Related papers: What if? Emulative Simulation with World Models fo…

What happens when a language model thinks without words? Standard reasoning LLMs verbalize intermediate steps as chain-of-thought; latent reasoning transformers (LRTs) instead perform deliberation entirely in continuous hidden space. We…

Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language models (MLLMs) remains largely untapped, hindered by the…

How to enable agents to predict the outcomes of their own motion intentions in three-dimensional space has been a fundamental problem in embodied intelligence. To explore general spatial imagination capability, we present AirScape, the…

Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typically rely on modular designs that decouple navigation planning from visual world modeling,…

The rapid advancing of Multimodal Large Language Models (MLLMs) has spurred interest in complex multimodal reasoning tasks in the real-world and virtual environment, which require coordinating multiple abilities, including visual…

Humans are able to accurately reason in 3D by gathering multi-view observations of the surrounding world. Inspired by this insight, we introduce a new large-scale benchmark for 3D multi-view visual question answering (3DMV-VQA). This…

Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…

Building on the success of text-based reasoning models like DeepSeek-R1, extending these capabilities to multimodal reasoning holds great promise. While recent works have attempted to adapt DeepSeek-R1-style reinforcement learning (RL)…

Recent multimodal large language models (MLLMs) achieve strong performance on visual reasoning benchmarks, yet it remains unclear to what extent such performance reflects reasoning directly grounded in visual evidence. We introduce…

The possible consequences for the same context may vary depending on the situation we refer to. However, current studies in natural language processing do not focus on situated commonsense reasoning under multiple possible scenarios. This…

Evaluating the reasoning abilities of large language models (LLMs) is challenging. Existing benchmarks often depend on static datasets, which are vulnerable to data contamination and may get saturated over time, or on binary live human…

Vision-Language Models (VLMs) have achieved remarkable progress across tasks such as visual question answering and image captioning. Yet, the extent to which these models perform visual reasoning as opposed to relying on linguistic priors…

As large language models (LLMs) continue to improve in reasoning and decision-making, there is a growing need for realistic and interactive environments where their abilities can be rigorously evaluated. We present VirtualEnv, a…

While large multimodal models (LMMs) have demonstrated strong performance across various Visual Question Answering (VQA) tasks, certain challenges require complex multi-step reasoning to reach accurate answers. One particularly challenging…

Real-world autonomous planning requires coordinating tightly coupled constraints where a single decision dictates the feasibility of all subsequent actions. However, existing benchmarks predominantly feature loosely coupled constraints…

Achieving human-like reasoning in deep learning models for complex tasks in unknown environments remains a critical challenge in embodied intelligence. While advanced vision-language models (VLMs) excel in static scene understanding, their…

In this paper, we argue that simulation platforms enable a novel type of embodied spatial reasoning, one facilitated by a formal model of object and event semantics that renders the continuous quantitative search space of an open-world,…

Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated experience across tasks. However, most existing LLM-based…

This paper presents MobQA, a benchmark dataset designed to evaluate the semantic understanding capabilities of large language models (LLMs) for human mobility data through natural language question answering. While existing models excel at…

Language model agents excel in long-session planning and reasoning, but existing benchmarks primarily focus on goal-oriented tasks with explicit objectives, neglecting creative adaptation in unfamiliar environments. To address this, we…