Related papers: GeoStack: A Framework for Quasi-Abelian Knowledge …

The recent advancements in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively. Building upon this capability, we propose to enable…

Large Language Models (LLMs) store and retrieve vast amounts of factual knowledge acquired during pre-training. Prior research has localized and identified mechanisms behind knowledge recall; however, it has only focused on English…

We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs). Traditionally, compositionality has been associated with algebraic operations on embeddings of words from a pre-existing vocabulary.…

Language-guided grasping has emerged as a promising paradigm for enabling robots to identify and manipulate target objects through natural language instructions, yet it remains highly challenging in cluttered or occluded scenes. Existing…

Generalizable robotic mobile manipulation in open-world environments poses significant challenges due to long horizons, complex goals, and partial observability. A promising approach to address these challenges involves planning with a…

Vision-language models (VLMs) often struggle with compositional reasoning due to insufficient high-quality image-text data. To tackle this challenge, we propose a novel block-based diffusion approach that automatically generates…

Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while neglecting out-of-domain generalization, which is essential under…

Applying AI foundation models directly to geospatial datasets remains challenging due to their limited ability to represent and reason with geographical entities, specifically vector-based geometries and natural language descriptions of…

Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Vision-Language Models (VLMs) by adding extra expert encoders,…

The paper demonstrate that simple adjustments of the fine-tuning recipes of multimodal large language models (MLLM) are sufficient to mitigate catastrophic forgetting. On visual question answering, we design a 2x2 experimental framework to…

Incremental multi-view clustering aims to achieve stable clustering results while addressing the stability-plasticity dilemma (SPD) in view-incremental scenarios. The core challenge is that the model must have enough plasticity to quickly…

The expansion of instruction-tuning data has enabled foundation language models to exhibit improved instruction adherence and superior performance across diverse downstream tasks. Semantically-rich 3D human motion is being progressively…

Vision-language models (VLMs) and generative world models are opening new opportunities for embodied navigation. VLMs are increasingly used as direct planners or trajectory predictors, while world models support look-ahead reasoning by…

We propose a new method for unsupervised generative continual learning through realignment of Variational Autoencoder's latent space. Deep generative models suffer from catastrophic forgetting in the same way as other neural structures.…

Cross-capability transfer is a key challenge in large language model (LLM) research, with applications in multi-task integration, model compression, and continual learning. Recent works like FuseLLM and FuseChat have demonstrated the…

Modern vision-language models (VLMs) develop patch embedding and convolution backbone within vector space, especially Euclidean ones, at the very founding. When expanding VLMs to a galaxy scale for understanding astronomical phenomena, the…

Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have made them powerful tools in embodied navigation, enabling agents to leverage commonsense and spatial reasoning for efficient exploration in…

Visual geo-localization for drones faces critical degradation under weather perturbations, \eg, rain and fog, where existing methods struggle with two inherent limitations: 1) Heavy reliance on limited weather categories that constrain…

A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propose a novel framework called ReCL to slow down forgetting in…

Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows and end-to-end action prediction, which makes them brittle…