-
Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
Paper • 2505.24726 • Published • 276 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 262 -
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Paper • 2507.01006 • Published • 240 -
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 259
Erik Thorelli
esthor
AI & ML interests
Quantifying Agent Experience
Recent Activity
liked
a model
3 days ago
nvidia/NVIDIA-Nemotron-Nano-9B-v2
liked
a dataset
2 months ago
google/simpleqa-verified
liked
a model
2 months ago
Qwen/Qwen3-VL-235B-A22B-Thinking
Organizations
None yet
-
Qwen/Qwen2-Audio-7B-Instruct
Audio-Text-to-Text • 8B • Updated • 199k • 498 -
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 4.95M • • 5.17k -
openai/whisper-large-v3-turbo
Automatic Speech Recognition • 0.8B • Updated • 4.62M • • 2.72k -
ibm-granite/granite-speech-3.3-8b
Automatic Speech Recognition • 9B • Updated • 67.4k • 145
-
Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
Paper • 2505.24726 • Published • 276 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 262 -
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Paper • 2507.01006 • Published • 240 -
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 259
-
Qwen/Qwen2-Audio-7B-Instruct
Audio-Text-to-Text • 8B • Updated • 199k • 498 -
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 4.95M • • 5.17k -
openai/whisper-large-v3-turbo
Automatic Speech Recognition • 0.8B • Updated • 4.62M • • 2.72k -
ibm-granite/granite-speech-3.3-8b
Automatic Speech Recognition • 9B • Updated • 67.4k • 145
models
0
None public yet
datasets
0
None public yet