Wild3R: Feed-Forward 3D Gaussian Splatting from Unconstrained Sparse Photo Collection
Paper • 2606.11894 • Published
ZeroGPU Explorers
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
mapooon
authored a
paper 15 days ago
Post
640
Follow my X account — I'll be sharing thoughts and findings on building open-source AI Agent projects, Agent Memory, and Observability.
Thanks for connecting!
https://x.com/code_hiyouga
Thanks for connecting!
https://x.com/code_hiyouga
Lakonik
authored a
paper about 2 months ago
Lakonik
submitted a
paper to Daily Papers about 2 months ago
Post
3399
A small model that struggled against a random opponent now beats GPT-5-mini at tic-tac-toe
I took LiquidAI/LFM2-2.6B and trained it through play.
🧑🍳 Here's how:
1️⃣ Build a solid RL env with Verifiers (Prime Intellect)
2️⃣ Generate synthetic data: <200 games sampled from GPT-5-mini playing in the env
3️⃣ SFT warm-up to teach format
4️⃣ Group-based RL (CISPO) against opponents making 20-70% random moves
5️⃣ RL again with stronger opponents (0-25% random moves) + 1.25 temperature to push exploration and shake off suboptimal strategies
Done! Beats GPT-5-mini 🏆
---
🎮 Play against the model: anakin87/LFM2-2.6B-mr-tictactoe
🤗 Model: anakin87/LFM2-2.6B-mr-tictactoe
📚 Walkthrough/course: https://github.com/anakin87/llm-rl-environments-lil-course
🤗 Dataset and checkpoints: https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
I took LiquidAI/LFM2-2.6B and trained it through play.
🧑🍳 Here's how:
1️⃣ Build a solid RL env with Verifiers (Prime Intellect)
2️⃣ Generate synthetic data: <200 games sampled from GPT-5-mini playing in the env
3️⃣ SFT warm-up to teach format
4️⃣ Group-based RL (CISPO) against opponents making 20-70% random moves
5️⃣ RL again with stronger opponents (0-25% random moves) + 1.25 temperature to push exploration and shake off suboptimal strategies
Done! Beats GPT-5-mini 🏆
---
🎮 Play against the model: anakin87/LFM2-2.6B-mr-tictactoe
🤗 Model: anakin87/LFM2-2.6B-mr-tictactoe
📚 Walkthrough/course: https://github.com/anakin87/llm-rl-environments-lil-course
🤗 Dataset and checkpoints: https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
Post
107
Local Gemma 4 agent 💎🕵️🗺️
drop in a mysterious map, get the location, live weather, and top spots to visit
I've been exploring what google/gemma-4-E4B-it can do in a local agentic setup and put together a 📓 𝙣𝙤𝙩𝙚𝙗𝙤𝙤𝙠 with Gemma + Haystack AI Framework covering 4 demos.
📓 https://t.ly/04Ty5
Another interesting one is the 𝗚𝗶𝘁𝗛𝘂𝗯 𝗔𝗴𝗲𝗻𝘁.
I initially tried to load all tools from the GitHub MCP server, quickly filling the context available on Colab -> unusable, forgetful agent ❌
Then I used the 𝗦𝗲𝗮𝗿𝗰𝗵𝗮𝗯𝗹𝗲 𝗧𝗼𝗼𝗹𝘀𝗲𝘁 🔎 🧰
It dynamically discovers the right tools from the GitHub MCP server on the fly, loading only what it actually needs for the task at hand, keeping context lean.
Now it actually works.
The notebook also contains
💎 Multimodal weather agent: the mystery map demo above
💎 Visual Question Answering from a paper
💎 RAG on Rock music
drop in a mysterious map, get the location, live weather, and top spots to visit
I've been exploring what google/gemma-4-E4B-it can do in a local agentic setup and put together a 📓 𝙣𝙤𝙩𝙚𝙗𝙤𝙤𝙠 with Gemma + Haystack AI Framework covering 4 demos.
📓 https://t.ly/04Ty5
Another interesting one is the 𝗚𝗶𝘁𝗛𝘂𝗯 𝗔𝗴𝗲𝗻𝘁.
