NousResearch/RLVR_Coding_Problems
Preview
•
Updated
•
11
•
10
pascalmusabyimana
pascal-maker
AI & ML interests
computer vision, nlp , machine learning and deeplearning
Recent Activity
liked
a dataset
about 1 hour ago
NousResearch/RLVR_Coding_Problems
upvoted
an
article
about 2 hours ago
Tokenization in Transformers v5: Simpler, Clearer, and More Modular
upvoted
a
collection
about 12 hours ago
T5Gemma 2
Organizations
liked
a
dataset
about 1 hour ago
upvoted
an
article
about 2 hours ago
Article
Tokenization in Transformers v5: Simpler, Clearer, and More Modular
- +4
•
106
upvoted
a
collection
about 12 hours ago
upvoted
a
collection
1 day ago
liked
a
model
4 days ago
reacted to
kanaria007's
post with 👀
10 days ago
Post
2924
✅ New Article: *Pattern-Learning-Bridge (PLB)*
Title:
🧩 Pattern-Learning-Bridge: How SI-Core Actually Learns From Its Own Failures
🔗 https://huggingface.co/blog/kanaria007/learns-from-its-own-failures
---
Summary:
Most stacks “learn” by fine-tuning weights and redeploying — powerful, but opaque.
SI-Core already produces *structured evidence* (jump logs, ethics traces, effect ledgers, goal vectors, rollback traces), so learning can be *structural* instead:
*Upgrade policies, compensators, SIL code, and goal structures — using runtime evidence.*
> Learning isn’t a model tweak.
> *It’s upgrading the structures that shape behavior.*
---
Why It Matters:
• Makes improvement *localized and explainable* (what changed, where, and why)
• Keeps “self-improvement” *governable* (versioned deltas + review + CI/CD)
• Turns incidents/metric drift into *actionable patches*, not postmortem PDFs
• Scales to real ops: ethics policies, rollback plans, semantic compression, goal estimators
---
What’s Inside:
• What “learning” means in SI-Core (and what changes vs. classic ML)
• The *Pattern-Learning-Bridge*: where it sits between runtime evidence and governed code
• Safety properties: PLB proposes *versioned deltas*, never edits production directly
• Validation pipeline: sandbox/simulation → conformance checks → golden diffs → rollout
---
📖 Structured Intelligence Engineering Series
A non-normative, implementable design for “learning from failures” without sacrificing auditability.
Title:
🧩 Pattern-Learning-Bridge: How SI-Core Actually Learns From Its Own Failures
🔗 https://huggingface.co/blog/kanaria007/learns-from-its-own-failures
---
Summary:
Most stacks “learn” by fine-tuning weights and redeploying — powerful, but opaque.
SI-Core already produces *structured evidence* (jump logs, ethics traces, effect ledgers, goal vectors, rollback traces), so learning can be *structural* instead:
*Upgrade policies, compensators, SIL code, and goal structures — using runtime evidence.*
> Learning isn’t a model tweak.
> *It’s upgrading the structures that shape behavior.*
---
Why It Matters:
• Makes improvement *localized and explainable* (what changed, where, and why)
• Keeps “self-improvement” *governable* (versioned deltas + review + CI/CD)
• Turns incidents/metric drift into *actionable patches*, not postmortem PDFs
• Scales to real ops: ethics policies, rollback plans, semantic compression, goal estimators
---
What’s Inside:
• What “learning” means in SI-Core (and what changes vs. classic ML)
• The *Pattern-Learning-Bridge*: where it sits between runtime evidence and governed code
• Safety properties: PLB proposes *versioned deltas*, never edits production directly
• Validation pipeline: sandbox/simulation → conformance checks → golden diffs → rollout
---
📖 Structured Intelligence Engineering Series
A non-normative, implementable design for “learning from failures” without sacrificing auditability.
reacted to
MikeDoes's
post with 👀👀
11 days ago
Post
4180
What if an AI agent could be tricked into stealing your data, just by reading a tool's description? A new paper reports it's possible.
