Related papers: Spatiotemporal Sycophancy: Negation-Based Gaslight…
Although Video Large Language Models perform remarkably well across tasks such as video understanding, question answering, and reasoning, they still suffer from the problem of hallucination, which refers to generating outputs that are…
Vision-language models (VLMs) have advanced rapidly, but their ability to capture spatial relationships remains a blindspot. Current VLMs are typically built with contrastive language-image pretraining (CLIP) style image encoders. The…
Existing video understanding benchmarks often conflate knowledge-based and purely image-based questions, rather than clearly isolating a model's temporal reasoning ability, which is the key aspect that distinguishes video understanding from…
Recently, researchers have attempted to investigate the capability of LLMs in handling videos and proposed several video LLM models. However, the ability of LLMs to handle video grounding (VG), which is an important time-related video task…
Large Language Models (LLMs) are expected to provide helpful and harmless responses, yet they often exhibit sycophancy--conforming to user beliefs regardless of factual accuracy or ethical soundness. Prior research on sycophancy has…
Existing video-language pre-training methods primarily focus on instance-level alignment between video clips and captions via global contrastive learning but neglect rich fine-grained local information in both videos and text, which is of…
Video Question Answering (VideoQA) aims to answer natural language questions based on the information observed in videos. Despite the recent success of Large Multimodal Models (LMMs) in image-language understanding and reasoning, they deal…
We study how Large Language Models (LLMs) process negation mechanistically. First, we establish that even though open-weight models often provide wrong answers to questions involving negation, they do possess internal components that…
Spatial Reasoning is an important component of human cognition and is an area in which the latest Vision-language models (VLMs) show signs of difficulty. The current analysis works use image captioning tasks and visual question answering.…
Explainable video anomaly detection (VAD) is crucial for safety-critical applications, yet even with recent progress, much of the research still lacks spatial grounding, making the explanations unverifiable. This limitation is especially…
Large language models (LLMs) often generate self-contradictory outputs, which severely impacts their reliability and hinders their adoption in practical applications. In video-language models (Video-LLMs), this phenomenon recently draws the…
Video-language alignment is a crucial multi-modal task that benefits various downstream applications, e.g., video-text retrieval and video question answering. Existing methods either utilize multi-modal information in video-text pairs or…
Large Vision-Language Models (LVLMs) have shown promising performance in vision-language understanding and reasoning tasks. However, their visual understanding behaviors remain underexplored. A fundamental question arises: to what extent do…
Multimodal learning can benefit from the representation power of pretrained Large Language Models (LLMs). However, state-of-the-art transformer based LLMs often ignore negations in natural language and there is no existing benchmark to…
Spatial Reasoning is an important component of human cognition and is an area in which the latest Vision-language models (VLMs) show signs of difficulty. The current analysis works use image captioning tasks and visual question answering.…
Hallucination is a long-standing problem that has been actively investigated in Vision-Language Models (VLMs). Existing research commonly attributes hallucinations to technical limitations or sycophancy bias, where the latter means the…
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and textual representations is not fully…
The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus predominantly on coarse-grained tasks such as action segmentation, classification,…
Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary…
When an omnimodal large language model accepts a question whose textual premise contradicts what it actually sees or hears, does the failure lie in perception or in action? Recent omnimodal models are positioned as perception-grounded…