I initially tried to load all tools from the GitHub MCP server, quickly filling the context available on Colab -> unusable, forgetful agent ❌
Then I used the 𝗦𝗲𝗮𝗿𝗰𝗵𝗮𝗯𝗹𝗲 𝗧𝗼𝗼𝗹𝘀𝗲𝘁 🔎 🧰
It dynamically discovers the right tools from the GitHub MCP server on the fly, loading only what it actually needs for the task at hand, keeping context lean.
Now it actually works.
The notebook also contains
💎 Multimodal weather agent: the mystery map demo above
💎 Visual Question Answering from a paper
💎 RAG on Rock music
Post
10412
How LLM training with RL Environments works?
It all starts with 𝗥𝗲𝗶𝗻𝗳𝗼𝗿𝗰𝗲𝗺𝗲𝗻𝘁 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗩𝗲𝗿𝗶𝗳𝗶𝗮𝗯𝗹𝗲 𝗥𝗲𝘄𝗮𝗿𝗱𝘀
- question asked
- model generates reasoning + answer
- answer checked against ground truth
- reward drives RL training
In this setup, the environment is simple: fixed questions and answers, rollout logic, reward(s)
Consider a more complex tic-tac-toe env ❌⭕
It adds:
- dynamic game generation/handling
- tunable opponent skill
- multi-turn interactions
(envs can also include tools)
---
What happens at training?
We use 𝗚𝗿𝗼𝘂𝗽 𝗥𝗲𝗹𝗮𝘁𝗶𝘃𝗲 𝗣𝗼𝗹𝗶𝗰𝘆 𝗢𝗽𝘁𝗶𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻 with a tic-tac-toe env
No critic model needed, the group is the baseline
Simpler than PPO
1️⃣ Rollout generation: from the same board, model plays N games via sampling
2️⃣ Each game scored with deterministic rewards (win, format, ...)
3️⃣ Mean score computed across the group
4️⃣ Each rollout's advantage = its score minus the group mean
5️⃣ Model updated to favor trajectories above baseline
🔁 Repeat
For a deep dive, check out
🌱 https://github.com/anakin87/llm-rl-environments-lil-course
a free hands-on course on RL environments for LLMs
It all starts with 𝗥𝗲𝗶𝗻𝗳𝗼𝗿𝗰𝗲𝗺𝗲𝗻𝘁 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗩𝗲𝗿𝗶𝗳𝗶𝗮𝗯𝗹𝗲 𝗥𝗲𝘄𝗮𝗿𝗱𝘀
- question asked
- model generates reasoning + answer
- answer checked against ground truth
- reward drives RL training
In this setup, the environment is simple: fixed questions and answers, rollout logic, reward(s)
Consider a more complex tic-tac-toe env ❌⭕
It adds:
- dynamic game generation/handling
- tunable opponent skill
- multi-turn interactions
(envs can also include tools)
---
What happens at training?
We use 𝗚𝗿𝗼𝘂𝗽 𝗥𝗲𝗹𝗮𝘁𝗶𝘃𝗲 𝗣𝗼𝗹𝗶𝗰𝘆 𝗢𝗽𝘁𝗶𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻 with a tic-tac-toe env
No critic model needed, the group is the baseline
Simpler than PPO
1️⃣ Rollout generation: from the same board, model plays N games via sampling
2️⃣ Each game scored with deterministic rewards (win, format, ...)
3️⃣ Mean score computed across the group
4️⃣ Each rollout's advantage = its score minus the group mean
5️⃣ Model updated to favor trajectories above baseline
🔁 Repeat
For a deep dive, check out
🌱 https://github.com/anakin87/llm-rl-environments-lil-course
a free hands-on course on RL environments for LLMs
- 2 replies
Why doesn't anyone host llms in zerogpu spaces?
8
#172 opened 3 months ago
by 
Reality123b
Why doesn't anyone host llms in zerogpu spaces?
8
#172 opened 3 months ago
by Reality123b
Post
1625
Your RL environment is an SFT data factory 🏭
In LLM post-training it's common to do Supervised Fine-Tuning warm-up before Reinforcement Learning.
When teaching a new task, RL needs some signal to amplify and SFT builds a good initial basis, for example by teaching format.
If you've built an RL env, generating SFT synthetic data is basically free.
