Tsinghua-NICS-EFC

university

http://nics-effalg.com/

thu-nics

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

HuiningYuan updated a model 2 days ago

nics-efc/MARSHAL-Kuhn-Poker-Qwen3-4B

HuiningYuan updated a model 2 days ago

nics-efc/MARSHAL-Mini-Hanabi-Qwen3-4B

HuiningYuan updated a model 2 days ago

nics-efc/MARSHAL-Generalist-Qwen3-8B

View all activity

Papers

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

Cache-to-Cache: Direct Semantic Communication Between Large Language Models

View all Papers

Collections 5

View 5 collections

spaces 2

Cache-to-Cache Communication Demo

🔗

Compare Single, Text-to-Text, and Cache-to-Cache inference

JuggleRL

🚀

Mastering Ball Juggling with a Quadrotor via Deep

models 10

datasets 4

nics-efc/R2R_query

Viewer • Updated Jul 11 • 2.93k • 72

nics-efc/R2R_Router_Training

Viewer • Updated Jun 2 • 8.19M • 237 • 2

nics-efc/MoA_Long_HumanQA

Viewer • Updated Jun 19, 2024 • 3.5k • 69 • 4

nics-efc/MoA_Long_Retrieval

Viewer • Updated Jun 19, 2024 • 4.4k • 27 • 4

Tsinghua-NICS-EFC

AI & ML interests

Recent Activity

Papers

Collections 5

MARS: Reinforcing Multi-Agent Reasoning of LLMs through Self-Play in Strategic Games

nics-efc/MARSHAL-Generalist-Qwen3-4B

nics-efc/MARSHAL-Generalist-Qwen3-8B

nics-efc/MARSHAL-Tic-Tac-Toe-Qwen3-4B

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

nics-efc/TaH-plus-1.7B

MARS: Reinforcing Multi-Agent Reasoning of LLMs through Self-Play in Strategic Games

nics-efc/MARSHAL-Generalist-Qwen3-4B

nics-efc/MARSHAL-Generalist-Qwen3-8B

nics-efc/MARSHAL-Tic-Tac-Toe-Qwen3-4B

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

nics-efc/TaH-plus-1.7B

spaces 2

Cache-to-Cache Communication Demo

JuggleRL

models 10

nics-efc/MARSHAL-Kuhn-Poker-Qwen3-4B

nics-efc/MARSHAL-Mini-Hanabi-Qwen3-4B

nics-efc/MARSHAL-Generalist-Qwen3-8B

nics-efc/MARSHAL-Generalist-Qwen3-4B

nics-efc/MARSHAL-Tic-Tac-Toe-Qwen3-4B

nics-efc/TaH-plus-1.7B

nics-efc/C2C_Fuser

nics-efc/R2R_router_collections

nics-efc/R2R_router

nics-efc/MixDQ

datasets 4

nics-efc/R2R_query

nics-efc/R2R_Router_Training

nics-efc/MoA_Long_HumanQA

nics-efc/MoA_Long_Retrieval

AI & ML interests

Recent Activity

Papers

Team members 14

Collections 5

spaces 2 Sort: Recently updated

Cache-to-Cache Communication Demo

JuggleRL

models 10 Sort: Recently updated

datasets 4 Sort: Recently updated

spaces 2

models 10

datasets 4