success rate and path efficiency. Our results validate that explicitly incorporating multimodal belief representations into planning enables more robust navigation in partially observable settings.

cs.AI↗
arXiv2026

Accelerating High-Dimensional Nearest Neighbor Search with Dynamic Query Preference

Approximate Nearest Neighbor Search (ANNS) has emerged as an essential operation in modern database and AI systems. While graph-based methods like NSG demonstrate state-of-the-art ANNS performance, they typically ignore that query distributions are often skewed. In real-world scenarios, user preferences and time-varying access patterns lead to non-uniform workloads, where specific data regions are retrieved significantly more frequently than others. Meanwhile, these patterns evolve over time, making pre-built indexes outdated and thus inefficient for future query workloads. Motivated by this, we propose DQF, a novel Dual-Index Query Framework for dynamic query preference. This dual-index structure comprises a Hot Index containing frequently accessed nodes and a Full Index covering the entire dataset, so that hot queries can be answered faster within the compact Hot Index while cold queries still obtain complete results from the Full Index. Furthermore, we propose a three-phase competitive search in which both layers share a single priority queue. A lightweight decision tree detects when the top-k results have stabilized and triggers per-query early termination. To address temporal shifts in query patterns, we design an adaptive update mechanism that periodically promotes new high-frequency nodes to the Hot Index while demoting outdated ones. Experiments on five real-world datasets demonstrate that DQF achieves a 2.2-6.9x speedup over the strongest baseline on each million-scale dataset at 95% recall. Moreover, it scales to 100M vectors with consistent performance gains, successfully adapting to distribution shifts without requiring Full Index reconstruction.

cs.DB↗
arXiv2026

Directory-Aware Query and Maintenance in Vector Databases

Vector databases typically manage metadata as flat scalar attributes, which limits their ability to express hierarchical directory semantics commonly used to organize code repositories, enterprise documents, and agent memories. As a result, directory-scoped retrieval and structural updates are often implemented as application-layer workarounds, making recursive scope resolution expensive and directory maintenance difficult to keep consistent. This paper studies native directory semantics as a first-class capability for vector databases. We formalize two core operators: Directory-Semantic Query (DSQ) for hierarchically scoped retrieval, and Directory-Semantic Maintenance (DSM) for structural updates. We then evaluate three implementation strategies: query-time path expansion (PE-Online), ingestion-time path expansion (PE-Offline), and a Trie-based Hierarchical Index (TrieHI). Our analysis exposes the fundamental limitations of expansion-based designs: flattening the hierarchy incurs high recursive-query latency in PE-Online and unscalable write amplification during structural changes in both expansion strategies. In contrast, TrieHI keeps the directory topology as a native prefix tree, enabling efficient recursive retrieval through tree traversal and reducing maintenance cost through topological node manipulation. We benchmark these design points within ByteDance's Viking vector search engine and release two large-scale datasets, WIKI-Dir and ARXIV-Dir, to support future research on directory-semantic vector search. Finally, TrieHI has been integrated into OpenViking, an open-source context database for AI agents, where it supports filesystem-style context organization and directory-recursive retrieval.

cs.DB↗
arXiv2026

VikingMem: A Memory Base Management System for Stateful LLM-based Applications

Large Language Models have revolutionized interactive applications; however, their finite context windows pose a critical data management challenge for maintaining stateful, long-term interactions. Existing memory approaches often rely on simplistic extraction methods that lead to incomplete memories or use rigid, single-purpose memory extraction prompts tailored to a single use case, such as chatbots. Consequently, they lack generalizability and perform poorly across diverse downstream tasks. To bridge this gap, we introduce the Memory Base, a novel data management paradigm for managing the persistent state of long-term interactions. It is characterized by three core principles: selective extraction of high-value memories from raw information streams; inherent statefulness and evolution, where memory content is progressively summarized, corrected, and temporally weighted to prioritize recent interactions; and a generalizable abstraction paradigm designed for robust transferability across diverse applications, including education, recommendation, and agent memory. Building on this foundation, we present VikingMem, an end-to-end Memory Base Management System implemented on the VikingDB vector engine. VikingMem materializes this paradigm through interconnected event and entity abstractions. It features event-centric memory extraction to selectively handle complex information streams, while entities are dynamically updated by events to achieve stateful evolution. Using temporal compression via a topic-wise timeline and time-weighted recall, the system progressively produces high-level summary memories, prioritizes recent items, and compresses and fades older ones. Extensive evaluations on long-term memory benchmarks demonstrate that VikingMem outperformes baselines by up to 30% in memory retrieval effectiveness while maintaining the low latency essential for interactive applications.