An env already has: task data, rollout logic, rewards.
1️⃣ pick a strong model
2️⃣ run it through the env
3️⃣ filter rollouts by reward
works out of the box with Verifiers (Prime Intellect) and Atropos (Nous Research)
🧑💻 Example: https://github.com/anakin87/llm-rl-environments-lil-course/blob/main/chapters/05.md
In LLM post-training it's common to do Supervised Fine-Tuning warm-up before Reinforcement Learning.
When teaching a new task, RL needs some signal to amplify and SFT builds a good initial basis, for example by teaching format.
If you've built an RL env, generating SFT synthetic data is basically free.
An env already has: task data, rollout logic, rewards.
1️⃣ pick a strong model
2️⃣ run it through the env
3️⃣ filter rollouts by reward
works out of the box with Verifiers (Prime Intellect) and Atropos (Nous Research)
🧑💻 Example: https://github.com/anakin87/llm-rl-environments-lil-course/blob/main/chapters/05.md
Post
4193
🌀 Let LLMs wander - Engineering RL Environments
Reinforcement Learning Environments are little worlds
where models can act, get rewards, and learn.
I've been exploring how to design them, figuring out what works and what doesn't.
If you want to learn how to build them, I recorded a practical intro video.
You'll also see how to turn Liquid AI LFM2-2.6B into a Tic-tac-toe master 🙂
🎥 Engineering RL Environments video: https://www.youtube.com/watch?v=71V3fTaUp2Q
---
🌱 LLM RL Environments Lil Course: https://github.com/anakin87/llm-rl-environments-lil-course
🤗🕹️ Play against the trained model: anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
Reinforcement Learning Environments are little worlds
where models can act, get rewards, and learn.
I've been exploring how to design them, figuring out what works and what doesn't.
If you want to learn how to build them, I recorded a practical intro video.
You'll also see how to turn Liquid AI LFM2-2.6B into a Tic-tac-toe master 🙂
🎥 Engineering RL Environments video: https://www.youtube.com/watch?v=71V3fTaUp2Q
---
🌱 LLM RL Environments Lil Course: https://github.com/anakin87/llm-rl-environments-lil-course
🤗🕹️ Play against the trained model: anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
Post
3314
📣 I just published a free course on Reinforcement Learning Environments for Language Models!
📌 COURSE: https://github.com/anakin87/llm-rl-environments-lil-course
Over the past year, we've seen a shift in LLM Post-Training.
Previously, Supervised Fine-Tuning was the most important part: making models imitate curated Question-Answer pairs.
Now we also have Reinforcement Learning with Verifiable Rewards. With techniques like GRPO, models can learn through trial and error in dynamic environments. They can climb to new heights without relying on expensively prepared data.
But what actually are these environments in practice❓ And how do you build them effectively❓
Fascinated by these concepts, I spent time exploring this space through experiments, post-training Small Language Models.
I've packaged everything I learned into this short course.
What you'll learn
🔹 Agents, Environments, and LLMs: how to map Reinforcement Learning concepts to the LLM domain
🔹 How to use Verifiers (open-source library by Prime Intellect) to build RL environments as software artifacts
🔹 Common patterns: How to build single-turn, multi-turn, and tool-use environments
🔹 Hands-on: turn a small language model (LFM2-2.6B by LiquidAI) into a Tic Tac Toe master
🔸 Build the game Environment
🔸 Use it to generate synthetic data for SFT warm-up
🔸 Group-based Reinforcement Learning
If you're interested in building "little worlds" where LLMs can learn, this course is for you.
---
🤗🕹️ Play against the trained model: anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
📌 COURSE: https://github.com/anakin87/llm-rl-environments-lil-course
Over the past year, we've seen a shift in LLM Post-Training.
Previously, Supervised Fine-Tuning was the most important part: making models imitate curated Question-Answer pairs.
Now we also have Reinforcement Learning with Verifiable Rewards. With techniques like GRPO, models can learn through trial and error in dynamic environments. They can climb to new heights without relying on expensively prepared data.
But what actually are these environments in practice❓ And how do you build them effectively❓
Fascinated by these concepts, I spent time exploring this space through experiments, post-training Small Language Models.
