Related papers: FloorSet -- a VLSI Floorplanning Dataset with Design Constraints of Real-World SoCs

Related papers

Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts [13.835014453826057]
We develop MOSAIC, which formulates model architecture and systems co-design.<n>We instantiate the framework for sparse Mixture-of-Experts (MoE) language models.<n>We show that, within the calibrated sparsity range, an efficiency-agnostic model-FLOPs budget admits no interior optimal sparsity.
arXiv Detail & Related papers (2026-08-11T07:49:00Z)
STAIF: A Stage-wise Optimization for Complex Instruction Following [50.48101504556211]
STAIF is a stage-wise optimization framework that decouples the alignment of subjective (soft) constraints from the optimization of objectively verifiable (hard) constraints.<n>To support this method, we construct STAINSTRUCT, a high-quality bilingual (English, Chinese) dataset of approximately 31,000 complex multi-constraint instructions.
arXiv Detail & Related papers (2026-06-26T06:14:07Z)
Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards [16.41930427892441]
An AI system for professional floor plan design must precisely control room dimensions and areas while respecting the desired connectivity between rooms.<n>Existing generative approaches focus primarily on respecting the requested connectivity between rooms, but do not support generating floor plans that respect numerical constraints.<n>We introduce a text-based floor plan generation approach that fine-tunes a large language model (LLM) on real plans and then applies reinforcement learning with verifiable rewards.<n>Our results demonstrate that LLMs can effectively handle constraints in this setting, suggesting broader applications for text-based generative modeling.
arXiv Detail & Related papers (2026-05-13T21:06:12Z)
Unified Vector Floorplan Generation via Markup Representation [36.228613615394856]
We introduce Floorplan Markup Language (FML), a representation that encodes floorplan information within a single structured grammar.<n>We develop a transformer-based generative model, FMLM, capable of producing high-fidelity and functional floorplans under diverse conditions.
arXiv Detail & Related papers (2026-04-06T17:04:30Z)
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels [49.35636088613484]
Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces.<n>We introduce LeModelWorld, the first JEPA that trains stably end-to-end from raw pixels using only two loss terms.<n>With 15M parameters trainable on a single GPU in a few hours, LeWM plans up to 48x faster than foundation-model-based world models.
arXiv Detail & Related papers (2026-03-13T19:48:14Z)
TLC-Plan: A Two-Level Codebook Based Network for End-to-End Vector Floorplan Generation [19.063941053235567]
We propose TLC-Plan, a hierarchical generative model that directly synthesizes vectors from spatial input boundaries.<n>TLC-Plan employs a two-level VQ-VAE to encode global layouts as semantically labeled room bounding boxes.<n>Experiments show state-of-the-art performance on RPLAN dataset and leading results on LI dataset.
arXiv Detail & Related papers (2026-02-06T15:36:50Z)
FloorplanVLM: A Vision-Language Model for Floorplan Vectorization [15.691267151619442]
We present FloorplanVLM, a unified framework that reformulates vectorization as an image-conditioned sequence modeling task.<n>This 'pixels-to-sequence' paradigm enables the precise and holistic constraint satisfaction of complex grounding, such as walls and curved arcs.
arXiv Detail & Related papers (2026-02-06T08:57:52Z)
THOR: A Versatile Foundation Model for Earth Observation Climate and Society Applications [9.852915112122567]
THOR is a "computeadaptive" foundation model that solves both input heterogeneity and deployment rigidity.<n>We pre-train THOR with a novel randomized patch and input image size strategy.<n>This allows a single set of pre-trained weights to be deployed at inference with any patch size, enabling a dynamic trade-off between computational cost and feature resolution without retraining.
arXiv Detail & Related papers (2026-01-22T14:38:00Z)
DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models [103.18486625853099]
DEFT, Decompositional Efficient Fine-Tuning, adapts a pre-trained weight matrix by decomposing its update into two components.<n>We conduct experiments on the Dreambooth and Dreambench Plus datasets for personalization, the InsDet dataset for object and scene adaptation, and the VisualCloze dataset for a universal image generation framework.
arXiv Detail & Related papers (2025-09-26T18:01:15Z)
PlanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations [75.04864582433879]
PlanQA is a diagnostic benchmark for evaluating geometric and spatial reasoning in large-language models.<n>The benchmark uncovers diverse question types that test not only metric and topological reasoning but also interior design constraints.
arXiv Detail & Related papers (2025-07-10T11:16:48Z)
OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization [54.60030826635478]
Existing indoor layout generation methods fall into two categories: prompt-driven and learning-based.<n>We present 3D- SynthPlace, a large-scale dataset that combines synthetic layouts generated via a 'GPT synthesize, Human inspect' pipeline.<n>We introduce OptiScene, a strong open-source LLM optimized for indoor layout generation.
arXiv Detail & Related papers (2025-06-09T09:13:06Z)
HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs [15.575498324678373]
A promising compression scheme is to decompose foundation models' dense weights into a sum of sparse plus low-rank matrices. In this paper, we design a unified framework coined HASSLE-free for (semi-structured) sparse plus low-rank matrix decomposition.
