arxiv:2510.27492
🔄 In a Training Loop
Yunzhuo Hao
luckychao
AI & ML interests
NLP
Recent Activity
upvoted a paper 9 days ago
Morphing into Hybrid Attention Models upvoted a paper about 1 month ago
ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics upvoted a paper about 2 months ago
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon WorkflowsOrganizations
datasets 14
luckychao/hhsxbhjgy
Updated • 12
luckychao/joint_test_20260205_200940
Viewer • Updated • 16 • 27
luckychao/visualcot_1k_latent_400steps_grpo_1.0temp_64bsz_20260128_182125
Viewer • Updated • 27 • 6
luckychao/emu_showcase
Viewer • Updated • 492 • 31
luckychao/showcase_preview
Viewer • Updated • 51 • 20
luckychao/frozenlake-step-400
Viewer • Updated • 44 • 17
luckychao/vlmevalkit_tsv
Preview • Updated • 218
luckychao/visualcot-step-900
Viewer • Updated • 32 • 11
luckychao/frozen-lake-action-safe-single-image-tag-20k-cot-train-6000
Viewer • Updated • 6k • 9
luckychao/frozen-lake-action-safe-single-image-tag-20k-cot-test-200
Viewer • Updated • 200 • 9