相关论文: PointArena: Probing Multimodal Grounding Through L…

Recent advances in multimodal large language models (MLLMs) have yielded increasingly powerful models, yet their perceptual capacities remain poorly characterized. In practice, most model families scale language component while reusing…

Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks. Recent advances in large language models (LLMs) have greatly enhanced their reasoning abilities in arithmetic, commonsense, and symbolic…

MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental…

Event cameras capture changes in brightness with microsecond precision and remain reliable under motion blur and challenging illumination, offering clear advantages for modeling highly dynamic scenes. Yet, their integration with natural…

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…

Large language models (LLMs) are now used worldwide, yet their multimodal understanding and reasoning often degrade outside Western, high-resource settings. We propose MMA-ASIA, a comprehensive framework to evaluate LLMs' cultural awareness…

Recent large language models (LLMs) have shown strong reasoning capabilities. However, a critical question remains: do these models possess genuine strategic reasoning, or do they primarily excel at pattern recognition? To address this, we…

Multimodal Large Language Models (MLLMs) have emerged as powerful tools for chart comprehension. However, they heavily rely on extracted content via OCR, which leads to numerical hallucinations when chart textual annotations are sparse.…

Multimodal Large Language models (MLLMs) have shown promise in web-related tasks, but evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks. Existing benchmarks are either designed…

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…

Interactive articulated manipulation requires long-horizon, multi-step interactions with appliances while maintaining physical consistency. Existing vision-language and diffusion-based policies struggle to generalize across parts,…

As AI systems progress, we rely more on them to make decisions with us and for us. To ensure that such decisions are aligned with human values, it is imperative for us to understand not only what decisions they make but also how they come…

Understanding human emotions from multimodal signals poses a significant challenge in affective computing and human-robot interaction. While multimodal large language models (MLLMs) have excelled in general vision-language tasks, their…

Single-turn benchmarks such as AnimalHarmBench (AHB) have established important baselines for measuring animal welfare alignment in large language models (LLMs), but they miss a critical failure mode: models that respond appropriately when…

We open-source MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models delivering state-of-the-art performance in both general visual understanding and multimodal reasoning. MiMo-VL-7B-RL outperforms Qwen2.5-VL-7B on 35 out of…

Pointing-based methods decompose complex tasks as sequential grounding and reasoning steps. Given a query, the model first grounds the relevant objects by generating their coordinates, and then predicts an answer conditioned on these…

We propose a new spatial memory module and a spatial reasoner for the Visual Grounding (VG) task. The goal of this task is to find a certain object in an image based on a given textual query. Our work focuses on integrating the regions of a…

The ability for robots to comprehend and execute manipulation tasks based on natural language instructions is a long-term goal in robotics. The dominant approaches for language-guided manipulation use 2D image representations, which face…

The ability to process information from multiple modalities and to reason through it step-by-step remains a critical challenge in advancing artificial intelligence. However, existing reasoning benchmarks focus on text-only reasoning, or…

While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks…