Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval
Paper
•
2408.10613
•
Published
AI & ML interests
None defined yet.
Recent Activity
View all activity
Suu
authored
6
papers
23 days ago
CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts
Paper
•
2410.16077
•
Published
•
1
Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts
Paper
•
2502.12928
•
Published
UniAttn: Reducing Inference Costs via Softmax Unification for Post-Training LLMs
Paper
•
2502.00439
•
Published
•
1
LightRetriever: A LLM-based Hybrid Retrieval Architecture with 1000x Faster Query Inference
Paper
•
2505.12260
•
Published
Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
Paper
•
2508.07629
•
Published
•
39
Suu
updated
a
collection
25 days ago
ffgcc
updated
4
datasets
about 1 month ago
ffgcc
updated
5
models
about 1 month ago
caskcsg/Llama-3-8B-LongMagpie-p-mix-512K-Instruct
8B
•
Updated
•
5
caskcsg/Llama-3-8B-LongMagpie-512K-Instruct
8B
•
Updated
•
4
caskcsg/Llama-3-8B-NExtLong-512K-Base
8B
•
Updated
•
3
caskcsg/Llama-3-8B-NExtLong-512K-Instruct
8B
•
Updated
•
3
•
4
caskcsg/Llama-3-8B-NExtLong-128K-Base
8B
•
Updated
•
5
ffgcc
updated
4
datasets
about 1 month ago