James Cai

jamescai20's activity

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

upvoted a paper about 2 months ago

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

Paper • 2505.24273 • Published May 30 • 4

commented 2 papers 3 months ago

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

Paper • 2505.24273 • Published May 30 • 4 •

4

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

Paper • 2505.24273 • Published May 30 • 4 •

4

authored 2 papers 3 months ago

Enhancing Large Language Models' Situated Faithfulness to External Contexts

Paper • 2410.14675 • Published Oct 18, 2024

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

Paper • 2505.24273 • Published May 30 • 4

updated a dataset 4 months ago

jamescai20/advanced-geometry_sft

Viewer • Updated May 10 • 76.8k • 4

published a dataset 4 months ago

jamescai20/advanced-geometry_sft

Viewer • Updated May 10 • 76.8k • 4

updated a dataset 4 months ago

jamescai20/sudoku_sft

Viewer • Updated May 9 • 76.8k • 2

published a dataset 4 months ago

jamescai20/sudoku_sft

Viewer • Updated May 9 • 76.8k • 2

updated a model 4 months ago

jamescai20/qwen3b-sudoku-1-backtrack-shuffled

Updated May 7

published a model 4 months ago

jamescai20/qwen3b-sudoku-1-backtrack-shuffled

Updated May 7

updated a model 4 months ago

jamescai20/qwen3b-sudoku-optimal-synthetic

Updated May 6

published a model 4 months ago

jamescai20/qwen3b-sudoku-optimal-synthetic

Updated May 6

updated a dataset 6 months ago

jamescai20/tts-reasoning

Viewer • Updated Mar 20 • 2.65M • 3

published a dataset 6 months ago

jamescai20/tts-reasoning

Viewer • Updated Mar 20 • 2.65M • 3