Denis Golovkin
CoruNethron
·
AI & ML interests
Imaging system color mapping function estimation
Recent Activity
reacted to DedeProGames's post with 🔥 4 days ago
We are working on LFM3-1.7B-Ox, a compact model for repo-level programming, agentic coding, and tinkering. new activity about 2 months ago
yandex/AliceAI-Foundation-80B-A3B-Base:Есть ли шанс получить эффективные кванты от Вас? liked a model 2 months ago
byteshape/Qwen3.8-27B-GGUFOrganizations
None yet
reacted to DedeProGames's post with 🔥 4 days ago
Есть ли шанс получить эффективные кванты от Вас?
2
#1 opened about 2 months ago
by
CoruNethron
reacted to Jiaqi-hkust's post with 🚀 3 months ago
Post
2,429
🧠 Remember-R1: Our fix for MLLMs forgetting the image during long reasoning
We noticed a frustrating problem: when multimodal models reason over long chains, they gradually stop looking at the image—and start hallucinating based on their own text.
So we built Remember‑R1, a simple RL framework that directly supervises visual attention on the original reasoning trajectory—no inference overhead, no proxy tasks.
We use three complementary rewards: coverage, persistence, and focus. They encourage the model to keep attending to relevant visual evidence even in later reasoning steps.
Results across 7 benchmarks and 2 model sizes: better reasoning, and—more importantly—visual attention decays much more slowly during generation.
No extra cost at inference, just cleaner supervision where it counts.
📄 Paper: https://arxiv.org/abs/2608.01314
💻 Code: https://github.com/Ch921-cell/Remember-R1
Happy to answer any questions and receive feedback!
#MultimodalAI #RL #MLLM #CoT #VisualReasoning
We noticed a frustrating problem: when multimodal models reason over long chains, they gradually stop looking at the image—and start hallucinating based on their own text.
So we built Remember‑R1, a simple RL framework that directly supervises visual attention on the original reasoning trajectory—no inference overhead, no proxy tasks.
We use three complementary rewards: coverage, persistence, and focus. They encourage the model to keep attending to relevant visual evidence even in later reasoning steps.
Results across 7 benchmarks and 2 model sizes: better reasoning, and—more importantly—visual attention decays much more slowly during generation.
No extra cost at inference, just cleaner supervision where it counts.
📄 Paper: https://arxiv.org/abs/2608.01314
💻 Code: https://github.com/Ch921-cell/Remember-R1
Happy to answer any questions and receive feedback!
#MultimodalAI #RL #MLLM #CoT #VisualReasoning
Either llama.cpp w. MTMD update or model seems to be broken
1
#1 opened 4 months ago
by
CoruNethron
MTP guide is missing for 3.5 models
👍 1
#2 opened 6 months ago
by
CoruNethron
Missing files
2
#5 opened 7 months ago
by
CoruNethron
IQ4_XS fits 64G mac when set max vram to 61440
👍 2
3
#1 opened about 1 year ago
by
CoruNethron
reacted to marksverdhei's post with 👀 9 months ago
Post
1,807
🤔 Many cultures penalize or look down upon self-celebratory behavior. One such example is liking your own post. So why do i do it? Two reasons:
1. I disagree that self-celebratory behavior is inherently bad.
2. On the Huggingface hub, if your post has 0 reactions, it takes TWO whole clicks to react instead of one. So it is actually a UI hack that lowers the bar to engage.
So if you see me reacting to to my own post and thing 'Ugh, this guy is so full of himself' you are only half correct 😆
Now behold as I perform this magic trick called "Exhausting all reaction options for increased visual engagement" so you don't have to click twice to react. You're welcome!
Follow this aspiring 🤗 HF Hub influencer for more half-serious bloat in your feed 😜
1. I disagree that self-celebratory behavior is inherently bad.
2. On the Huggingface hub, if your post has 0 reactions, it takes TWO whole clicks to react instead of one. So it is actually a UI hack that lowers the bar to engage.
So if you see me reacting to to my own post and thing 'Ugh, this guy is so full of himself' you are only half correct 😆
Now behold as I perform this magic trick called "Exhausting all reaction options for increased visual engagement" so you don't have to click twice to react. You're welcome!
Follow this aspiring 🤗 HF Hub influencer for more half-serious bloat in your feed 😜
Please add usage scenario examples
3
#10 opened 9 months ago
by
CoruNethron
upvoted an article 9 months ago
Article
GGML and llama.cpp join HF to ensure the long-term progress of Local AI


- +4
ggerganov, ngxson, allozaur, lysandre, victor, julien-c
• • 510Infinite thinking (after </thinking> tag with updated quants
5
#14 opened 10 months ago
by
CoruNethron
Fix model size typos in README.md
2
#1 opened 10 months ago
by
CoruNethron
Fix typos in README.md
1
#3 opened 10 months ago
by
CoruNethron
Thinking, coder models
3
#1 opened 10 months ago
by
NIK2703