arXiv subjects

Shihao Liu

Publications and source records attributed to Shihao Liu.

14 recordsLinked to original sources

arXiv2026

MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking

We present MagicSelector, a joint optimization framework integrating Counterfactual task decomposition, Progressive reranking, and Dynamic Top-K, designed to address the fundamental challenges of tool retrieval in agents. MagicSelector is a specialized framework capable of translating ambiguous user instructions into executable atomic subtasks and guiding high-precision tool retrieval, effectively mitigating redundant noise and severe context distraction in out-of-domain (OOD) scenarios. We empower MagicSelector with these capabilities through three key contributions: (1) a preference-guided counterfactual task decomposition mechanism that utilizes a counterfactual reward to quantify the marginal causal gain of decomposition on retrieval ranking, effectively imposing fine-grained structural supervision on logical coherence; (2) a progressive tool reranking method driven by self-distillation hard negative mining, which optimizes both point-wise and list-wise relevance to enhance fine-grained discrimination among highly similar tools; and (3) a dual semantic boundary-aware dynamic Top-K strategy that adaptively monitors reranking score cliffs and inter-tool semantic shifts to dynamically truncate the candidate list, maximizing relevant tool recall while filtering long-tail noise. Evaluated on MTDTool, the first task decomposition benchmark we constructed tailored for mobile multi-turn interactions with process-level annotations, MagicSelector yields promising performance. Extensive experiments demonstrate that MagicSelector significantly outperforms state-of-the-art methods in terms of tool retrieval accuracy, OOD generalization capability, and overall token efficiency, thereby demonstrating the effectiveness of our proposed framework.

cs.IR↗

arXiv2026

A Conservative Time-Accurate Local Time-Stepping DG Scheme Based on a Weakly Compressible Model for Unsteady Low-Mach-Number Flows

This paper presents a conservative high-order discontinuous Galerkin (DG) method featuring time-accurate local time stepping for simulating low-Mach-number unsteady flows, based on a weakly compressible formulation. In this model, pressure is defined solely as a function of density, eliminating the need for a global pressure Poisson equation typical of incompressible solvers while preserving the locality and conservation of compressible schemes. This makes it suitable for low-speed unsteady flows and aeroacoustics. The spatial discretization uses a strong-form nodal DG spectral element method (DGSEM) on Gauss-Lobatto-Legendre points. Inviscid fluxes are handled by numerical fluxes tailored to the weakly compressible system; specifically, a two-rarefaction approximate Riemann solver is developed for the constant-sound-speed barotropic equation of state. Viscous terms employ the incomplete interior penalty Galerkin (IIPG) method. For time integration, a continuous extension Runge-Kutta (CERK) scheme constructs cell-local predictor polynomials for continuous-in-time volume reconstructions. Face fluxes are split into interior and common contributions: the former matches the volume quadrature, while the latter uses piecewise Gaussian quadrature from continuous predictors. This split preserves discrete summation-by-parts cancellation and ensures conservative inter-element flux exchange.

physics.flu-dyn↗

arXiv2026

Directional-dependent Berezinskii-Kosterlitz-Thouless transition at EuO/KTaO$_3$(111) interfaces

In two dimensions, a phase-coherent superconducting state is established via a Berezinskii-Kosterlitz-Thouless (BKT) transition, whose critical temperature $T_{\rm BKT}$ is determined by the global superfluid stiffness in uniform superconducting systems. We report that at the interface between (111)-oriented KTaO$_3$ and ferromagnetic EuO, the two-dimensional superconducting state exhibits a BKT transition relying on the direction of in-plane bias current. The highest $T_{\rm BKT}$ occurs when current is applied along one of the [11$\bar{2}$] axes of KTaO$_3$, underscoring a spontaneous breaking of the threefold lattice rotational symmetry. Such directional dependence of $T_{\rm BKT}$ is consistently reflected in the nonreciprocal signals stemming from superconducting fluctuations above the transition. We attribute this phenomenon to an interfacial phase segregation; the phase with higher $T_{\rm BKT}$ self-organizes into quasi-one-dimensional textures that stretch along one of the [11$\bar{2}$] directions. Our results point toward the emergence of exotic phases of matter beyond the description of conventional BKT physics at a superconducting interface that is subjected to ferromagnetic proximity.

cond-mat.supr-con↗

arXiv2025

Can LLM Annotations Replace User Clicks for Learning to Rank?

