12 papers
Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models
Jia Deng, Junyi Li, Wayne Xin Zhao +3
Diffusion large language models (dLLMs) offer an efficient alternative to autoregressive models through parallel decoding, yet existing post-training methods largely rely on random…
EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models
Hongyu Lu, Feng Zhang, Wenwei Jin +5
Large vision-language models (LVLMs) achieve strong performance on image and video understanding tasks, but their inference efficiency is constrained by the large number of visual…
The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
Siqi Zhu, Xuyan Ye, Hongyu Lu +2
On-policy distillation (OPD) and on-policy self-distillation (OPSD) have emerged as promising post-training methods for large language models, offering dense token-level supervisio…
LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs
Hongyu Lu, Feng Zhang, Wenwei Jin +5
Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolutio…
SA-CAISR: Stage-Adaptive and Conflict-Aware Incremental Sequential Recommendation
Xiaomeng Song, Xinru Wang, Hanbing Wang +4
Sequential recommendation (SR) aims to predict a user's next action by learning from their historical interaction sequences. In real-world applications, these models require period…
GenCI: Generative Modeling of User Interest Shift via Cohort-based Intent Learning for CTR Prediction
Kesha Ou, Zhen Tian, Wayne Xin Zhao +2
Click-through rate (CTR) prediction plays a pivotal role in online advertising and recommender systems. Despite notable progress in modeling user preferences from historical behavi…