SongW

songwang41's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 14 days ago

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n48-1111-step-950-hf

8B • Updated 14 days ago • 14

published a model 14 days ago

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n48-1111-step-950-hf

8B • Updated 14 days ago • 14

updated a model 14 days ago

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n48-1111-step-500-hf

8B • Updated 14 days ago • 14

published a model 14 days ago

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n48-1111-step-500-hf

8B • Updated 14 days ago • 14

updated 2 models 14 days ago

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n48-1111-step-1000-hf

8B • Updated 14 days ago • 11

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n24-1111-step-900-hf

8B • Updated 14 days ago • 10

published 2 models 14 days ago

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n48-1111-step-1000-hf

8B • Updated 14 days ago • 11

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n24-1111-step-900-hf

8B • Updated 14 days ago • 10

updated a model 14 days ago

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n24-1111-step-1470-hf

8B • Updated 14 days ago • 11

published a model 14 days ago

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n24-1111-step-1470-hf

8B • Updated 14 days ago • 11

updated a model 14 days ago

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n24-1111-step-1000-hf

8B • Updated 14 days ago • 10

published a model 14 days ago

songwang41/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-n24-1111-step-1000-hf

8B • Updated 14 days ago • 10

authored 2 papers 4 months ago

TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

Paper • 2508.20374 • Published Aug 28 • 21

Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation Service

Paper • 2407.15441 • Published Jul 22, 2024 • 2

upvoted 2 papers 4 months ago

Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation Service

Paper • 2407.15441 • Published Jul 22, 2024 • 2

TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuning

Paper • 2508.20374 • Published Aug 28 • 21

authored 4 papers 4 months ago

Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization

Paper • 2208.09770 • Published Aug 21, 2022

Integrative Decoding: Improve Factuality via Implicit Self-consistency

Paper • 2410.01556 • Published Oct 2, 2024

An End-to-End Dialogue Summarization System for Sales Calls

Paper • 2204.12951 • Published Apr 27, 2022

Complex Logical Instruction Generation

Paper • 2508.09125 • Published Aug 12 • 40