AT^2PO: Agentic Turn-based Policy Optimization via Tree Search
Paper
•
2601.04767
•
Published
•
18
Demian L. P.
very-cooluser
AI & ML interests
Anything that can run on ~3GB of memory is a instant thumbs up to me
Recent Activity
upvoted
a
paper
18 minutes ago
AT^2PO: Agentic Turn-based Policy Optimization via Tree Search
upvoted
a
paper
18 minutes ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Organizations
None yet
upvoted
2
papers
18 minutes ago
reacted to
daavoo's
post with 🔥
20 days ago
Post
1845
2025: The Year of Agents.
2026: The Year of Local Agents?
Relying on cloud-hosted LLMs is often overkill. While frontier models still lead in complex coding, local models are now more than capable of handling many agentic workflows—with zero latency and total privacy.
To help bridge the gap between local inference and usable agents, I’m releasing agent.cpp: https://github.com/mozilla-ai/agent.cpp
It provides minimal, high-performance building blocks for agents in C++, built directly around the awesome llama.cpp ecosystem.
Stop sending your data to a remote API. Start building and running agents on your own hardware.
2026: The Year of Local Agents?
Relying on cloud-hosted LLMs is often overkill. While frontier models still lead in complex coding, local models are now more than capable of handling many agentic workflows—with zero latency and total privacy.
To help bridge the gap between local inference and usable agents, I’m releasing agent.cpp: https://github.com/mozilla-ai/agent.cpp
It provides minimal, high-performance building blocks for agents in C++, built directly around the awesome llama.cpp ecosystem.
Stop sending your data to a remote API. Start building and running agents on your own hardware.
- 1 reply
Pretty neat app
Update README.md
#8 opened 3 months ago
by
very-cooluser
Update README.md
#4 opened 3 months ago
by
very-cooluser
Update README.md
#2 opened 3 months ago
by
very-cooluser
reacted to
Locutusque's
post with 🔥
4 months ago
Post
7096
🌲🍄 LLM Forest Orchestra: Turning Hidden States into Music
Hello everyone! I'm excited to introduce a new Space I've been developing called LLM Forest Orchestra. This project converts the hidden states and attention patterns of transformer models into layered MIDI compositions. The concept draws inspiration from mushrooms and mycelial networks in forests. Fungi create underground connections linking plants and trees, establishing what some call a "wood-wide web" where signals and nutrients travel. Researchers have discovered that these exchanges form patterns resembling rhythms and pulses. When translated appropriately, these patterns can become music.
Transformers operate through remarkably similar principles: tokens share signals via hidden states and attention heads. This Space transforms those invisible information flows into notes, chords, and rhythms, treating the model as a digital forest orchestra.
🎛 Features
* Two compute modes:
- Full model operates on a Hugging Face model (defaulting to unsloth/Qwen3-14B-Base).
- Mock latents provides a CPU-friendly option that simulates tensors for immediate experimentation.
* Musical controls: You can adjust scale selection, tempo grid, velocity range, instrument/role presets, and seed randomization.
* Output: The system generates .mid files compatible with DAWs and remixing workflows.
🌌 Why?
Neural networks already resemble unusual musical instruments: signals flow through them, patterns emerge organically, and careful observation reveals hidden melodies. This is analogous to the forest's secret orchestra of mushrooms and trees.
👉 Try it
Try the Space here: Locutusque/LLM-Forest-Orchestra. I'm excited to hear the sounds you can generate. Please share your created MIDIs or remixes in the comments. Let's explore how this hidden forest of transformers can sound together. 🌳🎶
Hello everyone! I'm excited to introduce a new Space I've been developing called LLM Forest Orchestra. This project converts the hidden states and attention patterns of transformer models into layered MIDI compositions. The concept draws inspiration from mushrooms and mycelial networks in forests. Fungi create underground connections linking plants and trees, establishing what some call a "wood-wide web" where signals and nutrients travel. Researchers have discovered that these exchanges form patterns resembling rhythms and pulses. When translated appropriately, these patterns can become music.
Transformers operate through remarkably similar principles: tokens share signals via hidden states and attention heads. This Space transforms those invisible information flows into notes, chords, and rhythms, treating the model as a digital forest orchestra.
🎛 Features
* Two compute modes:
- Full model operates on a Hugging Face model (defaulting to unsloth/Qwen3-14B-Base).
- Mock latents provides a CPU-friendly option that simulates tensors for immediate experimentation.
* Musical controls: You can adjust scale selection, tempo grid, velocity range, instrument/role presets, and seed randomization.
* Output: The system generates .mid files compatible with DAWs and remixing workflows.
🌌 Why?
Neural networks already resemble unusual musical instruments: signals flow through them, patterns emerge organically, and careful observation reveals hidden melodies. This is analogous to the forest's secret orchestra of mushrooms and trees.
👉 Try it
Try the Space here: Locutusque/LLM-Forest-Orchestra. I'm excited to hear the sounds you can generate. Please share your created MIDIs or remixes in the comments. Let's explore how this hidden forest of transformers can sound together. 🌳🎶
reacted to
etemiz's
post with 👍
5 months ago
Post
6287
gpt-oss-120B scored 28 (one of the lowest) on AHA leaderboard. not very human aligned model.
these kind of models are not really "free": they are costing you your freedom if you know what i mean.
these kind of models are not really "free": they are costing you your freedom if you know what i mean.
- 13 replies
reacted to
DualityAI-RebekahBogdanoff's
post with ❤️
7 months ago
Post
2214
Can AI models trained solely on 100% synthetic data achieve top-tier accuracy in real-world object detection?
👉 @sergio-sanz-rodriguez just proved it while winning Duality AI’s Synthetic-to-Real Object Detection Challenge using Falcon-generated imagery. His model achieved perfect real-world detection accuracy without a single real image in the training loop.
In this blog, Dr. Sanz walks us through his method, which includes the design and training of an advanced pipeline to achieve 100% detection accuracy.
His full technical breakdown covers:
📍 Synthetic-only training
📍 Data augmentation with an ensemble learning approach for better generalization
📍 Custom occlusion generation
📍 A Faster R-CNN model fine-tuned with Falcon generated data
📍 And much more!
The results speak for themselves!
📖 Read the blog here: https://www.duality.ai/blog/leveraging-synthetic-data-for-real-world-object-detection
Congratulations Sergio! We can't wait to see what you do next.
🔔 Ready to take on the next Synthetic-to-Real challenge? The third edition of our Kaggle competition—Multi-Instance Object Detection Challenge—is now live: https://www.kaggle.com/competitions/multi-instance-object-detection-challenge
👉 @sergio-sanz-rodriguez just proved it while winning Duality AI’s Synthetic-to-Real Object Detection Challenge using Falcon-generated imagery. His model achieved perfect real-world detection accuracy without a single real image in the training loop.
In this blog, Dr. Sanz walks us through his method, which includes the design and training of an advanced pipeline to achieve 100% detection accuracy.
His full technical breakdown covers:
📍 Synthetic-only training
📍 Data augmentation with an ensemble learning approach for better generalization
📍 Custom occlusion generation
📍 A Faster R-CNN model fine-tuned with Falcon generated data
📍 And much more!
The results speak for themselves!
📖 Read the blog here: https://www.duality.ai/blog/leveraging-synthetic-data-for-real-world-object-detection
Congratulations Sergio! We can't wait to see what you do next.
🔔 Ready to take on the next Synthetic-to-Real challenge? The third edition of our Kaggle competition—Multi-Instance Object Detection Challenge—is now live: https://www.kaggle.com/competitions/multi-instance-object-detection-challenge
- 2 replies