Related papers: NarrativeTrack: Evaluating Entity-Centric Reasonin…

Multimodal large language models (MLLMs) are increasingly used for real-world tasks involving multi-step reasoning and long-form generation, where reliability requires grounding model outputs in heterogeneous input sources and verifying…

Contextual reasoning with constraints is crucial for enhancing temporal consistency in cross-frame modeling for visual tracking. However, mainstream tracking algorithms typically associate context by merely stacking historical information…

Narrative reasoning relies on the understanding of eventualities in story contexts, which requires a wealth of background world knowledge. To help machines leverage such knowledge, existing solutions can be categorized into two groups. Some…

Multimodal Large Language Models (MLLMs) have achieved significant advancements in tasks like Visual Question Answering (VQA) by leveraging foundational Large Language Models (LLMs). However, their abilities in specific areas such as visual…

A compelling portrayal of characters is essential to the success of narrative writing. For readers, appreciating a character's traits requires the ability to infer their evolving beliefs, desires, and intentions over the course of a complex…

Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. The existing benchmarks are…

With enhanced capabilities and widespread applications, Multimodal Large Language Models (MLLMs) are increasingly required to process and reason over multiple images simultaneously. However, existing MLLM benchmarks focus either on…

Artificial intelligence systems based on large language models (LLMs) can now generate coherent text, music, and images, yet they operate without a persistent state: each inference reconstructs context from scratch. This paper introduces…

How people narrate their experiences offers a window into how the mind organizes them. Computational approaches to therapeutic writing have evolved from lexical counting to neural methods, yet remain fragmented: dictionary tools miss…

Multimodal Large Language Models (MLLMs) have made rapid progress in single-video understanding, yet their ability to reason across multiple independent video streams remains poorly understood. Existing multi-video benchmarks rely largely…

The event-based Vision-Language Model (VLM) recently has made good progress for practical vision tasks. However, most of these works just utilize CLIP for focusing on traditional perception tasks, which obstruct model understanding…

Multimodal Large Language Models (MLLMs) have showcased exceptional Chain-of-Thought (CoT) reasoning ability in complex textual inference tasks including causal reasoning. However, will these causalities remain straightforward when crucial…

Understanding how humans and artificial intelligence systems process complex narrative videos is a fundamental challenge at the intersection of neuroscience and machine learning. This study investigates how the temporal context length of…

The recent advancement in video temporal grounding (VTG) has significantly enhanced fine-grained video understanding, primarily driven by multimodal large language models (MLLMs). With superior multimodal comprehension and reasoning…

Multimodal Large Language Models (MLLMs) strive to achieve a profound, human-like understanding of and interaction with the physical world, but often exhibit a shallow and incoherent integration when acquiring information (Perception) and…

Visual Language Models (VLMs) are powerful generative tools but often produce factually inaccurate outputs due to a lack of robust reasoning capabilities. While extensive research has been conducted on integrating external knowledge for…

Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically…

Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more, evolving from Chain-of-Thought prompting to product-level solutions like OpenAI o1. Despite various efforts to improve LLM reasoning,…

Existing research of video understanding still struggles to achieve in-depth comprehension and reasoning in complex videos, primarily due to the under-exploration of two key bottlenecks: fine-grained spatial-temporal perceptive…

Despite Large Language Models' remarkable capabilities, understanding their internal representations remains challenging. Mechanistic interpretability tools such as sparse autoencoders (SAEs) were developed to extract interpretable features…