Beijing Academy of Artificial Intelligence

non-profit

https://www.baai.ac.cn/english.html

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

cfli updated a model about 5 hours ago

cfli updated a collection about 17 hours ago

cfli published a model about 17 hours ago

View all activity

Papers

CoWindow Attention: Full Causal Coverage Is a Collective Property

MassAlloc Attention: Let Attention Allocate Its Own Compute

View all Papers

BAAI 's papers 27

Submitted by

Loser Cheems

CoWindow Attention: Full Causal Coverage Is a Collective Property

BAAI

Beijing Academy of Artificial Intelligence

Submitted by

Loser Cheems

MassAlloc Attention: Let Attention Allocate Its Own Compute

BAAI

Beijing Academy of Artificial Intelligence

Submitted by

Yuyang Hu

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

BAAI

Beijing Academy of Artificial Intelligence

Submitted by

XiaofengShi

Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization

BAAI

Beijing Academy of Artificial Intelligence

2

Submitted by

XiaofengShi

Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge

BAAI

Beijing Academy of Artificial Intelligence

2

Submitted by

zhengliu

AREX: Towards a Recursively Self-Improving Agent for Deep Research

BAAI

Beijing Academy of Artificial Intelligence

Submitted by

XiaofengShi

ChartWalker: Benchmarking the Cross-Chart RAG Task

BAAI

Beijing Academy of Artificial Intelligence

Submitted by

Yuchi Wang

When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents

BAAI

Beijing Academy of Artificial Intelligence

Submitted by

Börje Karlsson

ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control

BAAI

Beijing Academy of Artificial Intelligence

6

Submitted by

Kun Luo

AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

BAAI

Beijing Academy of Artificial Intelligence

Submitted by

JiaQi Wang

UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models

BAAI

Beijing Academy of Artificial Intelligence

Submitted by

Loser Cheems

OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale

BAAI

Beijing Academy of Artificial Intelligence