KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
Paper β’ 2606.03458 β’ Published β’ 49
Joseph [open/acc] Pollack PRO
Tonic
AI & ML interests
π€Making robots to help people learn things quicker π©π»βππ
Recent Activity
View all activity
Organizations
upvoted a paper 1 day ago
updated a
collection 8 days ago
liked a
dataset 8 days ago
liked 2
datasets 11 days ago
liked a
Space 15 days ago
reacted to salma-remyx's post with π 15 days ago
Post
5119
Just trained a 2B coding model to rank candidate AI/ML research ideas against the implicit preferences in a code repository's merge history.
The training data comes from a Gaussian Process fit on the accumulated dispositions in VQASynth, where each PR against a deployed project yields a pairwise comparison between the feature branch preferred and the baseline at main.
The GP scores candidate papers to synthesize preference pairs, and DPO with LoRA bakes the ranking pipeline into the model's weights.
After 1 epoch the model reaches 87.4% reward accuracy on the held-out eval split against 92.3% on training, consistent with learning the task without overfitting.
Now, I'm scaling the pipeline to thousands of repos for a generalization test.
Dataset: remyxai/mhpd-dpo-v0
Model: remyxai/mhpd-dpo-qwen3.5-2b-vqasynth
Substack: https://remyxai.substack.com/p/the-ai-pm
The training data comes from a Gaussian Process fit on the accumulated dispositions in VQASynth, where each PR against a deployed project yields a pairwise comparison between the feature branch preferred and the baseline at main.
The GP scores candidate papers to synthesize preference pairs, and DPO with LoRA bakes the ranking pipeline into the model's weights.
After 1 epoch the model reaches 87.4% reward accuracy on the held-out eval split against 92.3% on training, consistent with learning the task without overfitting.
Now, I'm scaling the pipeline to thousands of repos for a generalization test.
Dataset: remyxai/mhpd-dpo-v0
Model: remyxai/mhpd-dpo-qwen3.5-2b-vqasynth
Substack: https://remyxai.substack.com/p/the-ai-pm
liked 2
Spaces 16 days ago
replied to their post 19 days ago
hey dark , actually if you're keen it wouold be nice to get this into mobile apps , but i do need help with the ux
liked a
dataset 20 days ago
posted an update 22 days ago
Post
2823
ππ»ββοΈ Hey there folks ,
Turns out : if we predict π earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery π°οΈbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize π‘earth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
Turns out : if we predict π earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery π°οΈbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize π‘earth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
- 2 replies
reacted to danielhanchen's post with β€οΈ 22 days ago
Post
5812
Weβre excited to announce that Unsloth has joined the PyTorch Ecosystem! π₯π¦₯
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! π
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! π
Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth
- 2 replies
reacted to unmodeled-tyler's post with π 22 days ago
Post
2969
The UFO/UAP Dataset is complete!
unmodeled-tyler/DoW-UFO-UAP-1
The most recent release from the Department of War is there up in full and ready for analysis!
The dataset ships with an Hermes Agent Skill so you can quickly and easily start parsing through the data immediately.
Go chase some anomalies! π
unmodeled-tyler/DoW-UFO-UAP-1
The most recent release from the Department of War is there up in full and ready for analysis!
The dataset ships with an Hermes Agent Skill so you can quickly and easily start parsing through the data immediately.
Go chase some anomalies! π
reacted to cesear64's post with π 22 days ago
Post
4125
Just published: how we built production Sango (Central African Republic) translation without fine-tuning, parallel corpus, or training compute.
The method β vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon β generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included.
π Blog: https://huggingface.co/blog/MEYNG/sangoai
π¦ Dataset: MEYNG/sango-vocabulary
Would especially value feedback from anyone working on other low-resource African languages β Ewondo, Lingala, Wolof next on our roadmap.
The method β vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon β generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included.
π Blog: https://huggingface.co/blog/MEYNG/sangoai
π¦ Dataset: MEYNG/sango-vocabulary
Would especially value feedback from anyone working on other low-resource African languages β Ewondo, Lingala, Wolof next on our roadmap.
- 2 replies
liked a
Space 22 days ago
updated a
Space 25 days ago
updated a
collection 28 days ago
published a
Space 28 days ago
updated a
Space 28 days ago