相关论文: VisIT-Bench: A Benchmark for Vision-Language Instr…

Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also…

Multi-model learning has attracted great attention in visual-text tasks. However, visual-tabular data, which plays a pivotal role in high-stakes domains like healthcare and industry, remains underexplored. In this paper, we introduce…

As Vision-Language Models (VLMs) advance, human-centered Assistive Technologies (ATs) for helping People with Visual Impairments (PVIs) are evolving into generalists, capable of performing multiple tasks simultaneously. However,…

Existing visual reasoning benchmarks predominantly rely on natural language prompts, evaluate narrow reasoning modalities, or depend on subjective scoring procedures such as LLM-as-judge. We introduce the TACIT Benchmark, a programmatic…

Understanding multi-image, multi-turn scenarios is a critical yet underexplored capability for Large Vision-Language Models (LVLMs). Existing benchmarks predominantly focus on static or horizontal comparisons -- e.g., spotting visual…

Visual-Interleaved Chain-of-Thought (VI-CoT) enables Multi-modal Large Language Models (MLLMs) to continually update their understanding and decision space based on step-wise intermediate visual states (IVS), much like a human would, which…

Video language continual learning involves continuously adapting to information from video and text inputs, enhancing a model's ability to handle new tasks while retaining prior knowledge. This field is a relatively under-explored area, and…

Large Vision-Language Models (LVLMs) have made significant strides in the field of video understanding in recent times. Nevertheless, existing video benchmarks predominantly rely on text prompts for evaluation, which often require complex…

Multimodal large language models (MLLMs) have enabled a wide range of advanced vision-language applications, including fine-grained object recognition and contextual understanding. When querying specific regions or objects in an image,…

Recent generative models have achieved remarkable progress in image editing. However, existing systems and benchmarks remain largely text-guided. In contrast, human communication is inherently multimodal, where visual instructions such as…

Video-based large language models (Video-LLMs) have been recently introduced, targeting both fundamental improvements in perception and comprehension, and a diverse range of user inquiries. In pursuit of the ultimate goal of achieving…

Vision-language models (VLMs) have demonstrated remarkable progress in multimodal reasoning. However, existing benchmarks remain limited in terms of high-quality, human-verified examples. Many current datasets rely on synthetically…

Despite progress in video large language models (Video-LLMs), research on instructional video understanding, crucial for enhancing access to instructional content, remains insufficient. To address this, we introduce InstructionBench, an…

Thanks to the emerging of foundation models, the large language and vision models are integrated to acquire the multimodal ability of visual captioning, question answering, etc. Although existing multimodal models present impressive…

Visual Instruction Tuning (VisIT) data, commonly available as human-assistant conversations with images interleaved in the human turns, are currently the most widespread vehicle for aligning strong LLMs to understand visual inputs,…

The ability to perform complex tasks from detailed instructions is a key to many remarkable achievements of our species. As humans, we are not only capable of performing a wide variety of tasks but also very complex ones that may entail…

Existing evaluation frameworks for Multimodal Large Language Models (MLLMs) primarily focus on image reasoning or general video understanding tasks, largely overlooking the significant role of image context in video comprehension. To bridge…

The rapid advancement of Multimodal Large Language Models (MLLMs) has enabled browsing agents to acquire and reason over multimodal information in the real world. But existing benchmarks suffer from two limitations: insufficient evaluation…

Modern translation workflows demand more than semantic equivalence. Users routinely require models to preserve JSON or HTML schemas, honor curated glossaries, disambiguate with provided context, and match prescribed registers, often several…

Despite the critical need to align search targets with users' intention, retrievers often only prioritize query information without delving into the users' intended search context. Enhancing the capability of retrievers to understand…