suu's picture

5 9 7

suu

Suu

·

AI & ML interests

None yet

Recent Activity

upvoted a collection 18 days ago

upvoted a paper 18 days ago

Agentic Entropy-Balanced Policy Optimization

updated a collection about 1 month ago

KlearReasoner-8B

View all activity

Organizations

authored a paper about 1 month ago

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Paper • 2509.20712 • Published Sep 25 • 18

authored 6 papers 3 months ago

Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval

Paper • 2408.10613 • Published Aug 20, 2024

CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts

Paper • 2410.16077 • Published Oct 21, 2024 • 1

Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts

Paper • 2502.12928 • Published Feb 18 • 1

UniAttn: Reducing Inference Costs via Softmax Unification for Post-Training LLMs

Paper • 2502.00439 • Published Feb 1 • 1

LightRetriever: A LLM-based Hybrid Retrieval Architecture with 1000x Faster Query Inference

Paper • 2505.12260 • Published May 18

Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

Paper • 2508.07629 • Published Aug 11 • 41

authored 2 papers about 1 year ago

Scaffold-BPE: Enhancing Byte Pair Encoding with Simple and Effective Scaffold Token Removal

Paper • 2404.17808 • Published Apr 27, 2024

MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts

Paper • 2407.09816 • Published Jul 13, 2024 • 1