The "Attractive Metadata Attack" paper details this stealthy new threat. To measure the real-world impact of their attack, the researchers needed a source of sensitive data for the agent to leak. We're proud that the AI4Privacy corpus was used to create the synthetic user profiles containing standardized PII for their experiments.
This is a perfect win-win. Our open-source data helped researchers Kanghua Mo, 龙昱丞, Zhihao Li from Guangzhou University and The Hong Kong Polytechnic University to not just demonstrate a new attack, but also quantify its potential for harm. This data-driven evidence is what pushes the community to build better, execution-level defenses for AI agents.
🔗 Check out their paper to see how easily an agent's trust in tool metadata could be exploited: https://arxiv.org/pdf/2508.02110
#OpenSource
#DataPrivacy
#LLM
#Anonymization
#AIsecurity
#HuggingFace
#Ai4Privacy
#Worldslargestopensourceprivacymaskingdataset
The "Attractive Metadata Attack" paper details this stealthy new threat. To measure the real-world impact of their attack, the researchers needed a source of sensitive data for the agent to leak. We're proud that the AI4Privacy corpus was used to create the synthetic user profiles containing standardized PII for their experiments.
This is a perfect win-win. Our open-source data helped researchers Kanghua Mo, 龙昱丞, Zhihao Li from Guangzhou University and The Hong Kong Polytechnic University to not just demonstrate a new attack, but also quantify its potential for harm. This data-driven evidence is what pushes the community to build better, execution-level defenses for AI agents.
🔗 Check out their paper to see how easily an agent's trust in tool metadata could be exploited: https://arxiv.org/pdf/2508.02110
#OpenSource
#DataPrivacy
#LLM
#Anonymization
#AIsecurity
#HuggingFace
#Ai4Privacy
#Worldslargestopensourceprivacymaskingdataset
liked
3
models
15 days ago
reacted to
sanaka87's
post with 🔥
23 days ago
Post
3513
🚀 Introducing VideoCoF: Unified Video Editing with a Temporal Reasoner (Chain-of-Frames)!
We’re excited to introduce VideoCoF, a unified framework for instruction-based video editing that enables temporal reasoning and ~4× video length extrapolation, trained with only 50k video pairs. 🔥
🔍 What makes VideoCoF different?
🧠 Chain-of-Frames reasoning , mimic human thinking process like Seeing → Reasoning → Editing to apply edits accurately over time without external masks, ensuring physically plausible results.
📈 Strong length generalization — trained on 33-frame clips, yet supports multi-shot editing and long-video extrapolation (~4×).
🎯 Unified fine-grained editing — Object Removal, Addition, Swap, and Local Style Transfer, with instance-level & part-level, spatial-aware control.
⚡ Fast inference update
🚀 H100: ~20s / video with 4-step inference, making high-quality video editing far more practical for real-world use.
🔗 Links
📄 Paper: https://arxiv.org/abs/2512.07469
💻 Code: https://github.com/knightyxp/VideoCoF
🤗 Demo: XiangpengYang/VideoCoF
🧩 Models: XiangpengYang/VideoCoF
🌐 Project Page: https://videocof.github.io/
#VideoEditing #DiffusionModels #GenerativeAI #ComputerVision #AI
We’re excited to introduce VideoCoF, a unified framework for instruction-based video editing that enables temporal reasoning and ~4× video length extrapolation, trained with only 50k video pairs. 🔥
🔍 What makes VideoCoF different?
🧠 Chain-of-Frames reasoning , mimic human thinking process like Seeing → Reasoning → Editing to apply edits accurately over time without external masks, ensuring physically plausible results.
📈 Strong length generalization — trained on 33-frame clips, yet supports multi-shot editing and long-video extrapolation (~4×).
🎯 Unified fine-grained editing — Object Removal, Addition, Swap, and Local Style Transfer, with instance-level & part-level, spatial-aware control.
⚡ Fast inference update
🚀 H100: ~20s / video with 4-step inference, making high-quality video editing far more practical for real-world use.
