相关论文: SpatialTree: How Spatial Abilities Branch Out in M…

Vision-language models (VLMs) have advanced multimodal reasoning but still face challenges in spatial reasoning for 3D scenes and complex object configurations. To address this, we introduce SpatialViLT, an enhanced VLM that integrates…

This paper presents an in-depth examination of the evolution and interplay of cognitive and expressive capabilities in large language models (LLMs), with a specific focus on Baichuan-7B and Baichuan-33B, an advanced bilingual (Chinese and…

Large Language Models (LLMs) have undergone rapid progress, largely attributed to reinforcement learning on complex reasoning tasks. In contrast, while spatial intelligence is fundamental for Vision-Language Models (VLMs) in real-world…

In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized into sequential token representations. However, even when sufficient knowledge is…

We study the evolution of latent space in fine-tuned NLP models. Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations. More specifically, we discover latent concepts in the…

Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments. Despite their growing capability to perform multi-step reasoning and decision-making…

Solving long-horizon, temporally-extended tasks using Reinforcement Learning (RL) is challenging, compounded by the common practice of learning without prior knowledge (or tabula rasa learning). Humans can generate and execute plans with…

Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how to learn them automatically and effectively remains unclear. We introduce…

Reliable spatial reasoning remains a core bottleneck for vision-language models (VLMs). Existing mainstream training paradigms for spatial reasoning largely rely on outcome alignment or process imitation, lacking explicit constraints on the…

Large language models (LLMs) and vision language models (VLMs), such as DeepSeek R1,OpenAI o3, and Gemini 2.5 Pro, have demonstrated remarkable reasoning capabilities across logical inference, problem solving, and decision making. However,…

While diffusion models have shown exceptional capabilities in aesthetic image synthesis, they often struggle with complex spatial understanding and reasoning. Existing approaches resort to Multimodal Large Language Models (MLLMs) to enhance…

Recent supervised fine-tuning (SFT) approaches have significantly improved language models' performance on mathematical reasoning tasks, even when models are trained at a small scale. However, the specific capabilities enhanced through such…

Multimodal large language models (MLLMs) perform strongly on natural images, yet their ability to understand discrete visual symbols remains unclear. We present a multi-domain benchmark spanning language, culture, mathematics, physics and…

While Multimodal Large Language Models (MLLMs) excel in semantic tasks, they frequently lack the "spatial sense" essential for sophisticated geometric reasoning. Current models typically suffer from exorbitant modality-alignment costs and…

Multimodal large language models (MLLMs) have advanced static visual--spatial reasoning, yet they often fail to preserve long-horizon spatial coherence in embodied settings where beliefs must be continuously revised from egocentric…

Visual Spatial Reasoning is crucial for enabling Multimodal Large Language Models (MLLMs) to understand object properties and spatial relationships, yet current models still struggle with 3D-aware reasoning. Existing approaches typically…

Despite the ubiquity of large language models (LLMs) in AI research, the question of embodiment in LLMs remains underexplored, distinguishing them from embodied systems in robotics where sensory perception directly informs physical action.…

Spatial visualization is the mental ability to imagine, transform, and manipulate the spatial characteristics of objects and actions. This intelligence is a part of human cognition where actions and perception are connected on a mental…

Large Language Models (LLMs) solely trained on next-token prediction learn to solve a wide range of problems involving mathematical reasoning. But how does this ability evolve during training? We show the first analysis of how mathematical…

Spatial reasoning is a cornerstone capability for intelligent systems to perceive and interact with the physical world. However, multimodal large language models (MLLMs) frequently suffer from hallucinations and imprecision when parsing…