12 accepted papers
Modeling wind-driven object dynamics from video observations is highly challenging due to the invisibility and spatio–temporal variability of wind, as well as the complex deformations of objects. We present DiffWind, a physics-informed differentiable framework that unifies wind–object interaction mo…
Reinforcement learning (RL) has demonstrated potential for enhancing reasoning in large language models (LLMs). However, effective RL training, which requires medium-difficulty training samples, faces two fundamental challenges: Effective Data Scarcity and Dynamic Difficulty Shifts, where medium-dif…
Graph Foundation Models (GFMs) have achieved remarkable success in generalizing across diverse domains. However, they mainly focus on Text-Attributed Graphs (TAGs), leaving Multimodal-Attributed Graphs (MAGs) largely untapped. Developing Multimodal Graph Foundation Models (MGFMs) allows for leveragi…
Vision-Language-Action (VLA) models typically bridge the gap between perceptual and action spaces by pre-training a large-scale Vision-Language Model (VLM) on robotic data. While this approach greatly enhances performance, it also incurs significant training costs. In this paper, we investigate how
Adversarial attacks are essential for evaluating the robustness of deep learning-based forensics, revealing potential vulnerabilities. However, most existing adversarial sample generation methods face significant trade-offs between anti-forensic ability, transferability, and visual quality, as they…
Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details of state-of-the-art reasoning LLMs are concealed (such as in OpenAI o1 blog and DeepSeek R1 technical report), thus the…
Accurately recommending candidate news articles to users has always been the core challenge of news recommendation system. News recommendations often require modeling of user interest to match candidate news. Recent efforts have primarily focused on extracting local subgraph information in a global…
Neural surface representation has demonstrated remarkable success in the areas of novel view synthesis and 3D reconstruction. However, assessing the geometric quality of 3D reconstructions in the absence of ground truth mesh remains a significant challenge, due to its rendering-based optimization pr…
Advanced persistent threats (APTs) pose significant risks to national infrastructure and corporate security. System logs record interactions between system entities, which are widely used for APT detection. However, the complex syntax and intricate relationships in system logs pose significant chall…
Text style transfer (TST) aims to flexibly adjust the style of text while preserving its core content. Although large language models (LLMs) excel in TST tasks, they often face unidirectional issues due to imbalanced training data and their tendency to generate safer responses. These challenges pres…
In recent years, linguistic generative steganography has been greatly developed. Current linguistic steganography methods can generate sufficiently fluent steganographic text, but cannot control the semantic expression of the generated steganographic text. In social network, steganographic text with…
Multimodal sentiment analysis aims to utilize different modalities including language, visual, and audio to identify human emotions in videos. Multimodal interaciton mechanism is the key challenge. Previous works lack modeling of multimodal interaction at different grain levels, and does not suppres…