Related papers: GeoZero: Incentivizing Reasoning from Scratch on G…

Large language models (LLMs) can solve problems step-by-step. While this chain-of-thought (CoT) reasoning boosts LLMs' performance, it is unclear if LLMs \textit{know} when to use CoT and whether those CoT are always necessary to answer the…

As the field of Multimodal Large Language Models (MLLMs) continues to evolve, their potential to revolutionize artificial intelligence is particularly promising, especially in addressing mathematical reasoning tasks. Current mathematical…

Large language models(LLMs), with their powerful language generation and reasoning capabilities, have already achieved notable success in many domains, e.g., math and code generation. However, they often fall short when tackling real-life…

Large language models (LLMs) exhibit strong reasoning abilities, often attributed to few-shot or zero-shot chain-of-thought (CoT) prompting. While effective, these methods require labor-intensive prompt engineering, raising the question of…

Geometric ability is a significant challenge for large language models (LLMs) due to the need for advanced spatial comprehension and abstract thinking. Existing datasets primarily evaluate LLMs on their final answers, but they cannot truly…

In recent years, video question answering based on multimodal large language models (MLLM) has garnered considerable attention, due to the benefits from the substantial advancements in LLMs. However, these models have a notable deficiency…

State-of-the-art large multi-modal models (LMMs) face challenges when processing high-resolution images, as these inputs are converted into enormous visual tokens, many of which are irrelevant to the downstream task. In this paper, we…

Geolocation is now a vital aspect of modern life, offering numerous benefits but also presenting serious privacy concerns. The advent of large vision-language models (LVLMs) with advanced image-processing capabilities introduces new risks,…

Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scale video datasets also ``think in space'' from videos? We…

Learning predictive world models is crucial for enhancing the planning capabilities of reinforcement learning (RL) agents. Recently, MuZero-style algorithms, leveraging the value equivalence principle and Monte Carlo Tree Search (MCTS),…

The ability to reason is one of the most fundamental capabilities of large language models (LLMs), enabling a wide range of downstream tasks through sophisticated problem-solving. A critical aspect of this is code reasoning, which involves…

Recently spatial-temporal intelligence of Visual-Language Models (VLMs) has attracted much attention due to its importance for autonomous driving, embodied AI and general AI. Existing spatial-temporal benchmarks mainly focus on egocentric…

Recent advances in vision-language models have opened up new possibilities for reasoning-driven image geolocalization. However, existing approaches often rely on synthetic reasoning annotations or external image retrieval, which can limit…

Humans build viewpoint-independent cognitive maps through navigation, enabling intuitive reasoning about object permanence and spatial relations. We argue that multimodal large language models (MLLMs), despite extensive video training, lack…

The emergence of multimodal large language models (MLLMs) has triggered extensive research in model evaluation. While existing evaluation studies primarily focus on unimodal (vision-only) comprehension and reasoning capabilities, they…

Segmentation based on language has been a popular topic in computer vision. While recent advances in multimodal large language models (MLLMs) have endowed segmentation systems with reasoning capabilities, these efforts remain confined by…

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…

The rapid progress of Multimodal Large Language Models (MLLMs) has unlocked the potential for enhanced 3D scene understanding and spatial reasoning. A recent line of work explores learning spatial reasoning directly from multi-view images,…

Vision-language models (VLMs) have shown a promising ability in image geolocation, but they still lack structured geographic reasoning and the capacity for autonomous self-evolution. Existing methods predominantly rely on implicit…

Reasoning lies at the heart of intelligence, shaping the ability to make decisions, draw conclusions, and generalize across domains. In artificial intelligence, as systems increasingly operate in open, uncertain, and multimodal…