Large-scale supervised data is essential for training modern ranking models, but obtaining high-quality human annotations is costly. Click data has been widely used as a low-cost alternative, and with recent advances in large language models (LLMs), LLM-based relevance annotation has emerged as another promising annotation. This paper investigates whether LLM annotations can replace click data for learning to rank (LTR) by conducting a comprehensive comparison across multiple dimensions. Experiments on both a public dataset, TianGong-ST, and an industrial dataset, Baidu-Click, show that click-supervised models perform better on high-frequency queries, while LLM annotation-supervised models are more effective on medium- and low-frequency queries. Further analysis shows that click-supervised models are better at capturing document-level signals such as authority or quality, while LLM annotation-supervised models are more effective at modeling semantic matching between queries and documents and at distinguishing relevant from non-relevant documents. Motivated by these observations, we explore two training strategies -- data scheduling and frequency-aware multi-objective learning -- that integrate both supervision signals. Both approaches enhance ranking performance across queries at all frequency levels, with the latter being more effective. Our code is available at https://github.com/Trustworthy-Information-Access/LLMAnn_Click.

cs.IR↗

arXiv2025

Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling

Dense retrieval is a crucial task in Information Retrieval (IR), serving as the basis for downstream tasks such as re-ranking and augmenting generation. Recently, large language models (LLMs) have demonstrated impressive semantic understanding capabilities, making them attractive to researchers focusing on dense retrieval. While LLMs, as decoder-style generative models, excel in language generation, they often fall short in modeling global information due to a lack of attention to subsequent tokens. Drawing inspiration from the classical word-based language modeling approach for IR, specifically the query likelihood (QL) model, we aim to leverage the generative strengths of LLMs through QL maximization. Rather than employing QL estimation for document ranking, we propose an auxiliary task of QL maximization to enhance the backbone for subsequent contrastive learning of the retriever. We introduce our model, LLM-QL, which incorporates two key components: Attention Block (AB) and Document Corruption (DC). AB blocks the attention of predictive tokens to the document tokens before the document's ending token, while DC corrupts a document by masking a portion of its tokens during prediction. Evaluations on the in-domain (MS MARCO) and out-of-domain dataset (BEIR) indicate LLM-QL's superiority over other LLM-based retrievers. Furthermore, comprehensive analyses also validate the efficacy of LLM-QL and its components.

cs.IR↗

arXiv2025

Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation

This paper explores the use of large language models (LLMs) for annotating document utility in training retrieval and retrieval-augmented generation (RAG) systems, aiming to reduce dependence on costly human annotations. We address the gap between retrieval relevance and generative utility by employing LLMs to annotate document utility. To effectively utilize multiple positive samples per query, we introduce a novel loss that maximizes their summed marginal likelihood. Using the Qwen-2.5-32B model, we annotate utility on the MS MARCO dataset and conduct retrieval experiments on MS MARCO and BEIR, as well as RAG experiments on MS MARCO QA, NQ, and HotpotQA. Our results show that LLM-generated annotations enhance out-of-domain retrieval performance and improve RAG outcomes compared to models trained solely on human annotations or downstream QA metrics. Furthermore, combining LLM annotations with just 20% of human labels achieves performance comparable to using full human annotations. Our study offers a comprehensive approach to utilizing LLM annotations for initializing QA systems on new corpora.

cs.IR↗

arXiv2025

Unbiased Learning to Rank with Query-Level Click Propensity Estimation: Beyond Pointwise Observation and Relevance

