Related papers: Tokenization Allows Multimodal Large Language Mode…

The recent advancements introduced by Large Language Models (LLMs) have transformed how Artificial Intelligence (AI) can support complex, real world tasks, pushing research outside the text boundaries towards multi modal contexts and…

Large language models have demonstrated exceptional performance, yet struggle with complex tasks such as numerical reasoning, plan generation. Integrating external tools, such as calculators and databases, into large language models (LLMs)…

The geometric evolution of token representations in large language models (LLMs) presents a fundamental paradox: while human language inherently organizes semantic information in low-dimensional spaces ($\sim 10^1$ dimensions), modern LLMs…

Tokenization serves as a foundational step for Large Language Models (LLMs) to process text. In new domains or languages, the inefficiency of the tokenizer will slow down the training and generation of LLM. The mismatch in vocabulary also…

In this work, we propose HypergraphFormer, a novel and efficient approach to floor plan generation based on learning hypergraph representations with a large language model (LLM). The model is trained via supervised fine-tuning to generate a…

Multimodal models are expected to be a critical component to future advances in artificial intelligence. This field is starting to grow rapidly with a surge of new design elements motivated by the success of foundation models in natural…

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but they continue to struggle with spatial understanding. Existing spatial MLLMs often rely on explicit 3D inputs or architecture-specific…

The pursuit of artificial general intelligence (AGI) has been accelerated by Multimodal Large Language Models (MLLMs), which exhibit superior reasoning, generalization capabilities, and proficiency in processing multimodal inputs. A crucial…

Despite Multi-modal Large Language Models (MM-LLMs) have made exciting strides recently, they are still struggling to efficiently model the interactions among multi-modal inputs and the generation in non-textual modalities. In this work, we…

Text and time series data offer complementary views of financial markets: news articles provide narrative context about company events, while stock prices reflect how markets react to those events. However, despite their complementary…

Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each task, respectively. Existing approaches rely on spatial visual…

LLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool for many tasks. The current established technology of LLMs is to process input and generate output at the token level. This is in sharp…

Recent advancements in large language models (LLMs) have remarkably enhanced performances on a variety of tasks in multiple languages. However, tokenizers in LLMs trained primarily on English-centric corpora often overly fragment a text…

SpatialLM is a large language model designed to process 3D point cloud data and generate structured 3D scene understanding outputs. These outputs include architectural elements like walls, doors, windows, and oriented object boxes with…

We introduce Blueprint-Bench, a benchmark designed to evaluate spatial reasoning capabilities in AI models through the task of converting apartment photographs into accurate 2D floor plans. While the input modality (photographs) is well…

Language models (LMs) have demonstrated their capability in possessing commonsense knowledge of the physical world, a crucial aspect of performing tasks in everyday life. However, it remains unclear **whether LMs have the capacity to…

Effective foundation modeling in remote sensing requires spatially aligned heterogeneous modalities coupled with semantically grounded supervision, yet such resources remain limited at scale. We present GeoMeld, a large-scale multimodal…

Large language models (LLMs) have demonstrated impressive results in developing generalist planning agents for diverse tasks. However, grounding these plans in expansive, multi-floor, and multi-room environments presents a significant…

Masked image modeling (MIM) has emerged as a promising approach for pre-training Vision Transformers (ViTs). MIMs predict masked tokens token-wise to recover target signals that are tokenized from images or generated by pre-trained models…

Converting raster floorplans into engineering-grade vector graphics is challenging due to complex topology and strict geometric constraints. To address this, we present FloorplanVLM, a unified framework that reformulates floorplan…