Siheng Xiong
sxiong
·
AI & ML interests
Agentic AI · LLM Reasoning
Recent Activity
updated a model 2 days ago
sxiong/DHSA authored a paper 2 days ago
DIVE: Unlocking Self-Improvement in Frozen Language Models Through Diversity-Driven Skill EvolutionOrganizations
datasets 21
sxiong/deepcontrol_output
Viewer • Updated • 207k • 368 • 1
sxiong/SWAP
Viewer • Updated • 69.8k • 269 • 2
sxiong/DHSA_RULER
Preview • Updated • 156 • 1
sxiong/DHSA_Long-Data-Collections
Viewer • Updated • 2.33M • 330 • 5
sxiong/entailmentbank
Viewer • Updated • 17.5k • 582 • 1
sxiong/entailmentbank_output
Viewer • Updated • 678 • 44 • 1
sxiong/blocksworld_output
Viewer • Updated • 360 • 37 • 1
sxiong/math_trajectory_parsed
Viewer • Updated • 22.1k • 35 • 1
sxiong/synthetic-math
Viewer • Updated • 10.4k • 134 • 1
sxiong/BoardgameQA-trajectory
Viewer • Updated • 9.5k • 65 • 1