Related papers: GoalLadder: Incremental Goal Discovery with Vision…

Large language model alignment via reinforcement learning depends critically on reward function quality. However, static, domain-specific reward models are often costly to train and exhibit poor generalization in out-of-distribution…

Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper,…

Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imperfect rewards remains difficult due to inefficient exploration and poor credit…

Large language models (LLMs) have demonstrated high performance on tasks expressed in natural language, particularly in zero- or few-shot settings. These are typically framed as supervised (e.g., classification) or unsupervised (e.g.,…

Large Language Models (LLMs) and Reinforcement Learning (RL) are two powerful approaches for building autonomous agents. However, due to limited understanding of the game environment, agents often resort to inefficient exploration and…

Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investigate this, we introduce ViLP, a benchmark featuring…

Visual generation models have made remarkable progress in creating realistic images from text prompts, yet struggle with complex prompts that specify multiple objects with precise spatial relationships and attributes. Effective handling of…

Vision-language models (VLMs) have excelled in multimodal tasks, but adapting them to embodied decision-making in open-world environments presents challenges. One critical issue is bridging the gap between discrete entities in low-level…

Geo-localization from a single image at planet scale (essentially an advanced or extreme version of the kidnapped robot problem) is a fundamental and challenging task in applications such as navigation, autonomous driving and disaster…

Despite large-scale pretraining endowing models with language and vision reasoning capabilities, improving their spatial reasoning capability remains challenging due to the lack of data grounded in the 3D world. While it is possible for…

Recently, the remarkable success of ChatGPT has sparked a renewed wave of interest in artificial intelligence (AI), and the advancements in visual language models (VLMs) have pushed this enthusiasm to new heights. Differring from previous…

Training robust and generalizable reward models for human visual preferences is essential for aligning text-to-image and text-to-video generative models with human intent. However, current reward models often fail to generalize, and…

Recent works have shown that Large Language Models (LLMs) can be applied to ground natural language to a wide variety of robot skills. However, in practice, learning multi-task, language-conditioned robotic skills typically requires…

To explore a more scalable path for adding multimodal capabilities to existing LLMs, this paper addresses a fundamental question: Can a unimodal LLM, relying solely on text, reason about its own informational needs and provide effective…

Generative large language models (LLMs) exhibit impressive capabilities, which can be further augmented by integrating a pre-trained vision model into the original LLM to create a multimodal LLM (MLLM). However, this integration often…

The control of robots for manipulation tasks generally relies on visual input. Recent advances in vision-language models (VLMs) enable the use of natural language instructions to condition visual input and control robots in a wider range of…

This paper explores training medical vision-language models (VLMs) -- where the visual and language inputs are embedded into a common space -- with a particular focus on scenarios where training data is limited, as is often the case in…

Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. However, most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs,…

Large Language Models (LLMs) offer a promising basis for creating agents that can tackle complex tasks through iterative environmental interaction. Existing methods either require these agents to mimic expert-provided trajectories or rely…

Image scoring is a crucial task in numerous real-world applications. To trust a model's judgment, understanding its rationale is essential. This paper proposes a novel training method for Vision Language Models (VLMs) to generate not only…