Related papers: GRASP: Geospatial pixel Reasoning viA Structured P…
Spatial reasoning is central to navigation and robotics, yet measuring model capabilities on these tasks remains difficult. Existing benchmarks evaluate models in a one-shot setting, requiring full solution generation in a single response,…
Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the…
Spatial reasoning -- the ability to perceive and reason about relationships in space -- advances vision-language models (VLMs) from visual perception toward spatial semantic understanding. Existing approaches either revisit local image…
Large language models (LLMs) are expensive to serve because model parameters, attention computation, and KV caches impose substantial memory and latency costs. We present GRASPrune, a structured pruning framework applied after pretraining…
Recent advances in reinforcement learning (RL) have delivered strong reasoning capabilities in natural image domains, yet their potential for Earth Observation (EO) remains largely unexplored. EO tasks introduce unique challenges, spanning…
Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision and language tasks. However, their ability to reason about spatial arrangements remains limited. In this work, we introduce Spatial Region GPT (SpatialRGPT)…
Reinforcement learning with verifiable rewards has emerged as a promising paradigm for enhancing the reasoning capabilities of large language models particularly in mathematics. Current approaches in this domain present a clear trade-off:…
Grasp detection in cluttered scenes is a very challenging task for robots. Generating synthetic grasping data is a popular way to train and test grasp methods, as is Dex-net and GraspNet; yet, these methods generate training grasps on 3D…
Full-parameter fine-tuning of large language models is constrained by substantial GPU memory requirements. Low-rank adaptation methods mitigate this challenge by updating only a subset of parameters. However, these approaches often limit…
We focus on the task of unknown object rearrangement, where a robot is supposed to re-configure the objects into a desired goal configuration specified by an RGB-D image. Recent works explore unknown object rearrangement systems by…
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…
Open-vocabulary semantic segmentation has become an important direction in remote sensing, as it enables recognition beyond predefined land-cover categories. However, existing methods mainly depend on passive visual-text matching and often…
Vision-centric hierarchical embodied models have demonstrated strong potential. However, existing methods lack spatial awareness capabilities, limiting their effectiveness in bridging visual plans to actionable control in complex…
Robotic grasping is a primitive skill for complex tasks and is fundamental to intelligence. For general 6-Dof grasping, most previous methods directly extract scene-level semantic or geometric information, while few of them consider the…
Graphical User Interface (GUI) grounding, the task of mapping natural language instructions to precise screen coordinates, is fundamental to autonomous GUI agents. While existing methods achieve strong performance through extensive…
Grasping has been a long-standing challenge in facilitating the final interface between a robot and the environment. As environments and tasks become complicated, the need to embed higher intelligence to infer from the surroundings and act…
Spatial cognition is essential for human intelligence, enabling problem-solving through visual simulations rather than solely relying on verbal reasoning. However, existing AI benchmarks primarily assess verbal reasoning, neglecting the…
Group Relative Policy Optimization (GRPO), which is widely adopted by R1-like reasoning models, has advanced mathematical reasoning. Nevertheless, GRPO faces challenges in reward sparsity, verbosity, and inadequate focus on problem…
Grasping is one of the most fundamental challenging capabilities in robotic manipulation, especially in unstructured, cluttered, and semantically diverse environments. Recent researches have increasingly explored language-guided…
Goal-conditioned robotic grasping in cluttered environments remains a challenging problem due to occlusions caused by surrounding objects, which prevent direct access to the target object. A promising solution to mitigate this issue is…