arxiv:2512.10359
fansunqi
fansunqi
·
AI & ML interests
Deep learning
Recent Activity
upvoted
a
paper
7 days ago
Fast and Accurate Causal Parallel Decoding using Jacobi Forcing
upvoted
a
paper
8 days ago
DEER: Draft with Diffusion, Verify with Autoregressive Models
authored
a paper
13 days ago
Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task
Organizations
None yet
models
13
fansunqi/mind2web_meta_task_ws_org_sim_0_9_grpo_qwen2_5_vl_3b_h20_step_200
4B
•
Updated
•
6
fansunqi/mind2web_meta_task_ws_org_sim_0_9_grpo_qwen2_5_vl_3b_h20_step_180
4B
•
Updated
•
6
fansunqi/mind2web_meta_task_ws_org_sim_0_9_grpo_qwen2_5_vl_3b_h20_step_160
4B
•
Updated
•
5
fansunqi/combine_phase3_from_mind2web_phase1_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_375
4B
•
Updated
•
5
fansunqi/combine_phase3_from_mind2web_phase1_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_450
4B
•
Updated
•
6
fansunqi/combine_phase3_from_mind2web_phase1_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_300
4B
•
Updated
•
5
fansunqi/combine_phase3_from_mind2web_phase1_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_250
4B
•
Updated
•
5
fansunqi/combine_phase3_from_mind2web_phase1_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_200
4B
•
Updated
•
5
fansunqi/combine_parquet_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_450
4B
•
Updated
•
6
fansunqi/combine_parquet_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_400
4B
•
Updated
•
4