Related papers: STORM: Slot-based Task-aware Object-centric Repres…
Referring multi-object tracking (RMOT) is a task of associating all the objects in a video that semantically match with given textual queries or referring expressions. Existing RMOT approaches decompose object grounding and tracking into…
Vision-Language Model (VLM) is an important component to enable robust robot manipulation. Yet, using it to translate human instructions into an action-resolvable intermediate representation often needs a tradeoff between…
Many video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames. Existing methods built on large vision-language models (LVLMs) often address this challenge by externalizing reasoning through…
Object-centric slot attention is an emerging paradigm for unsupervised learning of structured, interpretable object-centric representations (slots). This enables effective reasoning about objects and events at a low computational cost and…
Recent advances in video-based multimodal large language models (Video-LLMs) have significantly improved video understanding by processing videos as sequences of image frames. However, many existing methods treat frames independently in the…
Predictive world models enable agents to model scene dynamics and reason about the consequences of their actions. Inspired by human perception, object-centric world models capture scene dynamics using object-level representations, which can…
Multimodal Large Language Models (MLLMs) have shown strong performance on Video Temporal Grounding (VTG). However, their coarse recognition capabilities are insufficient for fine-grained temporal understanding, making task-specific…
The de facto approach in video object-centric learning maintains temporal consistency through learned dynamics modules that predict future object representations, called slots. We demonstrate that these predictors function as expensive…
Object SLAM is considered increasingly significant for robot high-level perception and decision-making. Existing studies fall short in terms of data association, object representation, and semantic mapping and frequently rely on additional…
Understanding dynamics from visual observations is a challenging problem that requires disentangling individual objects from the scene and learning their interactions. While recent object-centric models can successfully decompose a scene…
The choice of representation plays a key role in self-driving. Bird's eye view (BEV) representations have shown remarkable performance in recent years. In this paper, we propose to learn object-centric representations in BEV to distill a…
Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose a method where general purpose pretrained visual models serve as…
A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based…
Humans can discern scene-independent features of objects across various environments, allowing them to swiftly identify objects amidst changing factors such as lighting, perspective, size, and position and imagine the complete images of the…
Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely…
Agents with the ability to comprehend and reason about the dynamics of objects would be expected to exhibit improved robustness and generalization in novel scenarios. However, achieving this capability necessitates not only an effective…
World Action Models (WAMs) enhance Vision-Language-Action policies by jointly predicting scene evolution and robot actions, but existing methods usually represent the predicted world as holistic images, video tokens, or global latents.…
Learning object-level, structured representations is widely regarded as a key to better generalization in vision and underpins the design of next-generation Pre-trained Vision Models (PVMs). Mainstream Object-Centric Learning (OCL) methods…
Large-scale robot learning has made progress on complex manipulation tasks, yet long horizon, contact rich problems, especially those involving deformable objects, remain challenging due to inconsistent demonstration quality. We propose a…
Learning object-centric representations from complex natural environments enables both humans and machines with reasoning abilities from low-level perceptual features. To capture compositional entities of the scene, we proposed cyclic walks…