cs.AI↗
arXiv2026

5% > 100%: Flatness Preference is All You Need for Multimodal Parameter-Efficient Fine-Tuning

Parameter-Efficient Fine-Tuning (PEFT) methods provide a streamlined and efficient tool for adapting large models to domain-specific multimodal downstream tasks. Although these methods proved their tangible effects in practice, their principal aspects remain under-explored. Therefore we remain curious about the underlying generalization mechanisms in various PEFT methods and how they can be further enhanced. In this paper, we reveal the flatness preference widely present in various PEFTs, where a small fraction of sharp dimensions dominates the generalization of PEFT. This finding suggests an appealing possibility: we may be satisfied with a better generalization by merely attending to this small fraction of sharp dimensions instead of all of them. Furthermore, we propose Flatness Preference Optimization (FlatPO) to flatten these key sharpness dimensions, leading various PEFTs toward better generalization. Extensive experiments demonstrate the effectiveness of our findings and the proposed method. Code is available at https://github.com/Can-Lin/FlatPO.

cs.CV↗
arXiv2026

An Information-Theoretic Definition for Open-Ended Learning

A growing body of work points to the great promise of AI systems that can continually expand their capabilities as they operate in an open-ended environment. But yet there is no coherent definition of open-endedness or theory about how an agent ought to explore an open-ended environment. We introduce an information-theoretic definition based on a new concept -- the ${\textit bit-equivalent}$ -- which quantifies the information required to attain each level of expected reward. We consider an environment to be open-ended if an agent can attain linear growth in the bit-equivalent. We establish that classical bandit environments are not open-ended and formulate a bandit environment that is. We also introduce an algorithm that achieves open-ended learning in this environment.

cs.LG↗
arXiv2026

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning

Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling knowledge as entity-relation graphs, but still face challenges in high construction cost, fixed one-time retrieval, and reliance on long-context reasoning and prompt design. To address these challenges, we propose Graph-R1, the first agentic GraphRAG framework via end-to-end reinforcement learning (RL). It introduces lightweight knowledge hypergraph construction, models retrieval as a multi-turn agent-environment interaction, and optimizes the agent process via an end-to-end reward mechanism. Experiments on standard RAG datasets show that Graph-R1 outperforms traditional GraphRAG and RL-enhanced RAG methods in reasoning accuracy, retrieval efficiency, and generation quality. Our software and data are publicly available at https://github.com/LHRLAB/Graph-R1.

cs.CL↗
arXiv2026

ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models

Multimodal large language models (MLLMs) have shown strong potential as embodied agents, yet embodied geo-localization remains underexplored due to the lack of fine-grained evaluation. We introduce ERGeoBench, a diagnostic benchmark for vision-driven embodied geo-localization. ERGeoBench evaluates models under three progressive settings -- single-view, panorama-view, and embodied-view -- where agents may actively acquire observations through sequential changes in yaw, pitch, and zoom. The benchmark contains 2,207 globally distributed street-view panoramas and measures four complementary capabilities: foundational perception, spatial awareness, common sense reasoning, and geo-localization reasoning. Evaluations of leading proprietary and open-source MLLMs show that current models can infer high-level geographic semantics, but still struggle with fine-grained perceptual operations, metric localization, and spatial consistency across views. We further observe that geo-localization is strongly correlated with the other capability dimensions, suggesting that accurate localization depends on integrated perception, spatial reasoning, and commonsense inference rather than isolated visual recognition. Overall, ERGeoBench provides a unified framework for diagnosing and advancing human-like embodied geo-localization. Project Page: https://kaixuewen.github.io/ERGeoBench/

cs.CV↗
arXiv2026

One-Shot Klein Cutting Planes for Lipschitz Geodesically Convex Optimization in Hyperbolic Space

