Related papers: What MLLMs Learn about When they Learn about Multi…

Vision-Language Models (VLMs) have recently gained attention due to their competitive performance on multiple downstream tasks, achieved by following user-input instructions. However, VLMs still exhibit several limitations in visual…

While Large Multimodal Models (LMMs) have made significant progress, they remain largely text-centric, relying on language as their core reasoning modality. As a result, they are limited in their ability to handle reasoning tasks that are…

Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…

Multimodal large language models (MLLMs) are increasingly deployed in open-ended, real-world environments where inputs are messy, underspecified, and not always trustworthy. Unlike curated benchmarks, these settings frequently involve…

Multi-round incomplete information tasks are crucial for evaluating the lateral thinking capabilities of large language models (LLMs). Currently, research primarily relies on multiple benchmarks and automated evaluation metrics to assess…

While Large Language Models (LLMs) achieve strong performance across diverse tasks, their inference dynamics remain poorly understood because of the limited resolution of existing analysis tools. In this work, we identify an intrinsic…

Multimodal Large Language Models (MLLMs) have achieved remarkable success in open-vocabulary perceptual tasks, yet their ability to solve complex cognitive problems remains limited, especially when visual details are abstract and require…

Vision-language models (VLMs) are widely assumed to exhibit in-context learning (ICL), a property similar to that of their language-only counterparts. While recent work suggests VLMs can perform multimodal ICL (MM-ICL), studies show they…

Multimodal Large Language Models (MLLMs) already achieve state-of-the-art results across a wide range of tasks and modalities. To push their reasoning ability further, recent studies explore advanced prompting schemes and post-training…

Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instructions. To address this, we adopt a reinforcement learning…

Continuous latent-space reasoning offers a compact alternative to textual chain-of-thought for multimodal models, enabling high-dimensional visual evidence to be integrated without explicit reasoning tokens. However, we identify a…

Multimodal Large Language Models (MLLMs) have demonstrated strong performance across a wide range of vision-language tasks, yet their internal processing dynamics remain underexplored. In this work, we introduce a probing framework to…

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

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…

Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in…

For human cognitive process, spatial reasoning and perception are closely entangled, yet the nature of this interplay remains underexplored in the evaluation of multimodal large language models (MLLMs). While recent MLLM advancements show…

Multimodal LLMs can accurately perceive numerical content across modalities yet fail to perform exact multi-digit multiplication when the identical underlying arithmetic problem is presented as numerals, number words, images, or in audio…

Understanding perspective is fundamental to human visual perception, yet the extent to which multimodal large language models (MLLMs) internalize perspective geometry remains unclear. We introduce MMPerspective, the first benchmark…

While multimodal LLMs (MLLMs) demonstrate remarkable reasoning progress, their application in specialized scientific domains like physics reveals significant gaps in current evaluation benchmarks. Specifically, existing benchmarks often…

Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatial understanding and reasoning. However, their fine-grained spatial understanding and reasoning capabilities in complex urban scenarios have…