SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
Paper • 2605.31433 • Published • 9
AI & ML interests
A one-year long research workshop on large language models: the Summer of Language Models 21 🌸
Recent Activity
View all activity
pminervini
submitted a
paper to Daily Papers about 4 hours ago
shubhamagarwal92
authored 11
papers about 1 month ago
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks
Paper • 2412.04626 • Published • 14
LitLLM: A Toolkit for Scientific Literature Review
Paper • 2402.01788 • Published
History for Visual Dialog: Do we really need it?
Paper • 2005.07493 • Published
Chitrarth: Bridging Vision and Language for a Billion People
Paper • 2502.15392 • Published
LitLLMs, LLMs for Literature Review: Are we there yet?
Paper • 2412.15249 • Published • 2
IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs
Paper • 2511.04727 • Published
VoiceAgentBench: Are Voice Assistants ready for agentic tasks?
Paper • 2510.07978 • Published
Seeing Straight: Document Orientation Detection for Efficient OCR
Paper • 2511.04161 • Published
Designing Production-Scale OCR for India: Multilingual and Domain-Specific Systems
Paper • 2602.16430 • Published
Chitranuvad: Adapting Multi-Lingual LLMs for Multimodal Translation
Paper • 2502.20420 • Published
MUTANT: A Recipe for Multilingual Tokenizer Design
Paper • 2511.03237 • Published
Muennighoff
submitted a
paper to Daily Papers 2 months ago
RTT1
authored a
paper 3 months ago
pminervini
authored 3
papers 3 months ago
[SPAM] Deleted
3
#289 opened 3 months ago
by 
sarthak-saxena
mmosbach
authored a
paper 3 months ago
Post
244
Good news! Ulysses Sequence Parallelism from the Snowflake AI Research and the Deepspeed teams has been integrated into
HuggingFace Trainer, Accelerate and TRL
For extensive details please see this writeup:
https://huggingface.co/blog/ulysses-sp
Thanks a lot to Kashif Rasul for helping make it happen. Also the others in the HF team who helped with integration.
HuggingFace Trainer, Accelerate and TRL
For extensive details please see this writeup:
https://huggingface.co/blog/ulysses-sp
Thanks a lot to Kashif Rasul for helping make it happen. Also the others in the HF team who helped with integration.