Weiwei Sun @sunweiwei12

PhD student @LTIatCMU | Ex @VectorInst @Baidu_Inc @ShandongU @ic4ai | Working on NLP, LLM, IR sunnweiwei.github.io Pittsburgh, PA Joined June 2021

Tweets

80
Followers

244
Following

181
Likes

2K

Xinyu Ma @xinyuma8

2 months ago

Excited to share ReasonRank—a listwise reranker that reasons before it ranks. On complex queries, ReasonRank-32B is #1 on the BRIGHT reasoning-intensive leaderboard (Aug 9, 2025; +.6 vs. strong baselines). Working with Wenhan, @sunweiwei12, etc.

3 9 69 7K 45

Download Image

Weiwei Sun @sunweiwei12

3 months ago

Most AI agents are tested in a bubble. But real ML breakthroughs happen in communities. We introduce CoMind, an research agent that learns from community knowledge. 📊 CoMind outperforms ~70% human teams in a CVPR 2025 workshop competition. 🧵👇

2 4 14 2K 5

Download Image

Shanda Li 黎善达 @Shanda_Li_2000

4 months ago

This work is done with amazing @__tm__157, @JunhongShen1, @sunweiwei12, @risteski_a, Yiming Yang, and @atalwalkar. We are excited about applying LLM techniques to solve more challenging PDEs in the future! 📝Paper: arxiv.org/abs/2505.08783 ⭐Code: github.com/LithiumDA/Code…

1 1 6 578 3

Shanda Li 黎善达 @Shanda_Li_2000

4 months ago

Can LLM solve PDEs? 🤯 We present CodePDE, a framework that uses LLMs to automatically generate solvers for PDE and outperforms human implementation! 🚀 CodePDE demonstrates the power of inference-time algorithms and scaling for PDE solving. More in 🧵: #ML4PDE #AI4Science

4 12 68 17K 24

Download Image

Weiwei Sun @sunweiwei12

4 months ago

Thrilled to introduce FrontierCO — a benchmark of real, challenging (some unsolved) combinatorial optimization problems. It’s built to push frontier AI beyond toy tasks and toward advancing the boundaries of human problem-solving! Paper: arxiv.org/abs/2505.16952

Shengyu Feng @ShawnSYFeng

4 months ago

1 10 32 4K 5

Download Image

0 2 10 845 0

Shengyu Feng @ShawnSYFeng

4 months ago

🌟Get rid of the evaluation on synthetic toy problems and advance human intelligence like #AlphaEvolve! 🚀 Introducing FrontierCO — our new Machine Learning for Combinatorial Optimization benchmark featuring high-quality NP-hard instances from real-world applications and…

1 10 32 4K 5

Download Image

Yiqun Chen @chenyiqun223336

8 months ago

We invite you to explore our latest work on RAG. We conceptualize RAG as a multi-agent collaboration task, aiming to align and unify the optimization objectives of its various modules with the ultimate goal of generating high-quality answers.

elvis @omarsar0

8 months ago

8 69 271 22K 239

Download Image

1 1 4 597 0

Yiqun Chen @chenyiqun223336

8 months ago

This new approach for RAG modeling and optimization, MMOA-RAG, treats RAG as a multi-agent collaboration task. It uses MARL to simultaneously optimize multiple modules, aligning their objectives with the final goal of generating high-quality responses.

Sumit @_reachsumit

8 months ago

0 2 9 1K 6

0 1 2 349 0

Sumit @_reachsumit

8 months ago

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning Optimizes multiple RAG components jointly through multi-agent RL to align their goals toward generating high-quality answers. 📝 arxiv.org/abs/2501.15228 👨🏽‍💻 github.com/chenyiqun/MMOA…

0 2 9 1K 6

elvis @omarsar0

8 months ago

Improving RAG through Multi-Agent RL This work treats RAG as a multi-agent cooperative task to improve answer generation quality. It models RAG components like query rewriting, document selection, and answer generation as reinforcement learning agents working together toward…

8 69 271 22K 239

Download Image

Weiwei Sun @sunweiwei12

11 months ago

I will be presenting our paper “MAIR: A Massive Benchmark for Evaluating Instructed Retrieval” at #EMNLP2024! Date: Tuesday, Nov 12 Time: 14:00-15:30 Session 03: Resources and Evaluation 1 Paper: arxiv.org/abs/2410.10127 See you there!