arXiv subjects

Haoliang Liu

Publications and source records attributed to Haoliang Liu.

8 recordsLinked to original sources

arXiv2026

BCL: Bayesian In-Context Learning Framework for Information Extraction

Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance across model scales or lack systematic optimization and generalizability. Building on this, we propose BCL (Bayesian In-Context Learning Framework for Information Extraction), the first optimization framework that uses particle filtering with Bayesian updates to systematically refine label representations across IE tasks. Through four steps initialization, observation, weight update, and resampling, BCL generalizes to both sequence labeling and relation classification paradigms. Extensive experiments demonstrate substantial and consistent improvements over existing approaches.

cs.CL↗

arXiv2026

E2CAR: An Efficient 2D-CNN Framework for Real-Time EEG Artifact Removal on Edge Devices

Electroencephalography (EEG) signals are frequently contaminated by artifacts, affecting the accuracy of subsequent analysis. Traditional artifact removal methods are often computationally expensive and inefficient for real-time applications in edge devices. This paper presents a method to reduce the computational cost of most existing convolutional neural networks (CNN) by replacing one-dimensional (1-D) CNNs with two-dimensional (2-D) CNNs and deploys them on Edge Tensor Processing Unit (TPU), which is an open-resource hardware accelerator widely used in edge devices for low-latency, low-power operation. A new Efficient 2D-CNN Artifact Removal (E2CAR) framework is also represented using the method above, and it achieves a 90\% reduction in inference time on the TPU and decreases power consumption by 18.98\%, while maintaining comparable artifact removal performance to existing methods. This approach facilitates efficient EEG signal processing on edge devices.

eess.SP↗

arXiv2025

Bayesian Optimization for Controlled Image Editing via LLMs

In the rapidly evolving field of image generation, achieving precise control over generated content and maintaining semantic consistency remain significant limitations, particularly concerning grounding techniques and the necessity for model fine-tuning. To address these challenges, we propose BayesGenie, an off-the-shelf approach that integrates Large Language Models (LLMs) with Bayesian Optimization to facilitate precise and user-friendly image editing. Our method enables users to modify images through natural language descriptions without manual area marking, while preserving the original image's semantic integrity. Unlike existing techniques that require extensive pre-training or fine-tuning, our approach demonstrates remarkable adaptability across various LLMs through its model-agnostic design. BayesGenie employs an adapted Bayesian optimization strategy to automatically refine the inference process parameters, achieving high-precision image editing with minimal user intervention. Through extensive experiments across diverse scenarios, we demonstrate that our framework significantly outperforms existing methods in both editing accuracy and semantic preservation, as validated using different LLMs including Claude3 and GPT-4.

cs.CV↗

arXiv2024

The Role of Deductive and Inductive Reasoning in Large Language Models

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning tasks, yet their reliance on static prompt structures and limited adaptability to complex scenarios remains a significant challenge. In this paper, we propose the Deductive and InDuctive(DID) method, a novel framework that enhances LLM reasoning by dynamically integrating both deductive and inductive reasoning approaches. Drawing from cognitive science principles, DID implements a dual-metric complexity evaluation system that combines Littlestone dimension and information entropy to precisely assess task difficulty and guide decomposition strategies. DID enables the model to progressively adapt its reasoning pathways based on problem complexity, mirroring human cognitive processes. We evaluate DID's effectiveness across multiple benchmarks, including the AIW and MR-GSM8K, as well as our custom Holiday Puzzle dataset for temporal reasoning. Our results demonstrate significant improvements in reasoning quality and solution accuracy - achieving 70.3% accuracy on AIW (compared to 62.2% for Tree of Thought) while maintaining lower computational costs. The success of DID in improving LLM performance while preserving computational efficiency suggests promising directions for developing more cognitively aligned and capable language models. Our work contributes a theoretically grounded, input-centric approach to enhancing LLM reasoning capabilities, offering an efficient alternative to traditional output-exploration methods.

cs.AI↗

arXiv2024

$T^2$ of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models

Large Language Models (LLMs) have emerged as powerful tools in artificial intelligence, especially in complex decision-making scenarios, but their static problem-solving strategies often limit their adaptability to dynamic environments. We explore the enhancement of reasoning capabilities in LLMs through Temperature Tree ($T^2$) prompting via a heuristic algorithm, termed as $T^2$ of Thoughts ($T^2oT$). The primary focus is on enhancing decision-making processes by dynamically adjusting search parameters, especially temperature, to improve accuracy without increasing computational demands. We empirically validate that our hybrid $T^2oT$ approach yields enhancements in, single-solution accuracy, multi-solution generation and text generation quality. Our findings suggest that while dynamic search depth adjustments based on temperature can yield mixed results, a fixed search depth, when coupled with adaptive capabilities of $T^2oT$, provides a more reliable and versatile problem-solving strategy. This work highlights the potential for future explorations in optimizing algorithmic interactions with foundational language models, particularly illustrated by our development for the Game of 24 and Creative Writing tasks.