Most existing unbiased learning-to-rank (ULTR) approaches are based on the user examination hypothesis, which assumes that users will click a result only if it is both relevant and observed (typically modeled by position). However, in real-world scenarios, users often click only one or two results after examining multiple relevant options, due to limited patience or because their information needs have already been satisfied. Motivated by this, we propose a query-level click propensity model to capture the probability that users will click on different result lists, allowing for non-zero probabilities that users may not click on an observed relevant result. We hypothesize that this propensity increases when more potentially relevant results are present, and refer to this user behavior as relevance saturation bias. Our method introduces a Dual Inverse Propensity Weighting (DualIPW) mechanism -- combining query-level and position-level IPW -- to address both relevance saturation and position bias. Through theoretical derivation, we prove that DualIPW can learn an unbiased ranking model. Experiments on the real-world Baidu-ULTR dataset demonstrate that our approach significantly outperforms state-of-the-art ULTR baselines. The code and dataset information can be found at https://github.com/Trustworthy-Information-Access/DualIPW.

cs.IR↗

arXiv2025

Generative Retrieval for Book search

In book search, relevant book information should be returned in response to a query. Books contain complex, multi-faceted information such as metadata, outlines, and main text, where the outline provides hierarchical information between chapters and sections. Generative retrieval (GR) is a new retrieval paradigm that consolidates corpus information into a single model to generate identifiers of documents that are relevant to a given query. How can GR be applied to book search? Directly applying GR to book search is a challenge due to the unique characteristics of book search: The model needs to retain the complex, multi-faceted information of the book, which increases the demand for labeled data. Splitting book information and treating it as a collection of separate segments for learning might result in a loss of hierarchical information. We propose an effective Generative retrieval framework for Book Search (GBS) that features two main components: data augmentation and outline-oriented book encoding. For data augmentation, GBS constructs multiple query-book pairs for training; it constructs multiple book identifiers based on the outline, various forms of book contents, and simulates real book retrieval scenarios with varied pseudo-queries. This includes coverage-promoting book identifier augmentation, allowing the model to learn to index effectively, and diversity-enhanced query augmentation, allowing the model to learn to retrieve effectively. Outline-oriented book encoding improves length extrapolation through bi-level positional encoding and retentive attention mechanisms to maintain context over long sequences. Experiments on a proprietary Baidu dataset demonstrate that GBS outperforms strong baselines, achieving a 9.8\% improvement in terms of MRR@20, over the state-of-the-art RIPOR method...

cs.IR↗

arXiv2024

Comprehensive Study on the Slat Noise of 30P30N High-Lift Airfoil Basd on High-Order Wall-Resolved Large-Eddy Simulation

This study presents wall-resolved large-eddy simulations (WRLES) of a high-lift airfoil, based on high-order flux reconstruction (FR) commercial software Dimaxer, which runs on consumer level GPUs. A series of independence tests are conducted, including various Ffowcs Williams-Hawkings sampling surfaces, different mesh densities, simulations at 4th and 5th order accuracies, and varying spanwise lengths, to establish best practice for predicting slat noise through high-order WRLES. The results show excellent agreement with experimental data while requiring significantly fewer computational resources than traditional second-order methods. An investigation on the effects of Reynolds number (Re) is performed by scaling the airfoil size, with Reynolds numbers ranging from 8.55e5 to a real aircraft level of 1.71e7. By applying simple scaling through Strouhal number (St), spanwise correction, and distance from the receiver, the far-field noise spectra for different Reynolds numbers can be coincided. Additionally, simulations are performed at four angles of attack: 3{\deg}, 5.5{\deg}, 9.5{\deg}, and 14{\deg}. The results indicate that higher angles of attack lead to a less intense feedback loop, resulting in lower tonal noise frequencies and reduced noise amplitude. The maximum noise reduction observed is over 14dB when comparing 14{\deg} to 3{\deg}. Furthermore, an improved formula is proposed to enhance the prediction of slat noise tonal frequencies and to better elucidate the mechanism behind tonal noise generation.

physics.flu-dyn↗

arXiv2024

InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct

Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it is possible to use a fine-tuned open-source model to generate additional data to augment its instruction-tuning dataset. We make two observations: (1) A code snippet can serve as the response to different instructions. (2) Instruction-tuned code LLMs perform better at translating code into instructions than the reverse. Based on these observations, we propose Inverse-Instruct, a data augmentation technique that uses a fine-tuned LLM to generate additional instructions of code responses from its own training dataset. The additional instruction-response pairs are added to the original dataset, and a stronger code LLM can be obtained by fine-tuning on the augmented dataset. We empirically validate Inverse-Instruct on a range of open-source code models (e.g. CodeLlama-Python and DeepSeek-Coder) and benchmarks (e.g., HumanEval(+), MBPP(+), DS-1000 and MultiPL-E), showing it consistently improves the base models.

