-
PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling
Paper • 2512.04784 • Published • 23 -
X-GenGroup/PaCo-Dataset
Preview • Updated • 52 -
X-GenGroup/ConsistencyRank-Bench
Preview • Updated • 22 -
X-GenGroup/PaCo-Reward-7B
Image-Text-to-Text • Updated • 115 • 2
Collections
Discover the best community collections!
Collections trending this week
-
google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 134k • 484 -
google/gemma-3-270m
Text Generation • 0.3B • Updated • 66k • 921 -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.01M • 1.03k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 61.4k • 127
-
allenai/Olmo-3-7B-Think-SFT
Text Generation • 7B • Updated • 4.05k • 6 -
allenai/Dolci-Think-SFT-7B
Viewer • Updated • 2.27M • 1.78k • 5 -
allenai/Olmo-3-7B-Think-DPO
Text Generation • 528k • Updated • 6.22k • 3 -
allenai/Dolci-Think-DPO-7B
Viewer • Updated • 150k • 681 • 7
-
ibm-granite/granite-4.0-micro
Text Generation • 3B • Updated • 60.3k • 235 -
ibm-granite/granite-4.0-micro-base
Text Generation • 3B • Updated • 5.57k • 35 -
ibm-granite/granite-4.0-h-micro
Text Generation • 3B • Updated • 27.5k • 123 -
ibm-granite/granite-4.0-h-micro-base
Text Generation • 3B • Updated • 38.8k • 31
-
meta-llama/Llama-3.1-8B
Text Generation • 8B • Updated • 741k • • 1.97k -
meta-llama/Llama-3.1-70B
Text Generation • 71B • Updated • 97.6k • 391 -
meta-llama/Llama-3.1-405B
Text Generation • 406B • Updated • 219k • 948 -
meta-llama/Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 678k • • 877
-
cerebras/Qwen3-Coder-REAP-363B-A35B-FP8
Text Generation • 363B • Updated • 33 • 13 -
cerebras/Qwen3-Coder-REAP-246B-A35B-FP8
Text Generation • 246B • Updated • 94 • 17 -
cerebras/Qwen3-Coder-REAP-363B-A35B
Text Generation • 363B • Updated • 27 • 2 -
cerebras/Qwen3-Coder-REAP-246B-A35B
Text Generation • 246B • Updated • 33 • 4
-
PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling
Paper • 2512.04784 • Published • 23 -
X-GenGroup/PaCo-Dataset
Preview • Updated • 52 -
X-GenGroup/ConsistencyRank-Bench
Preview • Updated • 22 -
X-GenGroup/PaCo-Reward-7B
Image-Text-to-Text • Updated • 115 • 2
-
ibm-granite/granite-4.0-micro
Text Generation • 3B • Updated • 60.3k • 235 -
ibm-granite/granite-4.0-micro-base
Text Generation • 3B • Updated • 5.57k • 35 -
ibm-granite/granite-4.0-h-micro
Text Generation • 3B • Updated • 27.5k • 123 -
ibm-granite/granite-4.0-h-micro-base
Text Generation • 3B • Updated • 38.8k • 31
-
google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 134k • 484 -
google/gemma-3-270m
Text Generation • 0.3B • Updated • 66k • 921 -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.01M • 1.03k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 61.4k • 127
-
meta-llama/Llama-3.1-8B
Text Generation • 8B • Updated • 741k • • 1.97k -
meta-llama/Llama-3.1-70B
Text Generation • 71B • Updated • 97.6k • 391 -
meta-llama/Llama-3.1-405B
Text Generation • 406B • Updated • 219k • 948 -
meta-llama/Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 678k • • 877
-
allenai/Olmo-3-7B-Think-SFT
Text Generation • 7B • Updated • 4.05k • 6 -
allenai/Dolci-Think-SFT-7B
Viewer • Updated • 2.27M • 1.78k • 5 -
allenai/Olmo-3-7B-Think-DPO
Text Generation • 528k • Updated • 6.22k • 3 -
allenai/Dolci-Think-DPO-7B
Viewer • Updated • 150k • 681 • 7
-
cerebras/Qwen3-Coder-REAP-363B-A35B-FP8
Text Generation • 363B • Updated • 33 • 13 -
cerebras/Qwen3-Coder-REAP-246B-A35B-FP8
Text Generation • 246B • Updated • 94 • 17 -
cerebras/Qwen3-Coder-REAP-363B-A35B
Text Generation • 363B • Updated • 27 • 2 -
cerebras/Qwen3-Coder-REAP-246B-A35B
Text Generation • 246B • Updated • 33 • 4