Related papers: CWM: Contrastive World Models for Action Feasibili…

A natural approach for reinforcement learning is to predict future rewards by unrolling a neural network world model, and to backpropagate through the resulting computational graph to learn a policy. However, this method often becomes…

Humans perceive the world through multisensory integration, blending the information of different modalities to adapt their behavior. Contrastive learning offers an appealing solution for multimodal self-supervised learning. Indeed, by…

Large language model (LLM) agents trained using reinforcement learning has achieved superhuman performance in low-cost environments like games, mathematics, and coding. However, these successes have not translated to complex domains where…

Fine-grained action recognition is attracting increasing attention due to the emerging demand of specific action understanding in real-world applications, whereas the data of rare fine-grained categories is very limited. Therefore, we…

Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at training time and rely on additional high-quality data,…

Contrastive pretraining is well-known to improve downstream task performance and model generalisation, especially in limited label settings. However, it is sensitive to the choice of augmentation pipeline. Positive pairs should preserve…

Controlling the behavior of Large Language Models (LLMs) remains a significant challenge due to their inherent complexity and opacity. While techniques like fine-tuning can modify model behavior, they typically require extensive…

Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output. But well-known problems with CoT faithfulness severely limit what insights can be gained from this practice. In this…

Self-supervised sentence representation learning is the task of constructing an embedding space for sentences without relying on human annotation efforts. One straightforward approach is to finetune a pretrained language model (PLM) with a…

Recently, contrastive learning has been shown to be effective in improving pre-trained language models (PLM) to derive high-quality sentence representations. It aims to pull close positive examples to enhance the alignment while push apart…

World Action Models (WAMs) have emerged as a promising alternative to Vision-Language-Action (VLA) models for embodied control because they explicitly model how visual observations may evolve under action. Most existing WAMs follow an…

Large language models (LLMs) have shown promising potential in scientific research, enabling tasks ranging from knowledge retrieval to property prediction. Existing science benchmarks mainly focus on perceptual or knowledge-based tasks,…

Visual Language Navigation (VLN) is a fundamental task within the field of Embodied AI, focusing on the ability of agents to navigate complex environments based on natural language instructions. Despite the progress made by existing…

Recent research has devoted considerable effort to verifying the intermediate reasoning steps of chain-of-thought (CoT) trajectories using process reward models (PRMs) and other verifier models. However, training a PRM typically requires…

A major challenge in deploying world models is the trade-off between size and performance. Large world models can capture rich physical dynamics but require massive computing resources, making them impractical for edge devices. Small world…

In the same way that generative models today conduct most of their training in a self-supervised fashion, how can agentic models conduct their training in a self-supervised fashion, interactively exploring, learning, and preparing to…

Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual…

The rapid progress in embodied artificial intelligence has highlighted the necessity for more advanced and integrated models that can perceive, interpret, and predict environmental dynamics. In this context, World Models (WMs) have been…

World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches face two critical bottlenecks that hinder performance and…

Recent advancements in machine learning (ML), natural language processing (NLP), and foundational models have shown promise for real-life applications in critical, albeit compute-constrainted fields like healthcare. In such areas, combining…