arxiv:2601.09688
Yibo Wang
yiboowang
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
Learning from the Self-future: On-policy Self-distillation for dLLMs upvoted a paper 7 days ago
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic EnvironmentsOrganizations
models 15
yiboowang/VTC-R1-Glyph
Image-Text-to-Text • 934k • Updated • 21 • 2
yiboowang/vtc-r1-glm4vbase
Updated
yiboowang/simplerl-qwen32b-ins-origin-step500
33B • Updated • 2
yiboowang/simplerl-qwen32b-ins-merge0.2-ppl2-step500
33B • Updated • 4
yiboowang/RF-Qwen2.5-32B-Instruct-curriculum-mix-tasks-squence-2k-ppl6-ep8_step_120
33B • Updated • 2
yiboowang/RF-Qwen2.5-32B-Instruct-curriculum-mix-tasks-formula-2k-ppl2-ep6_step_336
33B • Updated • 1
yiboowang/Qwen2.5-32B-Instruct_simple_r1_v6_ep4_bs2
Text Generation • 33B • Updated • 2
yiboowang/Qwen2.5-32B-Instruct_random_r1_v6_ep4_bs2
Text Generation • 33B • Updated • 6
yiboowang/RF-Qwen2.5-32B-Instruct-curriculum-mix-tasks-back_forward-2k-ppl2-ep4-step40
33B • Updated • 4
yiboowang/Qwen2.5-32B-Instruct_origin_5k_v6_ep4_bs2
Text Generation • 33B • Updated • 4
datasets 19
yiboowang/R1-Compress-other
Preview • Updated • 20
yiboowang/r1-model_generated
Preview • Updated • 53
yiboowang/R1-Compress-source
Preview • Updated • 3
yiboowang/R1-Compress
Preview • Updated • 101
yiboowang/R1-Compress-s1
Preview • Updated • 12
yiboowang/R1-Compress-Baseline
Preview • Updated • 51
yiboowang/cot-valve
Preview • Updated • 4
yiboowang/train_r1math_5k_c3ot
Preview • Updated • 11
yiboowang/tokenskip
Viewer • Updated • 3.72k • 8
yiboowang/c3ot
Viewer • Updated • 7.44k • 25 • 1