相关论文: SCRAMBLe : Enhancing Multimodal LLM Compositionali…

While large language models (LLMs) demonstrate strong reasoning capabilities utilizing reinforcement learning (RL) with verifiable reward, whether large vision-language models (VLMs) can directly inherit such capabilities through similar…

Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on a large and diverse…

Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthetic images improves many perception tasks, such as image…

LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks. Our research embarks on a quest to uncover the root causes of compositional reasoning failures of LLMs, uncovering that most of them stem…

Cognitive assessments require normative data as essential benchmarks for evaluating individual performance. Hence, developing new cognitive tests based on novel image stimuli is challenging due to the lack of readily available normative…

Embodied intelligence, a grand challenge in artificial intelligence, is fundamentally constrained by the limited spatial understanding and reasoning capabilities of current models. Prevailing efforts to address this through enhancing…

Intrinsic image decomposition aims to separate images into physical components such as albedo, depth, normals, and illumination. While recent diffusion- and transformer-based models benefit from paired supervision from synthetic datasets,…

Small language models (SLMs) are more efficient, cost-effective, and customizable than large language models (LLMs), though they often underperform in specific areas like reasoning. Past methods for enhancing SLMs' reasoning, such as…

Evaluating Large Language Models (LLMs) on reasoning benchmarks demonstrates their ability to solve compositional questions. However, little is known of whether these models engage in genuine logical reasoning or simply rely on implicit…

This study investigates whether diagnostic prompting can improve Multimodal Large Language Model (MLLM) reliability for visual complexity assessment of Amazon Search Results Pages (SRP). We compare diagnostic prompting with standard gestalt…

Vision-language models (VLMs) excel at image-text retrieval yet persistently fail at compositional reasoning, distinguishing captions that share the same words but differ in relational structure. We present, a unified evaluation and…

Multimodal Large Language Models (MLLMs) have been increasingly used as automatic evaluators-a paradigm known as MLLM-as-a-Judge. However, their reliability and vulnerabilities to biases remain underexplored. We find that many MLLM judges…

Multimodal Small-to-Medium sized Language Models (MSLMs) have demonstrated strong capabilities in integrating visual and textual information but still face significant limitations in visual comprehension and mathematical reasoning,…

Large Vision-Language Models (LVLMs) hold immense potential for complex multimodal instruction following, yet their development is often hindered by the high cost and inconsistency of human annotation required for effective fine-tuning and…

Large Language Models (LLMs) have advanced recommendation capabilities through enhanced reasoning, but pose significant challenges for real-world deployment due to high inference costs. Conversely, while Small Language Models (SLMs) offer…

Reasoning Vision-Language Models (VLMs) have shown promising performance on complex multimodal tasks. However, they still face significant challenges: they are highly sensitive to reasoning errors, require large volumes of annotated data or…

Video Large Language Models (Video LLMs) have achieved significant success by adopting the paradigm of large-scale pre-training followed by supervised fine-tuning (SFT). However, existing approaches struggle with temporal reasoning due to…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as…

Word sense plausibility rating requires predicting the human-perceived plausibility of a given word sense on a 1-5 scale in the context of short narrative stories containing ambiguous homonyms. This paper systematically compares three…

A fundamental characteristic common to both human vision and natural language is their compositional nature. Yet, despite the performance gains contributed by large vision and language pretraining, we find that: across 7 architectures…