相关论文: EcoAlign: An Economically Rational Framework for E…

With the rapid advancement of Large Vision-Language Models (LVLMs), ensuring their safety has emerged as a crucial area of research. This survey provides a comprehensive analysis of LVLM safety, covering key aspects such as attacks,…

Large Language Models (LLMs) enable intelligent multi-robot collaboration but face fundamental trade-offs: open-loop methods that compile tasks into formal representations for external executors produce sound plans but lack adaptability in…

While generative robot policies have demonstrated significant potential in learning complex, multimodal behaviors from demonstrations, they still exhibit diverse failures at deployment-time. Policy steering offers an elegant solution to…

Aligning Vision-Language Models (VLMs) with safety standards is essential to mitigate risks arising from their multimodal complexity, where integrating vision and language unveils subtle threats beyond the reach of conventional safeguards.…

Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit textual or visual triggers to bypass safety guardrails. Recent…

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

Emerging embodied AI applications, such as wearable cameras and autonomous agents, have underscored the need for robust reasoning from first person video streams. We introduce EgoVLM, a vision-language model specifically designed to…

The recent advancements in text-to-image generative models have been remarkable. Yet, the field suffers from a lack of evaluation metrics that accurately reflect the performance of these models, particularly lacking fine-grained metrics…

Large foundation models have made significant advances in embodied intelligence, enabling synthesis and reasoning over egocentric input for household tasks. However, VLM-based auto-labeling is often noisy because the primary data sources…

Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness, particularly when processing queries exceeding their knowledge boundaries. While existing mitigation strategies employ uncertainty estimation…

Large language models (LLMs) are increasingly being used as decision aids. However, users have diverse values and preferences that can affect their decision-making, which requires novel methods for LLM alignment and personalization.…

Aerial Vision-and-Language Navigation (VLN) aims to enable unmanned aerial vehicles (UAVs) to interpret natural language instructions and navigate complex urban environments using onboard visual observation. This task holds promise for…

Medical vision-language models (VLMs) show strong performance on radiology tasks but often produce fluent yet weakly grounded conclusions due to over-reliance on a dominant modality. We introduce a context-aligned reasoning framework that…

Autonomous navigation guided by natural language instructions is essential for improving human-robot interaction and enabling complex operations in dynamic environments. While large language models (LLMs) are not inherently designed for…

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

As Large Language Models (LLMs) become more powerful and autonomous, they increasingly face conflicts and dilemmas in many scenarios. We first summarize and taxonomize these diverse conflicts. Then, we model the LLM's preferences to make…

Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where the LLMs' knowledge boundaries are ambiguous. To improve…

Efficient processing of high-resolution images is crucial for real-world vision-language applications. However, existing Large Vision-Language Models (LVLMs) incur substantial computational overhead due to the large number of vision tokens.…

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…

Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in solving complex tasks. However, their deliberative reasoning process leads…