Related papers: Demo or Practice: Critical Analysis of the Languag…

We introduce \textbf{LaMP}, a dual-expert Vision-Language-Action framework that embeds dense 3D scene flow as a latent motion prior for robotic manipulation. Existing VLA models regress actions directly from 2D semantic visual features,…

Procedure planning requires a model to predict a sequence of actions that transform a start visual observation into a goal in instructional videos. While most existing methods rely primarily on visual observations as input, they often…

We study the identifiability of latent action policy learning (LAPO), a framework introduced recently to discover representations of actions from video data. We formally describe desiderata for such representations, their statistical…

Generalist Vision-Language-Action models are currently hindered by the scarcity of robotic data compared to the abundance of human video demonstrations. Existing Latent Action Models attempt to leverage video data but often suffer from…

Recently, latent action learning, pioneered by Latent Action Policies (LAPO), have shown remarkable pre-training efficiency on observation-only data, offering potential for leveraging vast amounts of video available on the web for embodied…

Idiomatic and figurative language form a large portion of colloquial speech and writing. With social media, this informal language has become more easily observable to people and trainers of large language models (LLMs) alike. While the…

Contrastive Language Audio Pretraining (CLAP) is a widely-used method to bridge the gap between audio and text domains. Current CLAP methods enable sound and music retrieval in English, ignoring multilingual spoken content. To address this,…

Interactive computational environments can help students explore algorithmic concepts through collaborative hands-on experimentation. However, static and instructor controlled demos in lectures limit engagement. Even when interactive…

Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for…

In this work, we want to give an overview on which pragmatic abilities have been tested in LLMs so far and how these tests have been carried out. To do this, we first discuss the scope of the field of pragmatics and suggest a subdivision…

Recent research has shown that hallucinations, omissions, and biases are prevalent in everyday use-cases of LLMs. However, chatbots used in medical contexts must provide consistent advice in situations where non-medical factors are…

Dialogue plays a crucial role in educational settings, yet existing evaluation methods for educational applications of large language models (LLMs) primarily focus on technical performance or learning outcomes, often neglecting attention to…

Vision-Language-Action (VLA) models achieve over 95% success on standard benchmarks. However, through systematic experiments, we find that current state-of-the-art VLA models largely ignore language instructions. Prior work lacks: (1)…

Large language models (LLMs) enabled dialogue systems have become one of the central modes in human-machine interaction, which bring about vast amounts of conversation logs and increasing demand for dialogue generation. The dialogue's…

Contrastive language-audio pretraining (CLAP) has recently emerged as a method for making audio analysis more generalisable. Specifically, CLAP-style models are able to `answer' a diverse set of language queries, extending the capabilities…

Language agents have shown impressive problem-solving skills within defined settings and brief timelines. Yet, with the ever-evolving complexities of open-world simulations, there's a pressing need for agents that can flexibly adapt to…

Automated Theorem Proving (ATP) in formal languages is a foundational challenge for AI. While Large Language Models (LLMs) have driven remarkable progress, a significant gap remains between their powerful informal reasoning capabilities and…

In-context learning (ICL) is a critical emerging capability of large language models (LLMs), enabling few-shot learning during inference by including a few demonstrations (demos) in the prompt. However, it has been found that ICL's…

Evaluation of large language models (LLMs) has raised great concerns in the community due to the issue of data contamination. Existing work designed evaluation protocols using well-defined algorithms for specific tasks, which cannot be…

Software vulnerability detection is generally supported by automated static analysis tools, which have recently been reinforced by deep learning (DL) models. However, despite the superior performance of DL-based approaches over rule-based…