cs.CL↗

arXiv2024

A new type of simplified inverse Lax-Wendroff boundary treatment I: hyperbolic conservation laws

In this paper, we design a new kind of high order inverse Lax-Wendroff (ILW) boundary treatment for solving hyperbolic conservation laws with finite difference method on a Cartesian mesh. This new ILW method decomposes the construction of ghost point values near inflow boundary into two steps: interpolation and extrapolation. At first, we impose values of some artificial auxiliary points through a polynomial interpolating the interior points near the boundary. Then, we will construct a Hermite extrapolation based on those auxiliary point values and the spatial derivatives at boundary obtained via the ILW procedure. This polynomial will give us the approximation to the ghost point value. By an appropriate selection of those artificial auxiliary points, high-order accuracy and stable results can be achieved. Moreover, theoretical analysis indicates that comparing with the original ILW method, especially for higher order accuracy, the new proposed one would require fewer terms using the relatively complicated ILW procedure and thus improve computational efficiency on the premise of maintaining accuracy and stability. We perform numerical experiments on several benchmarks, including one- and two-dimensional scalar equations and systems. The robustness and efficiency of the proposed scheme is numerically verified.

math.NA↗

arXiv2023

Enhancing Cell Proliferation and Migration by MIR-Carbonyl Vibrational Coupling: Insights from Transcriptome Profiling

Cell proliferation and migration highly relate to normal tissue self-healing, therefore it is highly significant for artificial controlling. Recently, vibrational strong coupling between biomolecules and Mid-infrared (MIR) light photons has been successfully used to modify in vitro bioreactions, neuronal signaling and even animal behavior. However, the synergistic effects from molecules to cells remains unclear, and the regulation of MIR on cells needs to be explained from the molecular level. Herein, the proliferation rate and migration capacity of fibroblasts were increased by 156% and 162.5%, respectively, by vibratory coupling of 5.6 micrometers photons with carbonyl groups in biomolecules. Through transcriptome sequencing analysis, the regulatory mechanism of infrared light in 5.6 micrometers was explained from the level of signal pathway and cell components. 5.6 micrometers optical high power lasers can regulate cell function through vibrational strong coupling while minimizing photothermal damage. This work not only sheds light on the non-thermal effect on MIR light-based on wound healing, but also provides new evidence to future frequency medicine.

q-bio.GN↗

arXiv2023

Regulating the Hydrophobic Domain in Peptide-Catecholamine Coassembled Nanostructures for Fluorescence Enhancement

Hydrophobic domains provide specific microenvironment for essential functional activities in life. Herein, we studied how the coassembling of peptides with catecholamines regulate the hydrophobic domain-containing nanostructures for fluorescence enhancement. By peptide encoding and coassembling with catecholamines of different hydrophilicities, a series of hierarchical assembling systems were constructed. In combination with molecular dynamics simulation, we experimentally discovered the hydrophobic domain of chromophore microenvironment regulates the fluorescence of coassembled nanostructures. Our results shed light on the rational design of fluorescent bio-coassembled nanoprobes for biomedical applications.

q-bio.BM↗

arXiv2017

MSR-net:Low-light Image Enhancement Using Deep Convolutional Network

Images captured in low-light conditions usually suffer from very low contrast, which increases the difficulty of subsequent computer vision tasks in a great extent. In this paper, a low-light image enhancement model based on convolutional neural network and Retinex theory is proposed. Firstly, we show that multi-scale Retinex is equivalent to a feedforward convolutional neural network with different Gaussian convolution kernels. Motivated by this fact, we consider a Convolutional Neural Network(MSR-net) that directly learns an end-to-end mapping between dark and bright images. Different fundamentally from existing approaches, low-light image enhancement in this paper is regarded as a machine learning problem. In this model, most of the parameters are optimized by back-propagation, while the parameters of traditional models depend on the artificial setting. Experiments on a number of challenging images reveal the advantages of our method in comparison with other state-of-the-art methods from the qualitative and quantitative perspective.

cs.CV↗