Related papers: ProFocus: Proactive Perception and Focused Reasoni…
Recent advances in Vision-and-Language Navigation in Continuous Environments (VLN-CE) have leveraged multimodal large language models (MLLMs) to achieve zero-shot navigation. However, existing methods often rely on panoramic observations…
Visual perception in modern Vision-Language Models (VLMs) is constrained by a perceptual bandwidth bottleneck: a broad field of view preserves global context but sacrifices the fine-grained details required for complex reasoning. We argue…
Existing vision-and-language navigation (VLN) models primarily reason over past and current visual observations, while largely ignoring the future visual dynamics induced by actions. As a result, they often lack an effective understanding…
Vision-and-language navigation (VLN) is a trending topic which aims to navigate an intelligent agent to an expected position through natural language instructions. This work addresses the task of VLN from a previously-ignored aspect, namely…
Vision-and-Language Navigation (VLN) requires agents to follow natural language instructions through environments, with memory-persistent variants demanding progressive improvement through accumulated experience. Existing approaches for…
Vision-Language Navigation (VLN) requires an embodied agent to navigate complex environments by following natural language instructions, which typically demands tight fusion of visual and language modalities. Existing VLN methods often…
Spatial reasoning from monocular images is essential for autonomous driving, yet current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception, particularly under large scale variation and ambiguous object…
Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-grounded dialogue, visual question answering, and scientific…
In Vision-and-Language Navigation (VLN), an embodied agent needs to reach a target destination with the only guidance of a natural language instruction. To explore the environment and progress towards the target location, the agent must…
In Vision-and-Language Navigation (VLN), an agent is required to plan a path to the target specified by the language instruction, using its visual observations. Consequently, prevailing VLN methods primarily focus on building powerful…
Capitalizing on the remarkable advancements in Large Language Models (LLMs), there is a burgeoning initiative to harness LLMs for instruction following robotic navigation. Such a trend underscores the potential of LLMs to generalize…
Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To…
Recent advances in vision-language navigation (VLN) were mainly attributed to emerging large language models (LLMs). These methods exhibited excellent generalization capabilities in instruction understanding and task reasoning. However,…
In this work we concentrate on the task of goal-oriented Vision-and-Language Navigation (VLN). Existing methods often make decisions based on historical information, overlooking the future implications and long-term outcomes of the actions.…
Vision-and-Language Navigation (VLN) requires agents to autonomously navigate complex environments via visual images and natural language instructions--remains highly challenging. Recent research on enhancing language-guided navigation…
Autonomous navigation guided by natural language instructions in embodied environments remains a challenge for vision-language navigation (VLN) agents. Although recent advancements in learning diverse and fine-grained visual environmental…
Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs)…
Pre-trained vision-language-action (VLA) models offer a promising foundation for generalist robot policies, but often produce brittle behaviors or unsafe failures when deployed zero-shot in out-of-distribution scenarios. We present…
Developing Vision-and-Language Navigation (VLN) agents typically assumes a \textit{train-once-deploy-once} strategy, which is unrealistic as deployed agents continually encounter novel environments. To address this, we propose the Continual…
Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real…