Motivated by the COLT 2023 open problem of Criscitiello, Martínez-Rubio, and Boumal on deterministic first-order methods for Lipschitz geodesically convex optimization on Hadamard manifolds, we study hyperbolic space \[ \HH^d_{-\kappaC^2} =\{X\in\R^{d+1}:\ipL{X}{X}=-1,\ X_0>0\}, \qquad \ip{U}{V}_X=\kappaC^{-2}\ipL{U}{V}. \] For every geodesically convex $M$-Lipschitz function \[ f:\bar B_{\HH}(x_0,r)\to\R,\qquad s=\kappaC r, \] we give a one-shot Klein cutting-plane method returning a queried point $\hat x$ such that \[ f(\hat x)-\min_{\bar B_{\HH}(x_0,r)}f\le \eps Mr \] after at most \[ \left\lceil 2d(d+1)\log\!\left(\frac{16\sinh s\cosh s}{s\eps}\right) \right\rceil \] oracle calls. For $d\ge2$, each localization step costs $O(d^2)$ arithmetic operations; for $d=1$, an interval variant gives the same oracle bound. Hence \[ N=O\bigl(d^2(s+\log(e/\eps))\bigr) =O\bigl(d^2ζ_s\log(e/\eps)\bigr), \qquad ζ_s=s/\tanh s . \] Compared with the constant-curvature construction associated with the COLT problem, this replaces chained curvature--accuracy dependence by additive dependence. The proof does not rely on convexity of the Klein pullback, which is generally only quasiconvex. Instead, every Riemannian subgradient halfspace becomes an exact Euclidean central cut: for $θ=\kappaC\dist(X,Y)$, \[ \ip{g}{\log_XY}_X =\fracθ{\kappaC^2\sinhθ}\ipL{g}{Y}, \] and tangency at $X$ converts $\ipL{g}{Y}\le0$ into \[ \gbar^{\mathsf T}(u-c)\le0,\qquad u=Φ(Y),\ c=Φ(X). \] Thus one fixed Euclidean ellipsoid localizes the hyperbolic ball, and curvature enters only through \[ \log\!\left(\frac{\sinh s\cosh s}{s\eps}\right) =\log(1/\eps)+2s-\log(4s)+O(e^{-4s}). \] The general Hadamard-manifold problem remains open.

cs.DS↗
arXiv2026

RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism

While Large Language Models (LLMs) are commonly fine-tuned to handle domain-specific tasks before being applied to vertical applications, adapting them to complex scenarios with diverse specialized knowledge remains challenging. Meanwhile, Mixture-of-Experts (MoE) architecture has risen as a crucial paradigm for training LLMs, and some recent works have also incorporated MoE into Parameter-Efficient Fine-Tuning (PEFT) to propose the Mixture of Low-rank Experts (MoE-LoRA), to enhance the power of low-rank adapters for learning complicated knowledge. However, conventional gating mechanisms in MoE typically apply only a scalar reweighing to selected experts, thereby limiting their underlying capacity of representation and generalization. Motivated and enabled by the low-rank structures in MoE-LoRA, we propose RotMoLE, a specialized MoE framework for low-rank experts featuring an additional rotation gate. Beyond simple scaling, RotMoLE implements a rotation mechanism for each selected expert, enabling superior expert exploitation and specialization for learning diverse data, especially when expert candidates are limited. Empirical results on complex multi-task and multilingual training scenarios validate our effectiveness.

cs.LG↗
arXiv2026

HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning

Domain Incremental Learning is a critical scenario that requires models to continuously adapt to new data domains without retraining. However, domain shifts often cause severe performance degradation. To address this, we propose Hybrid Energy-Distance Prompt, a domain-incremental framework inspired by Helmholtz free energy. HEDP introduces an energy regularization loss to enhance the separability of domain representations and a hybrid energy-distance weighted mechanism that fuses energy-based and distance-based cues to improve domain selection and generalization. Experiments on multiple benchmarks, including CORe50, show that HEDP achieves superior performance on unseen domains with a 2.57\% accuracy gain, effectively mitigating catastrophic forgetting and enhancing open-world adaptability. Our code is \href{https://github.com/dannis97500/HEDP/}{available here}.

cs.AI↗