Sungmin Cha
@_sungmin_cha
Followers
233
Following
899
Statuses
152
Faculty Fellow @nyuniversity | PhD @SeoulNatlUni
Manhattan, NY
Joined July 2019
I am happy to share that our paper, "Towards Robust and Cost-Efficient Knowledge Unlearning for Large Language Models", has been accepted to #ICLR2025! Stay tuned for the camera-ready version and the code release! #MachineUnlearning #LLMs
1
3
22
RT @_sungmin_cha: I am happy to share that our paper, "Towards Robust and Cost-Efficient Knowledge Unlearning for Large Language Models", h…
0
3
0
RT @Ar_Douillard: Workshop alert 🚨 We'll host in ICLR 2025 a workshop on modularity, encompassing collaborative + decentralized + continua…
0
38
0
RT @adarshnl: Open Problems in Machine Unlearning for AI Safety. Read and Discuss on @askalphaxiv
0
3
0
RT @Memoirs: Soup to go: mitigating forgetting during continual learning with model averaging.
0
1
0
RT @caglar_ee: For a 6th course in ML Stanford CS 236 Deep Generative Models Cornell CS 6785 Deep Probabilistic a…
0
50
0
RT @obsrvtrm: Merging multiple fine-tuned models is a promising approach for creating a multi-task model, but it suffers from task interfer…
0
6
0
RT @FelixHill84: Do you work in AI? Do you find things uniquely stressful right now, like never before? Haver you ever suffered from a…
0
109
0
RT @kchonyc: feeling a bit under the weather this week … thus an increased level of activity on social media and blog:
0
116
0
RT @xxxnell: It's the last week to apply for this fantastic internship opportunity—don’t miss out! Apply now!
0
1
0
RT @dereklim_lzh: Our new workshop at ICLR 2025: Weight Space Learning: Weights are data. We can learn from weigh…
0
58
0
RT @jakub_lucki: An Adversarial Perspective on Machine Unlearning for AI Safety 🏆 Best paper award @solarneurips 📅 Sat 14 Dec. Poster…
0
4
0
RT @LakeBrenden: Sepp Hochreiter at #NeurIPS2024 : "The bitter lesson is over." Now is the time for more efficient (data,energy), more prac…
0
10
0
RT @mengyer: Check out our new preprint on LLM continuous evaluation on daily news. LLMs get "out-of-date" sooner than we think. Continuous…
0
4
0
RT @AmyPrb: Come chat with us @ NeurIPS for hot takes on promising directions for continual learning with foundation models!
0
1
0
RT @confusezius: 😵💫Continually pretraining large multimodal models to keep them up-to-date all-the-time is tough, covering everything from…
0
8
0