arXiv Detail & Related papers (2025-02-02T20:23:32Z)
HouseTune: Two-Stage Floorplan Generation with LLM Assistance [10.558141230827847]
This paper proposes a two-stage text-to-floorplan framework that combines the reasoning capability of Large Language Models with the generative power of diffusion models. Experimental results demonstrate that our approach achieves state-of-the-art performance across all metrics, which validates its effectiveness in practical home design applications.
arXiv Detail & Related papers (2024-11-19T06:57:45Z)
Active Sampling of Interpolation Points to Identify Dominant Subspaces for Model Reduction [7.818201674097184]
We investigate model reduction for linear structured systems using dominant reachable and observable subspaces. When the training set $-$ containing all possible points $-$ is large, these subspaces can be determined by solving many large-scale linear systems. We propose an active sampling strategy to sample only a few points from the given training set, which can allow us to estimate those subspaces accurately.
arXiv Detail & Related papers (2024-09-05T19:59:14Z)
CFBench: A Comprehensive Constraints-Following Benchmark for LLMs [33.19756888719116]
CFBench is a large-scale Comprehensive Constraints Following Benchmark for Large Language Models. It features 1,000 curated samples that cover more than 200 real-life scenarios and over 50 NLP tasks. CFBench meticulously compiles constraints from real-world instructions and constructs an innovative systematic framework for constraint types.
arXiv Detail & Related papers (2024-08-02T09:03:48Z)
MSD: A Benchmark Dataset for Floor Plan Generation of Building Complexes [6.9924720592711935]
We develop textbfModified Swiss Dwellings (MSD) -- the first large-scale floor plan dataset that contains a significant share of layouts of multi-apartment dwellings. MSD features over 5.3K floor plans of medium- to large-scale building complexes, covering over 18.9K distinct apartments.
arXiv Detail & Related papers (2024-07-14T08:51:25Z)
360 Layout Estimation via Orthogonal Planes Disentanglement and Multi-view Geometric Consistency Perception [56.84921040837699]
Existing panoramic layout estimation solutions tend to recover room boundaries from a vertically compressed sequence, yielding imprecise results. We propose an orthogonal plane disentanglement network (termed DOPNet) to distinguish ambiguous semantics. We also present an unsupervised adaptation technique tailored for horizon-depth and ratio representations. Our solution outperforms other SoTA models on both monocular layout estimation and multi-view layout estimation tasks.
arXiv Detail & Related papers (2023-12-26T12:16:03Z)
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings [51.09574369310246]
Federated Learning (FL) is a novel approach enabling several clients holding sensitive data to collaboratively train machine learning models. We propose a novel cross-silo dataset suite focused on healthcare, FLamby, to bridge the gap between theory and practice of cross-silo FL. Our flexible and modular suite allows researchers to easily download datasets, reproduce results and re-use the different components for their research.
arXiv Detail & Related papers (2022-10-10T12:17:30Z)
$\texttt{FedBC}$: Calibrating Global and Local Models via Federated Learning Beyond Consensus [66.62731854746856]
In federated learning (FL), the objective of collaboratively learning a global model through aggregation of model updates across devices tends to oppose the goal of personalization via local information. In this work, we calibrate this tradeoff in a quantitative manner through a multi-criterion-based optimization. We demonstrate that $texttFedBC$ balances the global and local model test accuracy metrics across a suite datasets.
arXiv Detail & Related papers (2022-06-22T02:42:04Z)
Unsupervised Space Partitioning for Nearest Neighbor Search [6.516813715425121]
We propose an end-to-end learning framework that couples the partitioning and learning-to-search steps using a custom loss function. A key advantage of our proposed solution is that it does not require any expensive pre-processing of the dataset. We show that our method beats the state-of-the-art space partitioning method and the ubiquitous K-means clustering method.
arXiv Detail & Related papers (2022-06-16T11:17:03Z)
Data Summarization via Bilevel Optimization [48.89977988203108]
A simple yet powerful approach is to operate on small subsets of data. In this work, we propose a generic coreset framework that formulates the coreset selection as a cardinality-constrained bilevel optimization problem.
arXiv Detail & Related papers (2021-09-26T09:08:38Z)
Hybrid Federated Learning: Algorithms and Implementation [61.0640216394349]
Federated learning (FL) is a recently proposed distributed machine learning paradigm dealing with distributed and private data sets. We propose a new model-matching-based problem formulation for hybrid FL. We then propose an efficient algorithm that can collaboratively train the global and local models to deal with full and partial featured data.
arXiv Detail & Related papers (2020-12-22T23:56:03Z)
An Integer Linear Programming Framework for Mining Constraints from Data [81.60135973848125]
We present a general framework for mining constraints from data. In particular, we consider the inference in structured output prediction as an integer linear programming (ILP) problem. We show that our approach can learn to solve 9x9 Sudoku puzzles and minimal spanning tree problems from examples without providing the underlying rules.
arXiv Detail & Related papers (2020-06-18T20:09:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.