6 papers
EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation
Jiayi Luo, Hanxin Zhu, Chen Gao +5
Latent diffusion models (LDMs) have recently significantly advanced embodied learning in constructing powerful embodied manipulation world models. However, despite the remarkable p…
Rich-Media Re-Ranker: A User Satisfaction-Driven LLM Re-ranking Framework for Rich-Media Search
Zihao Guo, Ligang Zhou, Zeyang Tang +5
Re-ranking plays a crucial role in modern information search systems by refining the ranking of initial search results to better satisfy user information needs. However, existing m…
Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
Jiayi Luo, Jiayu Chen, Jiankun Wang +6
Diffusion Transformers (DiTs) achieve strong video generation quality but suffer from high inference cost due to dense 3D attention, motivating sparse attention techniques for impr…
Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty
Zeyu Shi, Ziming Wang, Tianyu Chen +4
The honesty of Large Language Models (LLMs) is increasingly important for safe deployment in high-stakes domains. However, this crucial trait is severely undermined by supervised f…
Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?
Ziming Wang, Zeyu Shi, Haoyi Zhou +3
Fine-tuned Large Language Models (LLMs) often demonstrate poor calibration, with their confidence scores misaligned with actual performance. While calibration has been extensively…
BotUmc: An Uncertainty-Aware Twitter Bot Detection with Multi-view Causal Inference
Tao Yang, Yang Hu, Feihong Lu +3
Social bots have become widely known by users of social platforms. To prevent social bots from spreading harmful speech, many novel bot detections are proposed. However, with the e…