Process Rewards with Learned Reliability
Paper • 2605.15529 • Published • 52
Abidoye Aanuoluwapo
Aanuoluwapo65
AI & ML interests
Computer vision and multimodal learning
Recent Activity
upvoted a paper 7 days ago
Process Rewards with Learned ReliabilityOrganizations
upvoted 8
papers 7 days ago
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
Paper • 2605.15980 • Published • 36
Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
Paper • 2605.02290 • Published • 39
AI for Auto-Research: Roadmap & User Guide
Paper • 2605.18661 • Published • 65
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
Paper • 2605.18739 • Published • 110
MMSkills: Towards Multimodal Skills for General Visual Agents
Paper • 2605.13527 • Published • 117
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
Paper • 2605.12882 • Published • 268
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
Paper • 2605.18451 • Published • 41
upvoted 2
papers 13 days ago
VoiceGRPO: Modern MoE Transformers with Group Relative Policy Optimization GRPO for AI Voice Health Care Applications on Voice Pathology Detection
Paper • 2503.03797 • Published • 1
A Survey on Computational Pathology Foundation Models: Datasets, Adaptation Strategies, and Evaluation Tasks
Paper • 2501.15724 • Published • 1
liked a
model 13 days ago
reacted to danielhanchen's post with 🔥 13 days ago
Post
5750
We’re excited to announce that Unsloth has joined the PyTorch Ecosystem! 🔥🦥
Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! 💕
Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth
Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! 💕
Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth
- 2 replies
reacted to HaChazal's post with 🔥 13 days ago
Post
126
I don't care about your degree.
I don't care about your résumé.
I care about your hunger.
Credentials just mean you were good at taking tests. Experience only comes through consistent effort.
I'm recruiting 10 people into Metaversal Studios — Hardknox '26 Research Cohort. We're building the orchestration engine that makes feature-length AI film possible. Five frontier research tracks. Real code. Real platform.
No tuition. No gatekeeping. Just an open door for people willing to put in the work. DM for more info
I don't care about your résumé.
I care about your hunger.
Credentials just mean you were good at taking tests. Experience only comes through consistent effort.
I'm recruiting 10 people into Metaversal Studios — Hardknox '26 Research Cohort. We're building the orchestration engine that makes feature-length AI film possible. Five frontier research tracks. Real code. Real platform.
No tuition. No gatekeeping. Just an open door for people willing to put in the work. DM for more info
reacted to cesear64's post with 🔥 13 days ago
Post
4115
Just published: how we built production Sango (Central African Republic) translation without fine-tuning, parallel corpus, or training compute.
The method — vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon — generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included.
📄 Blog: https://huggingface.co/blog/MEYNG/sangoai
📦 Dataset: MEYNG/sango-vocabulary
Would especially value feedback from anyone working on other low-resource African languages — Ewondo, Lingala, Wolof next on our roadmap.
The method — vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon — generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included.
📄 Blog: https://huggingface.co/blog/MEYNG/sangoai
📦 Dataset: MEYNG/sango-vocabulary
Would especially value feedback from anyone working on other low-resource African languages — Ewondo, Lingala, Wolof next on our roadmap.
- 2 replies
upvoted 5
articles 13 days ago
Article
EMO: Pretraining mixture of experts for emergent modularity
allenai
• • 38 Article
Granite 4.1 LLMs: How They’re Built
ibm-granite
• • 75 Article
How to build scalable web apps with OpenAI's Privacy Filter
- +1
ysharma, freddyaboulton, abidlabs
• • 11 Article
DeepInfra on Hugging Face Inference Providers 🔥
- +6
araikin, shang-pin-deepinfra, Pernekhan, yessenzhar, ovuruska, celinah, sbrandeis, Wauplin
• • 12 Article
Building Blocks for Foundation Model Training and Inference on AWS
amazon
• • 23 upvoted a paper 13 days ago