EventBench: Towards Comprehensive Benchmarking of Event-based MLLMs

A new method for enhancing social interaction understanding in videos has been proposed, focusing on the alignment of verbal and non-verbal cues in multi-speaker scenarios. This approach addresses the limitations observed in existing Multimodal Large Language Models (MLLMs), which struggle with cross-modal attention consistency in such contexts.

A new dataset named VisReason has been introduced to enhance visual Chain-of-Thought (CoT) reasoning in multimodal large language models (MLLMs). Comprising 489,000 annotated examples across four domains, VisReason aims to facilitate complex reasoning by providing multi-round, human-like rationales that guide MLLMs through visual reasoning steps. Additionally, a subset called VisReason-Pro, featuring 165,000 examples, has been curated with expert-level annotations.

Recent advancements in artificial intelligence have led to the development of NeuroVFM, a generalist neuroimaging model trained on 5.24 million clinical MRI and CT volumes. This model was created through a novel approach called health system learning, which utilizes uncurated data from routine clinical care, addressing the limitations faced by existing AI models that lack access to private clinical data.

A new framework named EventSTU has been introduced to enhance the efficiency of video large language models (VLLMs) by employing event-guided spatio-temporal understanding. This approach utilizes a coarse-to-fine keyframe sampling algorithm and an adaptive token pruning algorithm to reduce redundant frames and optimize spatial data processing, respectively. Additionally, EventBench, a multimodal benchmark, has been created to evaluate this framework's performance in real-world scenarios.

A new framework called Chain-of-Visual-Thought (COVT) has been introduced to enhance Vision-Language Models (VLMs) by enabling them to reason with continuous visual tokens, which encapsulate rich perceptual cues. This approach aims to address the limitations of current VLMs in dense visual perception tasks, such as spatial reasoning and geometric awareness, by distilling knowledge from lightweight vision experts within a budget of approximately 20 tokens.

A recent study evaluated the mathematical reasoning capabilities of Large Language Models (LLMs) using the 2026 Korean College Scholastic Ability Test (CSAT) Mathematics section, ensuring a contamination-free evaluation environment. The research involved digitizing all 46 questions immediately after the exam's public release, allowing for a rigorous assessment of 24 state-of-the-art LLMs across various input modalities and languages.

A new framework called ReVeL (Rewrite and Verify by LLM) has been proposed to enhance the multiple-choice question answering (MCQA) format used in evaluating multimodal language models. This framework transforms MCQA into open-form questions while ensuring answers remain verifiable, addressing issues of answer guessing and unreliable accuracy metrics during reinforcement fine-tuning (RFT).

EvoLMM, a self-evolving framework for large multimodal models, has been introduced to enhance reasoning capabilities without relying on human-annotated data. This framework consists of two cooperative agents: a Proposer that generates diverse questions and a Solver that answers them through a continuous self-rewarding process. This innovation aims to improve the autonomy and scalability of multimodal models.