MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
Paper • 2610.11959 • Published • 49
Rauno Ryystö
raunoryys
AI & ML interests
None yet
Recent Activity
reacted to danielhanchen's post with 🔥 41 minutes ago
You can now train your own Decision model like Jev locally!
We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.
Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth reacted to danielhanchen's post with ❤️ 41 minutes ago
You can now train your own Decision model like Jev locally!
We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.
Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.
GitHub: https://github.com/unslothai/unsloth
Guide: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth upvoted a paper about 3 hours ago
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-ImprovementOrganizations
None yet
upvoted 2
papers about 3 hours ago
upvoted a collection about 3 hours ago
upvoted a paper about 3 hours ago
upvoted a collection about 4 hours ago
upvoted a collection 1 day ago
upvoted a paper 1 day ago
upvoted an article 2 days ago
Article
Multimodal open d1 decision models for the edge
LiquidAI
• • 27 upvoted a paper 2 days ago
upvoted a collection 2 days ago
upvoted an article 2 days ago
Article
One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
nvidia
• • 12 upvoted 7
papers 2 days ago
Stop Comparing LLM Agents Without Disclosing the Harness
Paper • 2605.23950 • Published • 1
UNREAL: Unifying Retrieval and Long-Context with a Single Model
Paper • 2610.08463 • Published • 22
NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale
Paper • 2610.08430 • Published • 16
MiniCorp: The Last Mile of the AI Agent Firm
Paper • 2610.05912 • Published • 28
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Paper • 2610.07767 • Published • 107
SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting
Paper • 2610.04109 • Published • 32
Capability-Driven Self-Evolution of Agent Memory
Paper • 2610.06361 • Published • 19
upvoted a collection 3 days ago
upvoted an article 3 days ago
Article
autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model
autotrust
• • 219