5 papers
GRACE: Gradient-aligned Reasoning Data Curation for Efficient Post-training
Junjie Li, Ziao Wang, NingXuan Ma +2
Existing reasoning data curation pipelines score whole samples, treating every intermediate step as equally valuable. In reality, steps within a trace contribute very unevenly, and…
ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference
Junjie Li, Jiong Lou, Jie Li
Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Value (KV) cache memory wall, yet existing pruning methods force a choice betwee…
Uncovering Intrinsic Capabilities: A Paradigm for Data Curation in Vision-Language Models
Junjie Li, Ziao Wang, Jianghong Ma +1
Large vision-language models (VLMs) achieve strong benchmark performance, but controlling their behavior through instruction tuning remains difficult. Reducing the budget of instru…
GCRank: A Generative Contextual Comprehension Paradigm for Takeout Ranking Model
Ziheng Ni, Congcong Liu, Cai Shang +10
The ranking stage serves as the central optimization and allocation hub in advertising systems, governing economic value distribution through eCPM and orchestrating the user-centri…
GiVE: Guiding Visual Encoder to Perceive Overlooked Information
Junjie Li, Jianghong Ma, Xiaofeng Zhang +2
Multimodal Large Language Models have advanced AI in applications like text-to-video generation and visual question answering. These models rely on visual encoders to convert non-t…