8 papers
MixDiffusion: Mixing Diffusion-based Uni-condition Text-to-Image Generation Models for Multi-condition Image Synthesis
Pengcheng Wan, Liang Han, Lin Xu +2
Recent advances in text-to-image (T2I) generation have enabled controllable image synthesis by incorporating conditions beyond text. However, most existing diffusion-based methods…
Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation
Haoxiang Shi, Xiang Deng, Haoyu Zhang +3
Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural-language instructions while navigating in real-world-like environments. Most VLN-CE…
Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding
Haoyu Zhang, Qiaohui Chu, Meng Liu +3
AI personal assistants, deployed through robots or wearables, require embodied understanding to collaborate effectively with humans. However, current Multimodal Large Language Mode…
STransformer: Scalable Structured Transformers for Global Station Weather Forecasting
Hongyi Chen, Xiucheng Li, Xinyang Chen +4
Global Station Weather Forecasting (GSWF) is a key meteorological research area, critical to energy, aviation, and agriculture. Existing time series forecasting methods often ignor…
Towards Scalable and Structured Spatiotemporal Forecasting
Hongyi Chen, Xiucheng Li, Xinyang Chen +3
In this paper, we propose a novel Spatial Balance Attention block for spatiotemporal forecasting. To strike a balance between obeying spatial proximity and capturing global correla…
Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling
Qiyuan Deng, Xuefeng Bai, Kehai Chen +3
Reinforcement Learning (RL) algorithms for safety alignment of Large Language Models (LLMs), such as Direct Preference Optimization (DPO), encounter the challenge of distribution s…