Related papers: Incremental View Maintenance with Triple Lock Fact…
Though visual and repeat navigation is a convenient solution for mobile robot self-navigation, achieving balance between efficiency and robustness in task environment still remains challenges. In this paper, we propose a novel visual and…
Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs)…
Materialized views (MVs), stored pre-computed results, are widely used to facilitate fast queries on large datasets. When new records arrive at a high rate, it is infeasible to continuously update (maintain) MVs and a common solution is to…
Recent progress has shown great potential of visual prompt tuning (VPT) when adapting pre-trained vision transformers to various downstream tasks. However, most existing solutions independently optimize prompts at each layer, thereby…
Recent developments in prompt learning of large Vision-Language Models (VLMs) have significantly improved performance in target-specific tasks. However, these prompting methods often struggle to tackle the target-unspecific or generalizable…
Motivated by applications arising from sensor networks and machine learning, we consider the problem of minimizing a finite sum of nondifferentiable convex functions where each component function is associated with an agent and a…
Large Language Models (LLMs) have significantly impacted many facets of natural language processing and information retrieval. Unlike previous encoder-based approaches, the enlarged context window of these generative models allows for…
Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks. However, popular VLMs usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and…
Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…
Most large multimodal models (LMMs) are implemented by feeding visual tokens as a sequence into the first layer of a large language model (LLM). The resulting architecture is simple but significantly increases computation and memory costs,…
Vision-Language Models (VLMs) demonstrate remarkable potential in robotic manipulation, yet challenges persist in executing complex fine manipulation tasks with high speed and precision. While excelling at high-level planning, existing VLM…
Vision foundation models can perform generalized object classification in zero-shot mode, and face/person recognition when they are fine-tuned. However, fine-tuned models suffer from catastrophic forgetting. We create models that perform…
Traditionally, DBMSs separate their storage layer from their indexing layer. While the storage layer physically materializes the database and provides low-level access methods to it, the indexing layer on top enables a faster locating of…
Large Multimodal Models (LMMs) have achieved significant success across various tasks. These models usually encode visual inputs into dense token sequences, which are then concatenated with textual tokens and jointly processed by a language…
Vision Transformers implement multi-head self-attention via stacking multiple attention blocks. The query, key, and value are often intertwined and generated within those blocks via a single, shared linear transformation. This paper…
Object Goal Navigation (ObjectNav) in temporally changing indoor environments is challenging because object relocation can invalidate historical scene knowledge. To address this issue, we propose a probabilistic planning framework that…
Vision-Language Models (VLMs) have achieved notable success in multimodal tasks but face practical limitations due to the quadratic complexity of decoder attention mechanisms and autoregressive generation. Existing methods like FASTV and…
Visual autoregressive models achieve remarkable generation quality through next-scale predictions across multi-scale token pyramids. However, the conventional method uses uniform scale downsampling to build these pyramids, leading to…
Robust Visual SLAM (vSLAM) is essential for autonomous systems operating in real-world environments, where challenges such as dynamic objects, low texture, and critically, varying illumination conditions often degrade performance. Existing…
LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the…