Related papers: ASCIIBench: Evaluating Language-Model-Based Unders…

Multimodal Large Language Models (MLLMs) have demonstrated significant capabilities in joint visual and linguistic tasks. However, existing Visual Question Answering (VQA) benchmarks often fail to evaluate deep semantic understanding,…

Recent video generative models have greatly improved the realism of AI-generated videos, yet their outputs still exhibit artifacts such as temporal inconsistencies, structural distortions, and semantic incoherence. While Multimodal Large…

Existing vision-language understanding benchmarks largely consist of images of objects in their usual contexts. As a consequence, recent multimodal large language models can perform well with only a shallow visual understanding by relying…

Benchmarks are the de facto standard for tracking progress in large language models (LLMs), yet static test sets can rapidly saturate, become vulnerable to contamination, and are costly to refresh. Scalable evaluation of open-ended items…

Color plays an important role in human perception and usually provides critical clues in visual reasoning. However, it is unclear whether and how vision-language models (VLMs) can perceive, understand, and leverage color as humans. This…

Recent years have seen rapid advances in AI-driven image generation. Early diffusion models emphasized perceptual quality, while newer multimodal models like GPT-4o-image integrate high-level reasoning, improving semantic understanding and…

The evolution of Large Language Models (LLMs) into autonomous agents has expanded the scope of AI coding from localized code generation to complex, repository-level, and execution-driven problem solving. However, current benchmarks…

Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants. However, the effective evaluation of alignment for emerging Chinese LLMs is still largely unexplored. To fill in this gap,…

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…

The emergence of Large Vision-Language Models (LVLMs) marks significant strides towards achieving general artificial intelligence. However, these advancements are accompanied by concerns about biased outputs, a challenge that has yet to be…

Safety is critical to the usage of large language models (LLMs). Multiple techniques such as data filtering and supervised fine-tuning have been developed to strengthen LLM safety. However, currently known techniques presume that corpora…

Multimodal large language models (MLLMs) have achieved remarkable progress on vision-language tasks, yet their reasoning processes remain sometimes unreliable. We introduce PRISM-Bench, a benchmark of puzzle-based visual challenges designed…

A challenge in advancing Visual-Language Models (VLMs) is determining whether their failures on abstract reasoning tasks, such as Bongard problems, stem from flawed perception or faulty top-down reasoning. To disentangle these factors, we…

Text-to-Image (T2I) generative models are becoming increasingly crucial due to their ability to generate high-quality images, but also raise concerns about social biases, particularly in human image generation. Sociological research has…

While recent advancements in multimodal language models have enabled image generation from expressive multi-image instructions, existing methods struggle to maintain performance under complex interleaved instructions. This limitation stems…

Over the past decade, analogies, in the form of word-level analogies, have played a significant role as an intrinsic measure of evaluating the quality of word embedding methods such as word2vec. Modern large language models (LLMs), however,…

Reading measurement instruments is effortless for humans and requires relatively little domain expertise, yet it remains surprisingly challenging for current vision-language models (VLMs) as we find in preliminary evaluation. In this work,…

Evaluating the performance of visual language models (VLMs) in graphic reasoning tasks has become an important research topic. However, VLMs still show obvious deficiencies in simulating human-level graphic reasoning capabilities,…

Visual embedding models excel at zero-shot tasks like visual retrieval and classification. However, these models cannot be used for tasks that contain ambiguity or require user instruction. These tasks necessitate an embedding model which…

Despite the remarkable advancements and widespread applications of deep neural networks, their ability to perform reasoning tasks remains limited, particularly in domains requiring structured, abstract thought. In this paper, we investigate…