-
WorldKV: Efficient World Memory with World Retrieval and Compression
Paper • 2605.22718 • Published • 40 -
DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
Paper • 2605.25604 • Published • 136 -
Macaron-A2UI: A Model for Generative UI in Personal Agents
Paper • 2605.24830 • Published • 82 -
Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
Paper • 2601.04720 • Published • 59
Terrell Henry
ColdSlither
·
AI & ML interests
Training models. Learning inference engineering and CUDA. Fiddling around with making a agent harness
Recent Activity
updated a bucket 1 day ago
ColdSlither/emotional-roleplay-finetuning-dataset-bucket published a bucket 1 day ago
ColdSlither/emotional-roleplay-finetuning-dataset-bucket updated a bucket 1 day ago
ColdSlither/red_teaming_reward_modeling_pairwise_no_as_an_ai-bucketOrganizations
-
Chat With Janus-Pro-7B
🌍2.02kA unified multimodal understanding and generation model.
-
kudzueye/boreal-hl-v1
Text-to-Video • Updated • 125 -
kudzueye/boreal-flux-dev-v2
Text-to-Image • Updated • 791 • • 165 -
bartowski/thesby_Qwen2.5-VL-7B-NSFW-Caption-V3-GGUF
Image-Text-to-Text • 8B • Updated • 9.04k • 72
-
WorldKV: Efficient World Memory with World Retrieval and Compression
Paper • 2605.22718 • Published • 40 -
DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
Paper • 2605.25604 • Published • 136 -
Macaron-A2UI: A Model for Generative UI in Personal Agents
Paper • 2605.24830 • Published • 82 -
Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
Paper • 2601.04720 • Published • 59
-
Chat With Janus-Pro-7B
🌍2.02kA unified multimodal understanding and generation model.
-
kudzueye/boreal-hl-v1
Text-to-Video • Updated • 125 -
kudzueye/boreal-flux-dev-v2
Text-to-Image • Updated • 791 • • 165 -
bartowski/thesby_Qwen2.5-VL-7B-NSFW-Caption-V3-GGUF
Image-Text-to-Text • 8B • Updated • 9.04k • 72