arXiv subjects

Anastasia Volkova

Publications and source records attributed to Anastasia Volkova.

10 recordsLinked to original sources

arXiv2026

CoMa: Contextual Massing Generation with Vision-Language Models

Context-aware building massing is an important early-stage design task: given a site for buildings, a generated massing should not only fit the target parcel, but also relate to the scale, density, and morphology of its surrounding urban fabric. This task is naturally multimodal, since the target output should remain structured and editable, while the surrounding context, including other buildings or roads, can be represented as vector geometry, map imagery, or three-dimensional views. In this paper, we study contextual massing generation using vision-language models (VLMs) and analyze their performance on this task across different context modalities during training and inference. We assemble an experimental dataset of 12,845 Melbourne massings with parcel contours, structured 3D geometry, neighboring buildings, top-down views, and multi-view 3D context images. We also introduce a learned contextual relevance metric for evaluating whether generated massings are morphologically compatible with their surrounding context. Using Qwen3-VL models, we compare no-context, unimodal-context, and multimodal-context training regimes and evaluate inference performance under controlled combinations of modalities and amounts of context. The results show that model size strongly affects generation quality, multimodal training improves the use of individual modalities, and multimodal inference provides a stronger contextual signal than isolated context inputs.

cs.CV↗

arXiv2026

Decompose, Optimize, and Reconstruct: Very Large Constant Multiplication at Scale

Efficient arithmetic circuit design for resourceconstrained hardware involves challenging combinatorial optimization problems, among which Multiple Constant Multiplication (MCM) is a prominent example. MCM aims at implementing multiplications by fixed integer constants using bit-shifts and additions/subtractions but optimal methods are typically limited to moderately-sized constants, e.g. 12 bits. For practical applications targeting larger precision, Very large Constant Multiplication (VLCM) is solved instead. Existing approaches typically address VLCM through a heuristic flow that decomposes large constants into patterns, applies MCM optimization techniques on moderately-sized targets, and reconstructs the final result. This paper proposes multiple improvements to this flow: new declarative optimization models for the pattern selection and for the reconstruction, as well as applying recent optimal MCM models. The cornerstones of the obtained improvements are (i) allowing the patterns to overlap, minimising the number of unique target constants for the MCM step and (ii) performing the reconstruction step optimally, instead of heuristically. In addition, we propose a globally-optimal VLCM approach and characterize its limits. We employ a mix of constraint programming and SAT to solve each step. Experimental results on synthetic and real-life signal processing and cryptographic benchmarks, with coefficient word lengths ranging from tens to thousands of bits, demonstrate that the proposed approach scales to very large precisions and consistently outperforms existing baselines.

cs.AR↗

arXiv2025

Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphs

While Retrieval-Augmented Generation (RAG) methods commonly draw information from unstructured documents, the emerging paradigm of GraphRAG aims to leverage structured data such as knowledge graphs. Most existing GraphRAG efforts focus on Resource Description Framework (RDF) knowledge graphs, relying on triple representations and SPARQL queries. However, the potential of Cypher and Labeled Property Graph (LPG) databases to serve as scalable and effective reasoning engines within GraphRAG pipelines remains underexplored in current research literature. To fill this gap, we propose Multi-Agent GraphRAG, a modular LLM agentic system for text-to-Cypher query generation serving as a natural language interface to LPG-based graph data. Our proof-of-concept system features an LLM-based workflow for automated Cypher queries generation and execution, using Memgraph as the graph database backend. Iterative content-aware correction and normalization, reinforced by an aggregated feedback loop, ensures both semantic and syntactic refinement of generated queries. We evaluate our system on the CypherBench graph dataset covering several general domains with diverse types of queries. In addition, we demonstrate performance of the proposed workflow on a property graph derived from the IFC (Industry Foundation Classes) data, representing a digital twin of a building. This highlights how such an approach can bridge AI with real-world applications at scale, enabling industrial digital automation use cases.

cs.AI↗

arXiv2024

Towards Fixed-Point Formats Determination for Faust Programs

Modern programmable digital signal processing relies on floating-point numbers for their ease of use. Fixed-point number formats have the potential to save resources and improve execution time, but realising this potential burdens the programmer with the need to define each format, at every step of the computation. This article reviews existing methods to automatically determine fixed-point formats, then describes and evaluates the prototype implementation of automatic fixed-point format determination in the Faust compiler.

cs.PL↗

arXiv2022

Towards the Multiple Constant Multiplication at Minimal Hardware Cost

Multiple Constant Multiplication (MCM) over integers is a frequent operation arising in embedded systems that require highly optimized hardware. An efficient way is to replace costly generic multiplication by bit-shifts and additions, i.e. a multiplierless circuit. In this work, we improve the state-of-the-art optimal approach for MCM, based on Integer Linear Programming (ILP). We introduce a new lower-level hardware cost, based on counting the number of one-bit adders and demonstrate that it is strongly correlated with the LUT count. This new model for the multiplierless MCM circuits permitted us to consider intermediate truncations that permit to significantly save resources when a full output precision is not required. We incorporate the error propagation rules into our ILP model to guarantee a user-given error bound on the MCM results. The proposed ILP models for multiple flavors of MCM are implemented as an open-source tool and, combined with the FloPoCo code generator, provide a complete coefficient-to-VHDL flow. We evaluate our models in extensive experiments, and propose an in-depth analysis of the impact that design metrics have on actually synthesized hardware.