🔗 Links
📄 Paper: https://arxiv.org/abs/2512.07469
💻 Code: https://github.com/knightyxp/VideoCoF
🤗 Demo: XiangpengYang/VideoCoF
🧩 Models: XiangpengYang/VideoCoF
🌐 Project Page: https://videocof.github.io/
#VideoEditing #DiffusionModels #GenerativeAI #ComputerVision #AI
- 2 replies
reacted to
XiangpengYang's
post with 🔥
25 days ago
Post
3003
🚀 Introducing VideoCoF: Unified Video Editing with a Temporal Reasoner (Chain-of-Frames)!
We’re excited to introduce VideoCoF, a unified framework for instruction-based video editing that enables temporal reasoning and ~4× video length extrapolation, trained with only 50k video pairs. 🔥
🔍 What makes VideoCoF different?
🧠 Chain-of-Frames reasoning , mimic human thinking process like Seeing → Reasoning → Editing to apply edits accurately over time without external masks, ensuring physically plausible results.
📈 Strong length generalization — trained on 33-frame clips, yet supports multi-shot editing and long-video extrapolation (~4×).
🎯 Unified fine-grained editing — Object Removal, Addition, Swap, and Local Style Transfer, with instance-level & part-level, spatial-aware control.
⚡ Fast inference update
🚀 H100: ~20s / video with 4-step inference, making high-quality video editing far more practical for real-world use.
🔗 Links
📄 Paper: https://arxiv.org/abs/2512.07469
💻 Code: https://github.com/knightyxp/VideoCoF
🤗 Demo: XiangpengYang/VideoCoF
🧩 Models: XiangpengYang/VideoCoF
🌐 Project Page: https://videocof.github.io/
#VideoEditing #DiffusionModels #GenerativeAI #ComputerVision #AI
We’re excited to introduce VideoCoF, a unified framework for instruction-based video editing that enables temporal reasoning and ~4× video length extrapolation, trained with only 50k video pairs. 🔥
🔍 What makes VideoCoF different?
🧠 Chain-of-Frames reasoning , mimic human thinking process like Seeing → Reasoning → Editing to apply edits accurately over time without external masks, ensuring physically plausible results.
📈 Strong length generalization — trained on 33-frame clips, yet supports multi-shot editing and long-video extrapolation (~4×).
🎯 Unified fine-grained editing — Object Removal, Addition, Swap, and Local Style Transfer, with instance-level & part-level, spatial-aware control.
⚡ Fast inference update
🚀 H100: ~20s / video with 4-step inference, making high-quality video editing far more practical for real-world use.
🔗 Links
📄 Paper: https://arxiv.org/abs/2512.07469
💻 Code: https://github.com/knightyxp/VideoCoF
🤗 Demo: XiangpengYang/VideoCoF
🧩 Models: XiangpengYang/VideoCoF
🌐 Project Page: https://videocof.github.io/
#VideoEditing #DiffusionModels #GenerativeAI #ComputerVision #AI
-
- 11 replies
liked
a
Space
about 1 month ago
liked
3
models
about 1 month ago
reacted to
danielhanchen's
post with 🔥🔥
about 1 month ago
Post
8509
Qwen3-Next can now be Run locally! (30GB RAM)
Instruct GGUF: unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF
The models come in Thinking and Instruct versions and utilize a new architecture, allowing it to have ~10x faster inference than Qwen32B.
💜 Step-by-step Guide: https://docs.unsloth.ai/models/qwen3-next
Thinking GGUF: unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF
Instruct GGUF: unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF
The models come in Thinking and Instruct versions and utilize a new architecture, allowing it to have ~10x faster inference than Qwen32B.
💜 Step-by-step Guide: https://docs.unsloth.ai/models/qwen3-next
Thinking GGUF: unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF
reacted to
sergiopaniego's
post with 🔥
about 1 month ago
Post
1778
nanochat is now in transformers!
The LLM by @karpathy is officially in the library, and we wrote a blog covering: how did we port the model, differences from the original, and how to run or train it.
go read it 🤓
nanochat-students/transformers
The LLM by @karpathy is officially in the library, and we wrote a blog covering: how did we port the model, differences from the original, and how to run or train it.
go read it 🤓
nanochat-students/transformers