Related papers: Learning to Reason Iteratively and Parallelly for …
Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.…
Collaborative reasoning for understanding image-question pairs is a very critical but underexplored topic in interpretable visual question answering systems. Although very recent studies have attempted to use explicit compositional…
Video Question Answering (VideoQA) demands models that jointly reason over spatial, temporal, and linguistic cues. However, the task's inherent complexity often requires multi-step reasoning that current large multimodal models (LMMs)…
Enabling bi-directional retrieval of images and texts is important for understanding the correspondence between vision and language. Existing methods leverage the attention mechanism to explore such correspondence in a fine-grained manner.…
Recent large reasoning models (LRMs) have made substantial progress in complex reasoning tasks, yet they often generate lengthy reasoning paths for every query, incurring unnecessary computation and latency. Existing speed-up approaches…
Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on…
Medical vision-language models (VLMs) excel at image-text understanding but typically rely on a single-pass reasoning that neglects localized visual cues. In clinical practice, however, human experts iteratively scan, focus, and refine the…
Despite significant advancements, Large Vision-Language Models (LVLMs) continue to face challenges in complex visual reasoning tasks that demand deep contextual understanding, multi-angle analysis, or meticulous detail recognition. Existing…
Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…
Autonomous driving requires generating safe and reliable trajectories from complex multimodal inputs. Traditional modular pipelines separate perception, prediction, and planning, while recent end-to-end (E2E) systems learn them jointly.…
Despite recent successes, test-time scaling - i.e., dynamically expanding the token budget during inference as needed - remains brittle for vision-language models (VLMs): unstructured chains-of-thought about images entangle perception and…
Reasoning is increasingly crucial for various tasks. While chain-of-thought prompting enables large language models to leverage reasoning effectively, harnessing the reasoning capabilities of Vision-Language Models (VLMs) remains…
Interleaved reasoning paradigms enhance Multimodal Large Language Models (MLLMs) with visual feedback but are hindered by the prohibitive computational cost of re-encoding pixel-dense images. A promising alternative, latent visual…
Visual Commonsense Reasoning (VCR), deemed as one challenging extension of the Visual Question Answering (VQA), endeavors to pursue a more high-level visual comprehension. It is composed of two indispensable processes: question answering…
Recent advances in Vision-Language Models (VLMs) have demonstrated impressive capabilities in perception and reasoning. However, the ability to perform causal inference -- a core aspect of human cognition -- remains underexplored,…
Visual Programming (VP) has emerged as a powerful framework for Visual Question Answering (VQA). By generating and executing bespoke code for each question, these methods demonstrate impressive compositional and reasoning capabilities,…
Answering complex visual questions like `Which red furniture can be used for sitting?' requires multi-step reasoning, including object recognition, attribute filtering, and relational understanding. Recent work improves interpretability in…
Visual reasoning is a special visual question answering problem that is multi-step and compositional by nature, and also requires intensive text-vision interactions. We propose CMM: Cascaded Mutual Modulation as a novel end-to-end visual…
Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they remain limited in long-horizon multimodal scenarios, often suffering from visual…
Complex Visual Question Answering (Complex VQA) tasks, which demand sophisticated multi-modal reasoning and external knowledge integration, present significant challenges for existing large vision-language models (LVLMs) often limited by…