Mohsen Fayyaz @mohsen_fayyaz

CS PhD Student @ UCLA #NLProc #MachineLearning mohsenfayyaz.github.io Los Angeles, CA Joined April 2018

Tweets

32
Followers

262
Following

456
Likes

2K

Violet Peng @VioletNPeng

2 weeks ago

One of my most exciting results lately! We identify experts in MoE models for properties like safety and faithfulness, and steer them to improve/hurt model faithfulness and safety. Most shockingly, with stearMoE, we can jailbreak 100% safety guardrails for open models. Details 👇

Mohsen Fayyaz @mohsen_fayyaz

3 weeks ago

5 23 127 35K 95

Download Video

5 34 259 30K 162

Violet Peng @VioletNPeng

5 months ago

@mohsen_fayyaz's recent work showed several critical issues of dense retrievers favoring spurious correlations over knowledge, which makes RAG particularly vulnerable to adversarial examples. Check out more details 👇

Mohsen Fayyaz @mohsen_fayyaz

5 months ago

2 6 28 2K 2

0 2 7 620 0

Mohsen Fayyaz @mohsen_fayyaz

5 months ago

Now accepted to #ACL2025 main conference! 🎉

Mohsen Fayyaz @mohsen_fayyaz

6 months ago

Now accepted to #ACL2025 main conference! 🎉

2 5 41 8K 14

2 6 28 2K 2

Rohan Paul @rohanpaul_ai

6 months ago

Dense retrieval models in Retrieval Augmented Generation systems often prioritize superficial document features, overlooking actual answer relevance. This inefficiency arises from biases in retrievers. This paper addresses this by using controlled experiments based on Re-DocRED…

0 6 16 2K 10

Download Image

Wenbo Hu @gordonhu608

8 months ago

Excited to share MRAG-Bench is accepted at #ICLR2025 🇸🇬. The image corpus is a rich source of information, and extracting knowledge from it can often be more advantageous than from a text corpus. We study how MLLMs can utilize vision-centric multimodal knowledge. More in our…

Wenbo Hu @gordonhu608

12 months ago

4 31 98 20K 42

Download Image

0 3 33 3K 0

Wenbo Hu @gordonhu608

12 months ago

🚀Introducing MRAG-Bench: How do Large Vision-Language Models utilize vision-centric multimodal knowledge? 🤔Previous multimodal knowledge QA benchmarks can mainly be solved by retrieving text knowledge.💥We focus on scenarios where retrieving knowledge from image corpus is more…

4 31 98 20K 42

Download Image

Pan Lu @lupantech

a year ago

Spent a fantastic weekend at Lake Arrowhead with the @uclanlp group! ❄️🏔️⬆️ Enjoyed scenic drives, delicious meals, engaging conversations, and brainstorming sessions. Truly inspiring! 🚗🥘😋💬 🖼️🧠💡

2 6 67 8K 2

Download Image

Ali Modarressi @AModarressi

2 years ago

Check out our (w/ @mohsen_fayyaz, @AghazadeehEhsan, @yyaghoobzadeh & @tpilehvar) #ACL2023 paper “DecompX: Explaining Transformers Decisions by Propagating Token Decomposition” 📽️ Video, 💻 Code, Demo & 📄 Paper: github.com/mohsenfayyaz/D… arxiv.org/abs/2306.02873 (🧵1/4)