Sea AI Lab

company

Verified

https://sail.sea.com

AI & ML interests

None defined yet.

Papers

TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size

Rethinking the Trust Region in LLM Reinforcement Learning

View all Papers

sail 's papers 13

Submitted by

Stefan Lionar

TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size

sail

Submitted by

Penghui Qi

Rethinking the Trust Region in LLM Reinforcement Learning

sail

Submitted by

Xinyi Wan

Revisiting Parameter Server in LLM Post-Training

sail

Submitted by

Penghui Qi

Defeating the Training-Inference Mismatch via FP16

sail

Submitted by

Tianyu Pang

Imperceptible Jailbreaking against Large Language Models

sail

Submitted by

taesiri

GEM: A Gym for Agentic LLMs

sail

Submitted by

Tianyu Pang

Language Models Can Learn from Verbal Feedback Without Scalar Rewards

sail

Submitted by

Tianyu Pang

Variational Reasoning for Language Models

sail

Submitted by

Stefan Lionar

TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

sail

Submitted by

Longxu Dou

Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs

sail

Sailor: Open Language Models for South-East Asia

sail

Submitted by

AK

LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

sail