Tsinghua-NICS-EFC

university

https://nicsefc.ee.tsinghua.edu.cn/

thu-nics

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

HuiningYuan updated a collection 3 days ago

VPR

HuiningYuan updated a model 5 days ago

nics-efc/VPR-Tic-Tac-Toe

HuiningYuan updated a collection 5 days ago

VPR

View all activity

Papers

SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer

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

View all Papers

nics-efc 's collections 6

VPR

Verifiable Process Rewards for Agentic Reasoning

Verifiable Process Rewards for Agentic Reasoning

Paper • 2605.10325 • Published 7 days ago
nics-efc/VPR-Tic-Tac-Toe

Text Generation • 4B • Updated 5 days ago • 13
nics-efc/VPR-Sudoku

Text Generation • 4B • Updated 5 days ago • 13
nics-efc/VPR-Minesweeper

Text Generation • 4B • Updated 6 days ago • 16

TaH

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

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

Paper • 2511.08577 • Published Nov 11, 2025 • 110
nics-efc/TaH-plus-1.7B

Text Generation • 2B • Updated Nov 24, 2025 • 22 • 1
nics-efc/Standard-1.7B

Text Generation • 2B • Updated Jan 12 • 1

R2R

Collections for paper "R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing"

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

Paper • 2505.21600 • Published May 27, 2025 • 71
nics-efc/R2R_router

Token Classification • Updated Jul 14, 2025 • 1
nics-efc/R2R_Router_Training

Viewer • Updated Jun 2, 2025 • 8.19M • 314 • 4
nics-efc/R2R_query

Viewer • Updated Jul 11, 2025 • 2.93k • 35

MARSHAL

MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs 🎉 Accepted by ICLR 2026

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

Paper • 2510.15414 • Published Oct 17, 2025 • 1
nics-efc/MARSHAL-Generalist-Qwen3-4B

Text Generation • 4B • Updated Feb 11 • 30
nics-efc/MARSHAL-Generalist-Qwen3-8B

Text Generation • 8B • Updated Feb 11 • 12
nics-efc/MARSHAL-Tic-Tac-Toe-Qwen3-4B

Text Generation • 4B • Updated Feb 11 • 13

C2C

Artifacts of paper "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"

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

Paper • 2510.03215 • Published Oct 3, 2025 • 99
nics-efc/C2C_Fuser

Text Generation • Updated Dec 8, 2025 • 6
Running

Agents

2

Cache-to-Cache Communication Demo

🔗

2

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

Papers from the NICS-EFFALG Team

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

Paper • 2505.21600 • Published May 27, 2025 • 71
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

Paper • 2412.17153 • Published Dec 22, 2024 • 39
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding

Paper • 2307.15337 • Published Jul 28, 2023 • 39
DiTFastAttn: Attention Compression for Diffusion Transformer Models

Paper • 2406.08552 • Published Jun 12, 2024 • 25

VPR

Verifiable Process Rewards for Agentic Reasoning

Verifiable Process Rewards for Agentic Reasoning

Paper • 2605.10325 • Published 7 days ago
nics-efc/VPR-Tic-Tac-Toe

Text Generation • 4B • Updated 5 days ago • 13
nics-efc/VPR-Sudoku

Text Generation • 4B • Updated 5 days ago • 13
nics-efc/VPR-Minesweeper

Text Generation • 4B • Updated 6 days ago • 16

MARSHAL

MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs 🎉 Accepted by ICLR 2026

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

Paper • 2510.15414 • Published Oct 17, 2025 • 1
nics-efc/MARSHAL-Generalist-Qwen3-4B

Text Generation • 4B • Updated Feb 11 • 30
nics-efc/MARSHAL-Generalist-Qwen3-8B

Text Generation • 8B • Updated Feb 11 • 12
nics-efc/MARSHAL-Tic-Tac-Toe-Qwen3-4B

Text Generation • 4B • Updated Feb 11 • 13

TaH

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

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

Paper • 2511.08577 • Published Nov 11, 2025 • 110
nics-efc/TaH-plus-1.7B

Text Generation • 2B • Updated Nov 24, 2025 • 22 • 1
nics-efc/Standard-1.7B

Text Generation • 2B • Updated Jan 12 • 1

C2C

Artifacts of paper "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"

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

Paper • 2510.03215 • Published Oct 3, 2025 • 99
nics-efc/C2C_Fuser

Text Generation • Updated Dec 8, 2025 • 6
Running

Agents

2

Cache-to-Cache Communication Demo

🔗

2

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

R2R

Collections for paper "R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing"

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

Paper • 2505.21600 • Published May 27, 2025 • 71
nics-efc/R2R_router

Token Classification • Updated Jul 14, 2025 • 1
nics-efc/R2R_Router_Training

Viewer • Updated Jun 2, 2025 • 8.19M • 314 • 4
nics-efc/R2R_query

Viewer • Updated Jul 11, 2025 • 2.93k • 35

Papers from the NICS-EFFALG Team

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

Paper • 2505.21600 • Published May 27, 2025 • 71
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

Paper • 2412.17153 • Published Dec 22, 2024 • 39
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding

Paper • 2307.15337 • Published Jul 28, 2023 • 39
DiTFastAttn: Attention Compression for Diffusion Transformer Models

Paper • 2406.08552 • Published Jun 12, 2024 • 25

AI & ML interests

Recent Activity

Papers

Team members 15

nics-efc 's collections 6

Cache-to-Cache Communication Demo

Cache-to-Cache Communication Demo