相关论文: CurveBench: A Benchmark for Exact Topological Reas…
Multimodal Large Language Models (MLLMs) excel at recognizing individual visual elements and reasoning over simple linear diagrams. However, when faced with complex topological structures involving branching paths, converging flows, and…
Recent advancements in Unified Multimodal Models (UMMs) have enabled remarkable image understanding and generation capabilities. However, while models like Gemini-2.5-Flash-Image show emerging abilities to reason over multiple related…
Steering or intervening on model representations at inference time to correct predictions is essential for AI interpretability and safety, yet existing evaluation protocols are limited to ambiguous language modeling tasks. To address this…
Tree-like structures such as retinal images are widely studied in computer-aided diagnosis systems for large-scale screening programs. Despite several segmentation and tracking methods proposed in the literature, there still exist several…
Humans have the ability to reason about geometric patterns in images and scenes from a young age. However, developing large multimodal models (LMMs) capable of similar reasoning remains a challenge, highlighting the need for robust…
Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored. Current assessment methods primarily rely on AI-annotated preference…
Mathematical reasoning is a hallmark of human intelligence, and whether large language models (LLMs) can meaningfully perform it remains a central question in artificial intelligence and cognitive science. As LLMs are increasingly…
Recent video multimodal large language models achieve impressive results across various benchmarks. However, current evaluations suffer from two critical limitations: (1) inflated scores can mask deficiencies in fine-grained visual…
Structural pruning has emerged as a promising approach for producing more efficient models. Nevertheless, the community suffers from a lack of standardized benchmarks and metrics, leaving the progress in this area not fully comprehended. To…
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…
We investigate to what extent Multimodal Large Language Models (MLLMs) can accurately identify the orientation of input images rotated 0{\deg}, 90{\deg}, 180{\deg}, and 270{\deg}. This task demands robust visual reasoning capabilities to…
We introduce Cube Bench, a Rubik's-cube benchmark for evaluating spatial and sequential reasoning in multimodal large language models (MLLMs). The benchmark decomposes performance into five skills: (i) reconstructing cube faces from images…
The advent of Unified Multimodal Models (UMMs) signals a paradigm shift in artificial intelligence, moving from passive perception to active, cross-modal generation. Despite their unprecedented ability to synthesize information, a critical…
Graph Retrieval Augmented Generation (GraphRAG) has garnered increasing recognition for its potential to enhance large language models (LLMs) by structurally organizing domain-specific corpora and facilitating complex reasoning. However,…
Cross-view correspondence is a fundamental capability for spatial understanding and embodied AI. However, it is still far from being realized in Vision-Language Models (VLMs), especially in achieving precise point-level correspondence,…
Text-to-Visualization (Text2VIS) enables users to create visualizations from natural language queries, making data insights more accessible. However, Text2VIS faces challenges in interpreting ambiguous queries, as users often express their…
We study technical image generation, where a model must synthesize information-dense, scientifically precise illustrations from detailed descriptions rather than merely produce visually plausible pictures. To quantify the progress, we…
As LLMs advance their reasoning capabilities about the physical world, the absence of rigorous benchmarks for evaluating their ability to generate scientifically valid physical models has become a critical gap. Computational mechanics,…
Recent progress in text-to-image (T2I) generation underscores the importance of reliable benchmarks in evaluating how accurately generated images reflect the semantics of their textual prompt. However, (1) existing benchmarks lack the…
Recent advances in multi-modal generative models have enabled significant progress in instruction-based image editing. However, while these models produce visually plausible outputs, their capacity for knowledge-based reasoning editing…