相关论文: CurEvo: Curriculum-Guided Self-Evolution for Video…

Unified multimodal models integrating visual understanding and generation face a fundamental challenge: visual generation incurs substantially higher computational costs than understanding, particularly for video. This imbalance motivates…

Synthesizing high-quality instruction data from unsupervised text is a promising paradigm for training large language models (LLMs), yet automated methods for this task still exhibit significant limitations in the diversity and difficulty…

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any…

Effective feedback is essential for student learning but is time-intensive for teachers. We present LearnLens, a modular, LLM-based system that generates personalised, curriculum-aligned feedback in science education. LearnLens comprises…

Humans develop visual intelligence through perceiving and interacting with their environment - a self-supervised learning process grounded in egocentric experience. Inspired by this, we ask how can artificial systems learn stable object…

Curriculum learning (CL) aims to improve training by presenting data from "easy" to "hard", yet defining and measuring linguistic difficulty remains an open challenge. We investigate whether human-curated simple language can serve as an…

Machine learning relies heavily on data, yet the continuous growth of real-world data poses challenges for efficient dataset construction and training. A fundamental yet unsolved question is: given our current model and data, does a new…

Large-scale vision foundation models such as DINOv2 boast impressive performances by leveraging massive architectures and training datasets. But numerous scenarios require practitioners to reproduce those pre-training solutions, such as on…

Masked video modeling (MVM) has emerged as a simple and scalable self-supervised pretraining paradigm, but only encodes motion information implicitly, limiting the encoding of temporal dynamics in the learned representations. As a result,…

We introduce InstructVid2Vid, an end-to-end diffusion-based methodology for video editing guided by human language instructions. Our approach empowers video manipulation guided by natural language directives, eliminating the need for…

Ultra long video understanding remains an open challenge, as existing vision language models (VLMs) falter on such content due to limited context length and inefficient long term memory retention. To address this, recent works have…

Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified model. Despite the…

Recent self-supervised learning approaches focus on using a few thousand data points to learn policies for high-level, low-dimensional action spaces. However, scaling this framework for high-dimensional control require either scaling up the…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a dominant paradigm for enhancing Large Language Models (LLMs) reasoning, yet its reliance on external verifiers limits its scalability. Recent findings suggest that RLVR…

Learning skills by imitation is a promising concept for the intuitive teaching of robots. A common way to learn such skills is to learn a parametric model by maximizing the likelihood given the demonstrations. Yet, human demonstrations are…

In this work, we present a reward-driven automated curriculum reinforcement learning approach for interaction-aware self-driving at unsignalized intersections, taking into account the uncertainties associated with surrounding vehicles…

The superior performance of modern deep networks usually comes with a costly training procedure. This paper presents a new curriculum learning approach for the efficient training of visual backbones (e.g., vision Transformers). Our work is…

Recent advancements in prompt engineering strategies, such as Chain-of-Thought (CoT) and Self-Discover, have demonstrated significant potential in improving the reasoning abilities of Large Language Models (LLMs). However, these…

Video generative models trained on expert demonstrations have been utilized as performant text-conditioned visual planners for solving robotic tasks. However, generalization to unseen tasks remains a challenge. Whereas improved…

Large language model (LLM) agents are increasingly equipped with memory, which are stored experience and reusable guidance that can improve task-solving performance. Recent \emph{self-evolving} systems update memory based on interaction…