Dawn's picture

3

Dawn

LegendaryDawn

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 18 hours ago

Prepare Reasoning Language Models for Multi-Agent Debate with Self-Debate Reinforcement Learning

upvoted a paper about 19 hours ago

PhyCritic: Multimodal Critic Models for Physical AI

updated a model 1 day ago

LegendaryDawn/SDRL-baseline-Qwen3-8B-Base-DAPO-n8-bs256-long12-yarn2-step200

View all activity

Organizations

None yet

LegendaryDawn 's models 90

LegendaryDawn/baseline-Qwen2-VL-2B-G0-rlaifv-12k

2B • Updated May 12, 2025

LegendaryDawn/baseline-Qwen2-VL-2B-G0-bpo-12k

2B • Updated May 12, 2025

LegendaryDawn/baseline-Qwen2-VL-2B-G0-povid-12k

2B • Updated May 12, 2025

LegendaryDawn/ablation-Qwen2_5-G0-Rmmseed-GPT4o-rand-12k

8B • Updated May 12, 2025 • 1

LegendaryDawn/baseline-Qwen2-VL-2B-G0-csr-iter0-12k

2B • Updated May 12, 2025

LegendaryDawn/ablation-Qwen2_5-G16-R-multiyn1-r1-multiyn-2k

8B • Updated May 12, 2025 • 1

LegendaryDawn/ablation-Qwen2-VL-7b-G0-Rmmseed-GPT4o-adv-12k

8B • Updated May 12, 2025

LegendaryDawn/Qwen2-VL-7b-G0-bpo-12k

8B • Updated May 8, 2025

LegendaryDawn/Qwen2-VL-7b-G0-csr-iter0-12k

8B • Updated May 8, 2025

LegendaryDawn/Qwen2-VL-7b-G0-povid-12k

8B • Updated May 8, 2025

LegendaryDawn/Qwen2-VL-7b-G0-rlaifv-12k

8B • Updated May 8, 2025

LegendaryDawn/Paper-Qwen2_5-G16-R-multiyn-Rmmseed-GPT4o-adv-multiyn-12k

8B • Updated May 7, 2025

LegendaryDawn/Qwen2_5-G0-adv20-4-16-GPT4o-Rmmseed-12k

8B • Updated May 7, 2025 • 1

LegendaryDawn/baseline_CSR_select_12k_iter0_llava_lora

Updated May 7, 2025

LegendaryDawn/baseline-POVID_llava

Updated May 7, 2025

LegendaryDawn/baseline-RLAIF-V-llava-7B

7B • Updated May 6, 2025

LegendaryDawn/baseline-LlavaOneVision-G0-rlaifv-12k

8B • Updated May 6, 2025 • 4

LegendaryDawn/baseline-Qwen2_5-G0-rlaifv-12k

8B • Updated May 6, 2025

LegendaryDawn/baseline-LlavaOneVision-G0-csr-iter0-12k

8B • Updated May 6, 2025

LegendaryDawn/baseline-Qwen2_5-G0-bpo-12k

Image-Text-to-Text • 8B • Updated May 6, 2025

LegendaryDawn/baseline-Qwen2_5VL-G0-csr-iter0-12k

8B • Updated May 6, 2025

LegendaryDawn/baseline-Qwen2_5VL-G0-povid-12k

8B • Updated May 6, 2025

LegendaryDawn/baseline-Qwen2_5VL-G0-bpo-12k

8B • Updated May 6, 2025

LegendaryDawn/baseline-Qwen2_5-G0-povid-12k

8B • Updated May 6, 2025

LegendaryDawn/baseline-LlavaOneVision-G0-povid-12k

8B • Updated May 6, 2025

LegendaryDawn/baseline-Qwen2_5VL-G0-rlaifv-12k

8B • Updated May 6, 2025

LegendaryDawn/baseline-Qwen2_5-G0-csr-iter0-12k

8B • Updated May 6, 2025

LegendaryDawn/baseline-LlavaOneVision-G0-bpo-12k

Image-Text-to-Text • 8B • Updated May 6, 2025

LegendaryDawn/ours_optune_iter0

Feature Extraction • Updated May 14, 2024

LegendaryDawn/ours_sft_iter0

Feature Extraction • Updated May 12, 2024