cs.AR↗

arXiv2022

Dandelion: Certified Approximations of Elementary Functions

Elementary function operations such as sin and exp cannot in general be computed exactly on today's digital computers, and thus have to be approximated. The standard approximations in library functions typically provide only a limited set of precisions, and are too inefficient for many applications. Polynomial approximations that are customized to a limited input domain and output accuracy can provide superior performance. In fact, the Remez algorithm computes the best possible approximation for a given polynomial degree, but has so far not been formally verified. This paper presents Dandelion, an automated certificate checker for polynomial approximations of elementary functions computed with Remez-like algorithms that is fully verified in the HOL4 theorem prover. Dandelion checks whether the difference between a polynomial approximation and its target reference elementary function remains below a given error bound for all inputs in a given constraint. By extracting a verified binary with the CakeML compiler, Dandelion can validate certificates within a reasonable time, fully automating previous manually verified approximations.

cs.PL↗

arXiv2021

Hardware-aware Design of Multiplierless Second-Order IIR Filters with Minimum Adders

In this work, we optimally solve the problem of multiplierless design of second-order Infinite Impulse Response filters with minimum number of adders. Given a frequency specification, we design a stable direct form filter with hardware-aware fixed-point coefficients that yielding minimal number of adders when replacing all the multiplications by bit shifts and additions. The coefficient design, quantization and implementation, typically conducted independently, are now gathered into one global optimization problem, modeled through integer linear programming and efficiently solved using generic solvers. We guarantee the frequency-domain specifications and stability, which together with optimal number of adders will significantly simplify design-space exploration for filter designers. The optimal filters are implemented within the FloPoCo IP core generator and synthesized for Field Programmable Gate Arrays. With respect to state-of-the-art three-step filter design methods, our one-step design approach achieves, on average, 42% reduction in the number of lookup tables and 21% improvement in delay.

cs.AR↗

arXiv2020

A Framework for Semi-Automatic Precision and Accuracy Analysis for Fast and Rigorous Deep Learning

Deep Neural Networks (DNN) represent a performance-hungry application. Floating-Point (FP) and custom floating-point-like arithmetic satisfies this hunger. While there is need for speed, inference in DNNs does not seem to have any need for precision. Many papers experimentally observe that DNNs can successfully run at almost ridiculously low precision. The aim of this paper is two-fold: first, to shed some theoretical light upon why a DNN's FP accuracy stays high for low FP precision. We observe that the loss of relative accuracy in the convolutional steps is recovered by the activation layers, which are extremely well-conditioned. We give an interpretation for the link between precision and accuracy in DNNs. Second, the paper presents a software framework for semi-automatic FP error analysis for the inference phase of deep-learning. Compatible with common Tensorflow/Keras models, it leverages the frugally-deep Python/C++ library to transform a neural network into C++ code in order to analyze the network's need for precision. This rigorous analysis is based on Interval and Affine arithmetics to compute absolute and relative error bounds for a DNN. We demonstrate our tool with several examples.

cs.LG↗

arXiv2019

Design of Optimal Multiplierless FIR Filters

This work presents two novel optimization methods based on integer linear programming (ILP) that minimize the number of adders used to implement a direct/transposed finite impulse response (FIR) filter adhering to a given frequency specification. The proposed algorithms work by either fixing the number of adders used to implement the products (multiplier block adders) or by bounding the adder depth (AD) used for these products. The latter can be used to design filters with minimal AD for low power applications. In contrast to previous multiplierless FIR approaches, the methods introduced here ensure adder count optimality. To demonstrate their effectiveness, we perform several experiments using established design problems from the literature, showing superior results.

eess.SP↗

arXiv2018

Sound Approximation of Programs with Elementary Functions

Elementary function calls are a common feature in numerical programs. While their implementions in library functions are highly optimized, their computation is nonetheless very expensive compared to plain arithmetic. Full accuracy is, however, not always needed. Unlike arithmetic, where the performance difference between for example single and double precision floating-point arithmetic is relatively small, elementary function calls provide a much richer tradeoff space between accuracy and efficiency. Navigating this space is challenging. First, generating approximations of elementary function calls which are guaranteed to satisfy accuracy error bounds is highly nontrivial. Second, the performance of such approximations generally depends on several parameters which are unintuitive to choose manually, especially for non-experts. We present a fully automated approach and tool which approximates elementary function calls inside small programs while guaranteeing overall user provided error bounds. Our tool leverages existing techniques for roundoff error computation and approximation of individual elementary function calls, and provides automated selection of many parameters. Our experiments show that significant efficiency improvements are possible in exchange for reduced, but guaranteed, accuracy.

math.NA↗