shawnxzhu

shawnxzhu's activity

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

upvoted a paper 2 days ago

MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration

Paper • 2602.01734 • Published 9 days ago • 30

updated a model 3 months ago

shawnxzhu/cdgpt-1b

1B • Updated Nov 24, 2025 • 2

published a model 3 months ago

shawnxzhu/cdgpt-1b

1B • Updated Nov 24, 2025 • 2

upvoted a paper 4 months ago

QueST: Incentivizing LLMs to Generate Difficult Problems

Paper • 2510.17715 • Published Oct 20, 2025 • 35

upvoted a paper 5 months ago

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration

Paper • 2508.13755 • Published Aug 19, 2025 • 14

upvoted 2 papers 6 months ago

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Paper • 2508.18265 • Published Aug 25, 2025 • 213

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Paper • 2508.14029 • Published Aug 19, 2025 • 118

liked a dataset 8 months ago

TIGER-Lab/WebInstruct-verified

Viewer • Updated Nov 27, 2025 • 462k • 1.49k • 64

updated a dataset 9 months ago

shawnxzhu/DSAA6000Q-Mistral-7B-Instruct-v0.2-lima-dpo

Viewer • Updated May 11, 2025 • 1.03k • 2

published a dataset 9 months ago

shawnxzhu/DSAA6000Q-Mistral-7B-Instruct-v0.2-lima-dpo

Viewer • Updated May 11, 2025 • 1.03k • 2

updated a model 10 months ago

shawnxzhu/CHARM-calibrated-Skywork-Reward-Llama-3.1-8B-v0.2

Text Classification • 8B • Updated Apr 14, 2025 • 1

updated 2 collections 10 months ago

CHARM_datasets

Collection

Datasets used in CHARM: Calibrating Reward Models With Chatbot Arena Scores. • 16 items • Updated Apr 14, 2025

CHARM_models

Collection

Models used in CHARM: Calibrating Reward Models With Chatbot Arena Scores. • 1 item • Updated Apr 14, 2025