Related papers: Grounded 3D-LLM with Referent Tokens

Recent progress in large language models (LLMs) has demonstrated the ability to learn and leverage Internet-scale knowledge through pre-training with autoregressive models. Unfortunately, applying such models to settings with embodied…

We introduce the novel task of Language-Guided Object Placement in Real 3D Scenes. Our model is given a 3D scene's point cloud, a 3D asset, and a textual prompt broadly describing where the 3D asset should be placed. The task here is to…

Integrating the 3D world into large language models (3D-based LLMs) has been a promising research direction for 3D scene understanding. However, current 3D-based LLMs fall short in situated understanding due to two key limitations: 1)…

We introduce the task of 3D visual grounding in large-scale dynamic scenes based on natural linguistic descriptions and online captured multi-modal visual data, including 2D images and 3D LiDAR point clouds. We present a novel method,…

Conversational modeling using Large Language Models (LLMs) requires a nuanced understanding of context to generate coherent and contextually relevant responses. In this paper, we present Token Trails, a novel approach that leverages…

Dynamic scenes contain intricate spatio-temporal information, crucial for mobile robots, UAVs, and autonomous driving systems to make informed decisions. Parsing these scenes into semantic triplets <Subject-Predicate-Object> for accurate…

Guiding users through complex procedural plans is an inherently multimodal task in which having visually illustrated plan steps is crucial to deliver an effective plan guidance. However, existing works on plan-following language models…

In recent years, 2D Vision-Language Models (VLMs) have made significant strides in image-text understanding tasks. However, their performance in 3D spatial comprehension, which is critical for embodied intelligence, remains limited. Recent…

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…

Next-token prediction is the fundamental principle for training large language models (LLMs), and reinforcement learning (RL) further enhances their reasoning performance. As an effective way to model language, image, video, and other…

Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks.…

In this paper, we present a novel, scalable approach for constructing open set, instance-level 3D scene representations, advancing open world understanding of 3D environments. Existing methods require pre-constructed 3D scenes and face…

The two popular datasets ScanRefer [16] and ReferIt3D [3] connect natural language to real-world 3D data. In this paper, we curate a large-scale and complementary dataset extending both the aforementioned ones by associating all objects…

Large language models (LLMs) excel at processing and generating both text and code. However, LLMs have had limited applicability in grounded task-oriented dialogue as they are difficult to steer toward task objectives and fail to handle…

Despite recent advances in multimodal content generation enabled by vision-language models (VLMs), their ability to reason about and generate structured 3D scenes remains largely underexplored. This limitation constrains their utility in…

Large Vision and Language Models (LVLMs) have shown strong performance across various vision-language tasks in natural image domains. However, their application to remote sensing (RS) remains underexplored due to significant domain…

Large vision-language models (VLMs) have shown promising capabilities in scene understanding, enhancing the explainability of driving behaviors and interactivity with users. Existing methods primarily fine-tune VLMs on on-board multi-view…

In the pursuit of efficient automated content creation, procedural generation, leveraging modifiable parameters and rule-based systems, emerges as a promising approach. Nonetheless, it could be a demanding endeavor, given its intricate…

Current 3D visual grounding tasks only process sentence level detection or segmentation, which critically fails to leverage the rich compositional contextual reasonings within natural language expressions. To address this challenge, we…

Human motion generation has advanced rapidly in recent years, yet the critical problem of creating spatially grounded, context-aware gestures has been largely overlooked. Existing models typically specialize either in descriptive motion…