Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization
Paper • 2608.20281 • Published • 12
qian kou
RZ-Q
AI & ML interests
None yet
Recent Activity
authored a paper 2 days ago
Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization authored a paper 2 days ago
Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge authored a paper 2 days ago
ChartWalker: Benchmarking the Cross-Chart RAG TaskOrganizations
None yet
authored 8
papers 2 days ago
Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge
Paper • 2608.01862 • Published • 6
ChartWalker: Benchmarking the Cross-Chart RAG Task
Paper • 2606.23997 • Published • 3
Rethinking Supervised Fine-Tuning: Emphasizing Key Answer Tokens for Improved LLM Accuracy
Paper • 2512.21017 • Published • 1
RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting
Paper • 2606.00147 • Published • 2
MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding
Paper • 2605.30794 • Published • 5
SPAR: Scholar Paper Retrieval with LLM-based Agents for Enhanced Academic Search
Paper • 2507.15245 • Published • 11
SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation
Paper • 2506.12689 • Published • 2
upvoted a paper about 1 month ago
upvoted a paper 5 months ago
updated a
dataset 8 months ago
published a
dataset 8 months ago
updated a
dataset 8 months ago
published a
dataset 8 months ago
updated a
dataset 10 months ago
published a
dataset 10 months ago
updated a
dataset 10 months ago
published a
dataset 10 months ago
liked a
model over 1 year ago
