ZeroGPU Explorers

community

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

ozayezerceli authored a paper 3 days ago

TurkEmbed: Turkish Embedding Model on NLI & STS Tasks

ozayezerceli authored a paper 3 days ago

TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task

zubingou authored a paper 10 days ago

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

View all activity

Aurelien-Morgan

posted an update about 24 hours ago

Post

123

Hey, I went to Hangzhou to talk about retrain-pipelines at the GOSIM Foundation's conference last september.
The recording just got released. Go check it out !
https://www.youtube.com/watch?v=nmrMachM5aM
Slides are there :
https://docs.google.com/presentation/d/1hnAzHJ0SbeAOtGJir-iH84RBtXT1OxVT/

IliaLarchenko

posted an update 1 day ago

Post

111

🏆 BEHAVIOR Challenge 1st Place – Solution Summary

My team recently won 1st place in the BEHAVIOR Challenge at NeurIPS.
The competition focused on training a single policy to complete 50 long-horizon household tasks in simulation.

We built an end-to-end policy based on Pi0.5 with a bunch of custom modifications. Everything is open-sourced, and it should be useful for anyone exploring VLAs or adapting them to specific tasks.

Key Architecture Changes:
- Replaced language model with 50 trainable task embeddings (no text at all)
- Correlated noise for Flow Matching: ϵ ∼ N(0, 0.5I + 0.5Σ) using dataset action covariance
- Learnable mixed-layer attention: each action expert layer attends to a trainable mix of all VLM layers
- System 2 stage tracking: model predicts task stage, we smooth it with voting and feed it back as context

Training:
- Multi-sample Flow Matching: 15 FM samples per VLM pass to reduce gradient variance
- Delta action space + per-timestamp normalization
- FAST auxiliary loss and stage prediction loss
- Trained on 224×224 RGB + proprioception only
- We use 4 fine-tuned checkpoints, all derived from a multi-task model trained on all 50 tasks

Inference Optimizations:
- Soft inpainting: predict 30 actions, execute 26, use 4 as an input for the next chunk
- Correlation-aware guidance of inpainting to keep action chunks smooth
- 1.3× speedup via cubic spline compression
- General correction rule: reopen gripper after failed grasps

🔗 Code and Models:
- Code: https://github.com/IliaLarchenko/behavior-1k-solution
- Weights: IliaLarchenko/behavior_submission
- Paper: Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge (2512.06951)

IliaLarchenko

authored a paper 2 days ago

Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge

Paper • 2512.06951 • Published 4 days ago

ozayezerceli

authored 2 papers 3 days ago

TurkEmbed: Turkish Embedding Model on NLI & STS Tasks

Paper • 2511.08376 • Published 30 days ago • 2

TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task

Paper • 2511.07595 • Published about 1 month ago • 1

PeterL1n

authored a paper 9 days ago

Adversarial Flow Models

Paper • 2511.22475 • Published 14 days ago • 21

PeterL1n

authored a paper 10 days ago

Adversarial Flow Models

Paper • 2511.22475 • Published 14 days ago • 21

Lin-Chen

authored a paper 10 days ago

DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action

Paper • 2511.22134 • Published 14 days ago • 21

PeterL1n

authored a paper 10 days ago

Adversarial Flow Models

Paper • 2511.22475 • Published 14 days ago • 21

asigalov61

posted an update 16 days ago

Post

3385

🔥🎵 ➕ 🖹 🔥Check out my new large-scale MIDI + Lyrics dataset!!!

asigalov61/Lyrics-MIDI-Dataset

~179k MIDIs with corresponding Lyrics to play with!!! 🤗

If you liked the dataset, please ❤️

Any feedback and/or suggestions are also appreciated 🤗