works on

From the 1 of 14 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

Autonomous Video Generation with Counterfactual Controllability for Self-Evolving World Models

Xin Wang, Wenxuan Liu, Tongtong Feng +1

The paper introduces autonomous video generation, a framework that creates future video frames conditioned on counterfactual interventions and embodiment constraints, enabling self…

cs.CV2026

AV-Unified: A Unified Framework for Audio-visual Scene Understanding

Guangyao Li, Xin Wang, Wenwu Zhu

When humans perceive the world, they naturally integrate multiple audio-visual tasks within dynamic, real-world scenes. However, current works such as event localization, parsing,…

cs.CV2025

PhyVLLM: Physics-Guided Video Language Model with Motion-Appearance Disentanglement

Yu-Wei Zhan, Xin Wang, Hong Chen +6

Video Large Language Models (Video LLMs) have shown impressive performance across a wide range of video-language tasks. However, they often fail in scenarios requiring a deeper und…

cs.CV2025

Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards

Zijing Hu, Fengda Zhang, Long Chen +6

Diffusion models have achieved remarkable success in text-to-image generation. However, their practical applications are hindered by the misalignment between generated images and c…

cs.CV2025

JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration

Mingzi Wang, Yuan Meng, Chen Tang +9

The co-design of neural network architectures, quantization precisions, and hardware accelerators offers a promising approach to achieving an optimal balance between performance an…

cs.CV2024

Multi-weather Cross-view Geo-localization Using Denoising Diffusion Models

Tongtong Feng, Qing Li, Xin Wang +3

Cross-view geo-localization in GNSS-denied environments aims to determine an unknown location by matching drone-view images with the correct geo-tagged satellite-view images from a…