相关论文: Which Way Does Time Flow? A Psychophysics-Grounded…

With the rapid development of Multi-modal Large Language Models (MLLMs), a number of diagnostic benchmarks have recently emerged to evaluate the comprehension capabilities of these models. However, most benchmarks predominantly assess…

Accurate prediction of human behavior is crucial for AI systems to effectively support real-world applications, such as autonomous robots anticipating and assisting with human tasks. Real-world scenarios frequently present challenges such…

Visual Language Models (VLMs) have emerged as pivotal tools for robotic systems, enabling cross-task generalization, dynamic environmental interaction, and long-horizon planning through multimodal perception and semantic reasoning. However,…

Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation, prompting research efforts towards video LLMs to facilitate human-AI interaction at the video level. However, how to effectively…

Multimodal Large Language Models (MLLMs) have recently made rapid progress toward unified Omni models that integrate vision, language, and audio. However, existing environments largely focus on 2D or 3D visual context and vision-language…

Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…

Spatio-temporal reasoning is a remarkable capability of Vision Language Models (VLMs), but the underlying mechanisms of such abilities remain largely opaque. We postulate that visual/geometrical and textual representations of spatial…

Vision-Language Models (VLMs) have recently emerged as powerful tools, excelling in tasks that integrate visual and textual comprehension, such as image captioning, visual question answering, and image-text retrieval. However, existing…

While vision-language models (VLMs) excel at tasks involving single images or short videos, they still struggle with Long Video Question Answering (LVQA) due to its demand for complex multi-step temporal reasoning. Vanilla approaches, which…

Recent research on Vision Language Models (VLMs) suggests that they rely on inherent biases learned during training to respond to questions about visual properties of an image. These biases are exacerbated when VLMs are asked highly…

Medical vision-language models (VLMs) show strong performance on radiology tasks but often produce fluent yet weakly grounded conclusions due to over-reliance on a dominant modality. We introduce a context-aligned reasoning framework that…

Rapid development of large language models (LLMs) has significantly advanced multimodal large language models (LMMs), particularly in vision-language tasks. However, existing video-language models often overlook precise temporal…

We present VRBench, the first long narrative video benchmark crafted for evaluating large models' multi-step reasoning capabilities, addressing limitations in existing evaluations that overlook temporal reasoning and procedural validity. It…

We introduce TemporalVLM, a video large language model (video LLM) for temporal reasoning and fine-grained understanding in long videos. Our approach includes a visual encoder for mapping a long-term video into features which are time-aware…

With the success of large language models (LLMs), integrating the vision model into LLMs to build vision-language foundation models has gained much more interest recently. However, existing LLM-based large multimodal models (e.g.,…

Adapting Multimodal Large Language Models (MLLMs) for hour-long videos is bottlenecked by context limits. Dense visual streams saturate token budgets and exacerbate the lost-in-the-middle phenomenon. Existing heuristics, like sparse…

Accurately predicting human behaviors is crucial for mobile robots operating in human-populated environments. While prior research primarily focuses on predicting actions in single-human scenarios from an egocentric view, several robotic…

Recent work has shown that eliciting Large Language Models (LLMs) to generate reasoning traces in natural language before answering the user's request can significantly improve their performance across tasks. This approach has been extended…

Human action recognition in long-term videos, characterized by complex backgrounds and subtle action differences, poses significant challenges for traditional deep learning models due to computational overhead, difficulty in capturing…

Test-time scaling (TTS) has emerged as a powerful paradigm for improving the reasoning ability of Large Language Models (LLMs) by allocating additional computation at inference, yet its application to multimodal systems such as…