Jing-Jing Li
@drjingjing2026
Followers
2K
Following
1K
Statuses
147
PhD student in computational neuroscience @UCBerkeley with @ccnlab. Previously CS @Cornell. Intern @allen_ai. Intelligence and learning. Views my own.
Berkeley, CA
Joined January 2021
šØ New preprint from my internship @allen_ai! Introducing SafetyAnalyst, an LLM content moderation framework that š builds structured āharm-benefit treesā given a prompt š weights harms against benefits š delivers interpretable, transparent, and steerable safety decisions
2
17
112
@liweijianglw @NatMachIntell Congrats, Liwei! Canāt wait to see what amazing work youāll do next!
1
0
2
RT @RezaeiKeivan: šØPreprint from internship at @allen_ai š¤We propose restorative unlearning: not just forgetting knowledge from specific dā¦
0
22
0
RT @Anne_On_Tw: Sarah Oh and I have a new preprint! Developing a new experimental protocol to reveal habit formation separately from cognitā¦
0
9
0
RT @danfei_xu: The past decade has seen a troubling decline in Western perceptions of people of Chinese origin, largely fueled by politicalā¦
0
37
0
Iām thrilled to see the discussions sparked by my original posts. I learned that some speculated I was the one who challenged the speaker at the talk, which isnāt true. I deeply admire the wit and courage of her and others who have spoken up to make our community more inclusive.
1/3 Today, an anecdote shared by an invited speaker at #NeurIPS2024 left many Chinese scholars, myself included, feeling uncomfortable. As a community, I believe we should take a moment to reflect on why such remarks in public discourse can be offensive and harmful.
9
4
245
RT @NeurIPSConf: NeurIPS acknowledges that the cultural generalization made by the keynote speaker today reinforces implicit biases by makiā¦
0
403
0
3/3 I invite my fellow Chinese scholars to share their thoughts and feelings about this incident. I also encourage the broader NeurIPS community to join in reflecting on how we can work together to foster greater inclusivity within our community.
17
14
644
Iām presenting this work at the @solarneurips workshop #NeurIPS2024 on Saturday 11am-noon. Come to my poster to chat about interpretable AI safety!
šØ New preprint from my internship @allen_ai! Introducing SafetyAnalyst, an LLM content moderation framework that š builds structured āharm-benefit treesā given a prompt š weights harms against benefits š delivers interpretable, transparent, and steerable safety decisions
2
7
54
RT @liweijianglw: On Sat 14 Dec 11:00ā12:0 p.m. PST, I'll partially join our poster presentation for SafetyAnalyst at the SoLaR workshop (Wā¦
0
1
0
RT @AkariAsai: 1/ Introducing į“į“ļæ½ļæ½É“ź±į“Źį“Źį“Ź: a retrieval-augmented LM to help scientists synthesize knowledge š @uwnlp @allen_ai With open mā¦
0
268
0
RT @valentina__py: š£ We are looking forward to an interesting line up of invited speakers at the SoLaR workshop at NeurIPS! Come join usā¦
0
17
0
RT @niloofar_mire: Itās the season of āfinding ur next adventureā and folks have been asking me about my experience doing a postdoc, so I dā¦
0
21
0
RT @galenbrain: In this Neural Computation post, two nonlinear representation learning methods: winner-take-all, and our favorite, sparse cā¦
0
2
0
@HaqueIshfaq Similar experience studying in Europe. Different social norms and harder to be accepted as one of their own. As bad as the current political outlook is, my POC experience was still better in liberal areas under Trump than Europe
0
1
20
RT @mjqzhang: Why and when do preference annotators disagree? And how do reward models + LLM-as-Judge evaluators handle disagreements? Weā¦
0
32
0