Related papers: CamReasoner: Reinforcing Camera Movement Understan…
Camera-controllable video generation aims to synthesize videos with flexible and physically plausible camera movements. However, existing methods either provide imprecise camera control from text prompts or rely on labor-intensive manual…
Motion understanding is fundamental to physical reasoning, enabling models to infer dynamics and predict future states. However, state-of-the-art models still struggle on recent motion benchmarks, primarily due to the scarcity of…
Video spatial reasoning, which involves inferring the underlying spatial structure from observed video frames, poses a significant challenge for existing Multimodal Large Language Models (MLLMs). This limitation stems primarily from 1) the…
Large vision-language models have achieved remarkable progress in visual reasoning, yet most existing systems rely on single-step or text-only reasoning, limiting their ability to iteratively refine understanding across multiple visual…
Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) visual inputs consume large context budgets, forcing fewer…
Understanding text-rich videos requires reading small, transient textual cues that often demand repeated inspection. Yet most video QA models rely on single-pass perception over fixed frames, leading to hallucinations and failures on…
Large Multimodal Models (LMMs) have recently demonstrated remarkable visual understanding performance on both vision-language and vision-centric tasks. However, they often fall short in integrating advanced, task-specific capabilities for…
Large vision-language models exhibit inherent capabilities to handle diverse visual perception tasks. In this paper, we introduce VisionReasoner, a unified framework capable of reasoning and solving multiple visual perception tasks within a…
In this paper, we introduce Motion-Grounded Video Reasoning, a new motion understanding task that requires generating visual answers (video segmentation masks) according to the input question, and hence needs implicit spatiotemporal…
Multi-image spatial reasoning remains challenging for current multimodal large language models (MLLMs). While single-view perception is inherently 2D, reasoning over multiple views requires building a coherent scene understanding across…
Egocentric video understanding is inherently complex due to the dynamic 4D nature of the environment, where camera motion and object displacements necessitate a continuous re-evaluation of spatial relations. In this work, we target a suite…
We introduce CameraBench, a large-scale dataset and benchmark designed to assess and improve camera motion understanding. CameraBench consists of ~3,000 diverse internet videos, annotated by experts through a rigorous multi-stage quality…
Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video frames. Yet this signal is largely absent from multimodal LLMs (MLLMs) for video…
The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs)…
Spatial reasoning remains a fundamental challenge for Vision-Language Models (VLMs), with current approaches struggling to achieve robust performance despite recent advances. We identify that this limitation stems from a critical gap:…
Recent advances in image reasoning methods, particularly "Thinking with Images", have demonstrated remarkable success in Multimodal Large Language Models (MLLMs); however, this dynamic reasoning paradigm has not yet been extended to video…
Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm…
Healthcare robotics requires robust multimodal perception and reasoning to ensure safety in dynamic clinical environments. Current Vision-Language Models (VLMs) demonstrate strong general-purpose capabilities but remain limited in temporal…
With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to…
Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either…