Related papers: C2-Evo: Co-Evolving Multimodal Data and Model for …

Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant potential in complex visual tasks through the integration of Chain-of-Thought (CoT) reasoning. However, in Video Question Answering, extended thinking…

The mathematical capabilities of Multi-modal Large Language Models (MLLMs) remain under-explored with three areas to be improved: visual encoding of math diagrams, diagram-language alignment, and chain-of-thought (CoT) reasoning. This draws…

Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themselves as judges, leading to high computational costs and…

Large-scale high-quality training data is important for improving the performance of models. After trained with data that has rationales (reasoning steps), models gain reasoning capability. However, the dataset with high-quality rationales…

Reasoning is a fundamental capability for solving complex multi-step problems, particularly in visual contexts where sequential step-wise understanding is essential. Existing approaches lack a comprehensive framework for evaluating visual…

Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to…

The proliferation of multimedia content necessitates the development of effective Multimedia Event Extraction (M2E2) systems. Though Large Vision-Language Models (LVLMs) have shown strong cross-modal capabilities, their utility in the M2E2…

The tool-using capability of large language models (LLMs) enables them to access up-to-date external information and handle complex tasks. Current approaches to enhancing this capability primarily rely on distilling advanced models by data…

Reinforcement Learning (RL) has demonstrated significant potential in enhancing the reasoning capabilities of large language models (LLMs). However, the success of RL for LLMs heavily relies on human-curated datasets and verifiable rewards,…

Reasoning segmentation is an emerging vision-language task that requires reasoning over intricate text queries to precisely segment objects. However, existing methods typically suffer from overthinking, generating verbose reasoning chains…

Fine-tuning large pre-trained language models with Evol-Instruct has achieved encouraging results across a wide range of tasks. However, designing effective evolving methods for instruction evolution requires substantial human expertise.…

Multimodal large language models (MLLMs) perform well on many vision-language tasks but often struggle with vision-centric problems that require fine-grained visual reasoning. Recent evidence suggests that this limitation arises not from…

Self-evolving has emerged as a key paradigm for improving foundational models such as Large Language Models (LLMs) and Vision Language Models (VLMs) with minimal human intervention. While recent approaches have demonstrated that LLM agents…

Previous research has revealed the potential of large language models (LLMs) to support cognitive reframing therapy; however, their focus was primarily on text-based methods, often overlooking the importance of non-verbal evidence crucial…

In recent years, rapid advances in Multimodal Large Language Models (MLLMs) have increasingly stimulated research on ancient Chinese scripts. As the evolution of written characters constitutes a fundamental pathway for understanding…

While chain-of-thought (CoT) distillation from advanced large language models (LLMs) has proven effective in general reasoning tasks, it struggles in scientific domains where even advanced models often produce incorrect or superficial…

In recent years, multimodal large language models (MLLMs) have achieved significant breakthroughs, enhancing understanding across text and vision. However, current MLLMs still face challenges in effectively integrating knowledge across…

Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly…

Self-consistency methods are the core technique for improving the reasoning reliability of multimodal large language models (MLLMs). By generating multiple reasoning results through repeated sampling and selecting the best answer via…

Large language models have demonstrated substantial advancements in reasoning capabilities. However, current Vision-Language Models (VLMs) often struggle to perform systematic and structured reasoning, especially when handling complex…