cs.CL↗

arXiv2023

ScaleLat: A chemical structure matching algorithm for mapping atomic structure of multi-phase system and high entropy alloys

ScaleLat (Scale Lattice) is a computer program written in C for performing the atomic structure analysis of multi-phase system or high entropy alloys (HEAs). The program implements an atomic cluster extraction algorithm to obtain all independent and symmetry-reduced characteristic chemical structures for the complex atomic configurations which are usually obtained from molecular dynamics or kinetic Monte-Carlo simulations for supercell containing more than 104 atoms. ScaleLat employes an efficient and unique chemical structure matching algorithm to map all extracted atomic clusters from a large supercell (>10^4 atoms) to a representative small one (~ 10^3 or less), providing the possibility to directly use the highly accurate quantum mechanical methods to study the electronic, magnetic, and mechanical properties of multi-component alloys with complex microstructures. We demonstrate the capability of ScaleLat code by conducting both the atomic structure analysis and chemical structure matching procedure for Fe-12.8 at.% Cr binary alloy and equiatomic CrFeCoNiCu high entropy alloy, and by successfully obtaining the representatively supercells containing 10^2~10^3 atoms of the two alloys. Overall, ScaleLat program provides a universal platform to efficiently project all essential chemical structures of large complex atomic structures to a relatively easy-handling small supercell for quantum mechanical calculations of various user interested properties.

cond-mat.mtrl-sci↗

arXiv2023

Assessing r2SCAN meta-GGA functional for structural parameters, cohesive energy, mechanical modulus and thermophysical properties of 3d, 4d and 5d transition metals

The recent development of the accurate and efficient semilocal density functionals on the third rung of Jacob's ladder of density functional theory such as the revised regularized strongly constrained and appropriately normed (r2SCAN) density functional could enable the rapid and highly reliable prediction of the elasticity and temperature dependence of thermophysical parameters of refractory elements and their intermetallic compounds using quasi-harmonic approximation (QHA). Here, we present a comparative evaluation of the equilibrium cell volumes, cohesive energy, mechanical moduli, and thermophysical properties (Debye temperature and thermal expansion coefficient) for 22 transition metals using semilocal density functionals, including local density approximation (LDA), the Perdew-Burke-Ernzerhof (PBE) and PBEsol generalized gradient approximations (GGA), and the r2SCAN meta-GGA. PBEsol and r2SCAN deliver the same level of accuracies for structural, mechanical and thermophysical properties. Otherwise, PBE and r2SCAN perform better than LDA and PBEsol for calculating cohesive energies of transition metals. Among the tested density functionals, r2SCAN provides an overall well-balanced performance for reliably computing the cell volumes, cohesive energies, mechanical properties, and thermophysical properties of various 3d, 4d, and 5d transition metals using QHA. Therefore, we recommend that r2SCAN could be employed as a workhorse method to evaluate the thermophysical properties of transition metal compounds and alloys in the high throughput workflows.

physics.comp-ph↗

arXiv2018

Topological Insulator-Based van der Waals Heterostructures for Effective Control of Massless and Massive Dirac Fermions

Three dimensional (3D) topological insulators (TIs) are an important class of materials with applications in electronics, spintronics and quantum computing. With the recent development of truly bulk insulating 3D TIs, it has become possible to realize surface dominated phenomena in electrical transport measurements e.g. the quantum Hall (QH) effect of massless Dirac fermions in topological surface states (TSS). However, to realize more advanced devices and phenomena, there is a need for a platform to tune the TSS or modify them e.g. gap them by proximity with magnetic insulators, in a clean manner. Here we introduce van der Waals (vdW) heterostructures in the form of topological insulator/insulator/graphite to effectively control chemical potential of the TSS. Two types of gate dielectrics, normal insulator hexagonal boron nitride (hBN) and ferromagnetic insulator Cr2Ge2Te6 (CGT) are utilized to tune charge density of TSS in the quaternary TI BiSbTeSe2. hBN/graphite gating in the QH regime shows improved quantization of TSS by suppression of magnetoconductivity of massless Dirac fermions. CGT/graphite gating of massive Dirac fermions in the QH regime yields half-quantized Hall conductance steps and a measure of the Dirac gap. Our work shows the promise of the vdW platform in creating advanced high-quality TI-based devices.

cond-mat.mes-hall↗