Composer 2 Technical Report
Paper • 2603.24477 • Published • 15
AI & ML interests
machine translation
Recent Activity
View all activity
Muennighoff
submitted a
paper to Daily Papers about 1 month ago
lintang
authored a
paper about 2 months ago
JuliaKreutzerCohere
updated a
dataset about 2 months ago
JuliaKreutzerCohere
published a
dataset about 2 months ago
albertvillanova
posted an update 2 months ago
Post
2585
🚀 TRL v0.29.0 introduces trl-training: an agent-native training skill.
This makes the TRL CLI a structured, agent-readable capability, allowing AI agents to reliably execute training workflows such as:
- Supervised Fine-Tuning (SFT)
- Direct Preference Optimization (DPO)
- Group Relative Policy Optimization (GRPO)
We’re excited to see what the community builds on top of this.
If you’re working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! 🤗
The future of ML tooling is agent-native.
🔗 https://github.com/huggingface/trl/releases/tag/v0.29.0
This makes the TRL CLI a structured, agent-readable capability, allowing AI agents to reliably execute training workflows such as:
- Supervised Fine-Tuning (SFT)
- Direct Preference Optimization (DPO)
- Group Relative Policy Optimization (GRPO)
We’re excited to see what the community builds on top of this.
If you’re working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! 🤗
The future of ML tooling is agent-native.
🔗 https://github.com/huggingface/trl/releases/tag/v0.29.0
albertvillanova
posted an update 3 months ago
Post
1910
5 years already working in democratizing AI 🤗
Grateful to be part of such an awesome team making it happen every day.
Grateful to be part of such an awesome team making it happen every day.
dipteshkanojia
authored 13
papers 6 months ago
Airavata: Introducing Hindi Instruction-tuned LLM
Paper • 2401.15006 • Published • 4
PLOD: An Abbreviation Detection Dataset for Scientific Documents
Paper • 2204.12061 • Published • 1
HiNER: A Large Hindi Named Entity Recognition Dataset
Paper • 2204.13743 • Published
AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis
Paper • 2406.08920 • Published • 7
Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content?
Paper • 2410.06338 • Published
PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation
Paper • 2412.07754 • Published
When LLMs Struggle: Reference-less Translation Evaluation for Low-resource Languages
Paper • 2501.04473 • Published
Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content
Paper • 2502.07138 • Published
CAMU: Context Augmentation for Meme Understanding
Paper • 2504.17902 • Published
BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English
Paper • 2412.04726 • Published
GCDance: Genre-Controlled 3D Full Body Dance Generation Driven By Music
Paper • 2502.18309 • Published
The Mind's Eye: A Multi-Faceted Reward Framework for Guiding Visual Metaphor Generation
Paper • 2508.18569 • Published
CreoleVal: Multilingual Multitask Benchmarks for Creoles
Paper • 2310.19567 • Published
albertvillanova
posted an update 9 months ago
Post
4618
Latest smolagents release supports GPT-5: build agents that think, plan, and act.
⚡ Upgrade now and put GPT-5 to work!
⚡ Upgrade now and put GPT-5 to work!
- 1 reply