相关论文: ViaRL: Adaptive Temporal Grounding via Visual Iter…

Designing effective reward functions remains a fundamental challenge in reinforcement learning (RL), as it often requires extensive human effort and domain expertise. While RL from human feedback has been successful in aligning agents with…

We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are learned using a contrastive loss, where two augmented clips…

Vision-language reinforcement learning (RL) has primarily focused on narrow domains (e.g. geometry or chart reasoning). This leaves broader training scenarios and resources underexplored, limiting the exploration and learning of Vision…

Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. However, mainstream solutions generally adopt hand-crafted…

Vision-Language Models (VLMs) excel at visual reasoning but still struggle with integrating external knowledge. Retrieval-Augmented Generation (RAG) is a promising solution, but current methods remain inefficient and often fail to maintain…

We investigate the visual cross-embodiment imitation setting, in which agents learn policies from videos of other agents (such as humans) demonstrating the same task, but with stark differences in their embodiments -- shape, actions,…

We introduce ED-VTG, a method for fine-grained video temporal grounding utilizing multi-modal large language models. Our approach harnesses the capabilities of multimodal LLMs to jointly process text and video, in order to effectively…

Learning visuomotor policies for agile quadrotor flight presents significant difficulties, primarily from inefficient policy exploration caused by high-dimensional visual inputs and the need for precise and low-latency control. To address…

Recent text-only models demonstrate remarkable mathematical reasoning capabilities. Extending these to visual domains requires vision-language models to translate images into text descriptions. However, current models, trained to produce…

Continual learning (CL) with Vision-Language Models (VLMs) has overcome the constraints of traditional CL, which only focuses on previously encountered classes. During the CL of VLMs, we need not only to prevent the catastrophic forgetting…

Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability. While analytic learning enables rapid, recursive closed-form updates, its efficacy is often…

This thesis explores the central question of how to leverage temporal relations among video elements to advance video understanding. Addressing the limitations of existing methods, the work presents a five-fold contribution: (1) an…

Existing Multimodal Large Language Models (MLLMs) often suffer from hallucinations in long video understanding (LVU), primarily due to the imbalance between textual and visual tokens. Observing that MLLMs handle short visual inputs well,…

Reinforcement learning from verifiable rewards (RLVR) has recently been extended from text-only LLMs to vision-language models (VLMs) to elicit long-chain multimodal reasoning. However, RLVR-trained VLMs still exhibit two persistent failure…

Vision-Language-Action (VLA) models have demonstrated potential in autonomous driving. However, two critical challenges hinder their development: (1) Existing VLA architectures are typically based on imitation learning in open-loop setup…

Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization models rely on specific datasets for training and have high data…

Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation, offering strong cross-task and cross-scene generalization with broad impact on embodied AI. However, current VLA models often lack…

Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on…

Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their…

Visual retrieval-augmented generation (VRAG) augments vision-language models (VLMs) with external visual knowledge to ground reasoning and reduce hallucinations. Yet current VRAG systems often fail to reliably perceive and integrate…