I've packaged everything I learned into this short course.
What you'll learn
🔹 Agents, Environments, and LLMs: how to map Reinforcement Learning concepts to the LLM domain
🔹 How to use Verifiers (open-source library by Prime Intellect) to build RL environments as software artifacts
🔹 Common patterns: How to build single-turn, multi-turn, and tool-use environments
🔹 Hands-on: turn a small language model (LFM2-2.6B by LiquidAI) into a Tic Tac Toe master
🔸 Build the game Environment
🔸 Use it to generate synthetic data for SFT warm-up
🔸 Group-based Reinforcement Learning
If you're interested in building "little worlds" where LLMs can learn, this course is for you.
---
🤗🕹️ Play against the trained model: anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
- 1 reply
manchery
authored a
paper 3 months ago
Post
2775
Avatars are everywhere, but here is the reality behind full-system marketing automation. 🚀
Many see "Madame AI" simply as an AI news presenter. She is far deeper than that. Madame AI is a Real-time Agentic AI Assistant we developed to orchestrate entire workflows for marketing and professional media. She manages UGC (User-Generated Content), understands marketing system automation intuitively, and handles complex media tasks.
We have solved the character consistency and high production cost bottlenecks that traditionally required immense training and time. By precisely orchestrating every computational step behind videos and branded designs, we have fully automated the pipeline and significantly reduced costs.
This capability is built on our extensive experience managing large-scale automation projects with complex requirement documentation (PRD).
Grabclip is our public portal and the practical result of that journey. It is the interface where "Madame AI" acts as the intelligent engine.
We have spent three years building this pipeline with a clear goal: a 100% local, end-to-end solution that operates despite external restrictions.
See the live example on YouTube (our fast-paced AI news podcast with Madame AI) and try the automation portal yourself👇
📺 The Playlist: https://www.youtube.com/playlist?list=PLwEbW4bdYBSCVSziFfJYq4zXop_cyHquO
🌐 Our Portal (Grabclip) — The first practical step in our pipeline: https://grabclip.bilsimaging.com/
hashtag#AgenticAI hashtag#VirtualInfluencer hashtag#FutureOfWork hashtag#GenerativeAI hashtag#TunisiaTech hashtag#MarketingAutomation hashtag#100PercentLocal hashtag#OSMedia hashtag#Grabclip hashtag#RealTimeAssistant hashtag#UGC hashtag#ProfessionalMedia hashtag#TunisiaAI
Many see "Madame AI" simply as an AI news presenter. She is far deeper than that. Madame AI is a Real-time Agentic AI Assistant we developed to orchestrate entire workflows for marketing and professional media. She manages UGC (User-Generated Content), understands marketing system automation intuitively, and handles complex media tasks.
We have solved the character consistency and high production cost bottlenecks that traditionally required immense training and time. By precisely orchestrating every computational step behind videos and branded designs, we have fully automated the pipeline and significantly reduced costs.
This capability is built on our extensive experience managing large-scale automation projects with complex requirement documentation (PRD).
Grabclip is our public portal and the practical result of that journey. It is the interface where "Madame AI" acts as the intelligent engine.
We have spent three years building this pipeline with a clear goal: a 100% local, end-to-end solution that operates despite external restrictions.
See the live example on YouTube (our fast-paced AI news podcast with Madame AI) and try the automation portal yourself👇
📺 The Playlist: https://www.youtube.com/playlist?list=PLwEbW4bdYBSCVSziFfJYq4zXop_cyHquO
🌐 Our Portal (Grabclip) — The first practical step in our pipeline: https://grabclip.bilsimaging.com/
hashtag#AgenticAI hashtag#VirtualInfluencer hashtag#FutureOfWork hashtag#GenerativeAI hashtag#TunisiaTech hashtag#MarketingAutomation hashtag#100PercentLocal hashtag#OSMedia hashtag#Grabclip hashtag#RealTimeAssistant hashtag#UGC hashtag#ProfessionalMedia hashtag#TunisiaAI
mapooon
authored a
paper 3 months ago
MykolaL
authored 3
papers 3 months ago
manchery
authored a
paper 4 months ago
sayakpaul
authored a
paper 4 months ago