Virginia Smith Profile
Virginia Smith

@gingsmith

Followers
698
Following
12
Media
0
Statuses
38

ML Professor @ CMU 🦋 gingsmith

Joined December 2011
Don't wanna be here? Send us removal request.
@gingsmith
Virginia Smith
11 hours
RT @prthaker_: I'm very excited to share some new work This work started out in conversations with @thorn where we….
0
8
0
@gingsmith
Virginia Smith
14 days
RT @icmlconf: ICML offers an optional poster printing service Orders can be picked up the day at the Vancouver Con….
0
3
0
@gingsmith
Virginia Smith
28 days
RT @matthewyryang: 🚨 NEW PAPER: What if LLMs could tackle harder problems - not by explicitly training on longer traces, but by learning ho….
0
2
0
@gingsmith
Virginia Smith
2 months
RT @mlcmublog: Are your LLMs truly forgetting unwanted data? . In this new blog post authored by @shengyuan_26734,….
0
3
0
@gingsmith
Virginia Smith
2 months
RT @atalwalkar: I’m excited to share new work from Datadog AI Research! We just released Toto, a new SOTA (by a wide margin!) time series f….
0
54
0
@gingsmith
Virginia Smith
2 months
RT @icmlconf: Invited talked are announced. Jon Kleinberg.Pamela Samuelson.Frauke Kreuter.Anca Dragan.Andreas Kr….
0
5
0
@gingsmith
Virginia Smith
2 months
RT @AashiqMuhamed: Thrilled to share our new work on improving LLM unlearning! 🚀 .Gradient-based unlearning struggle with high cost, instab….
0
10
0
@gingsmith
Virginia Smith
3 months
RT @mlcmublog: 📈⚠️ Is your LLM unlearning benchmark measuring what you think it is? . In a new blog post authored….
0
12
0
@gingsmith
Virginia Smith
3 months
RT @andrewgwils: The ICML 2025 workshops list is online! Many exciting topics, spanning multi-agent systems, world….
0
17
0
@gingsmith
Virginia Smith
3 months
RT @setlur_amrith: How to effectively unlearn finetuning data?.❌ Approx. methods leak sensitive data.✅ Exact unlearning (eg. retraining) is….
0
10
0
@gingsmith
Virginia Smith
5 months
🔗 Learn more about the program here: 🔗 Apply here (deadline April 1, 2025): 
0
0
6
@gingsmith
Virginia Smith
5 months
The Simons Institute Research Fellowship provides a salary & benefits for the duration of the program, along with housing and visa support. The fellowship is intended for junior researchers who received their PhD at most 5 years ago.
1
0
3
@gingsmith
Virginia Smith
5 months
ML systems are increasingly powered by data from many sources and stakeholders. Techniques like FL can enable secure, collaborative learning in such scenarios. The program will convene experts in ML, optimization, econ, privacy & security to bridge theory & practice in the field.
1
0
2
@gingsmith
Virginia Smith
5 months
Are you a junior researcher interested in federated and collaborative learning? Consider applying to the Simons Institute Research Fellowship (due April 1) to participate in the Spring 2026 FL/CL Program at the Simons Institute at UC Berkeley! details below 👇.
1
11
66
@gingsmith
Virginia Smith
6 months
See the CfP for more details:
0
0
0
@gingsmith
Virginia Smith
6 months
Reminder that the abstract deadline for ICML is one week away (Jan 23). Authors should include the submission's title, abstract, and complete author list by this date. The paper itself is due a week later.
@icmlconf
ICML Conference
6 months
ICML submission site is now open. Note that there's an abstract deadline on Jan 23.
1
0
1
@gingsmith
Virginia Smith
6 months
RT @icmlconf: ICML submission site is now open. Note that there's an abstract deadline on Jan 23.
0
24
0
@gingsmith
Virginia Smith
6 months
RT @mlcmublog: How can we train LLMs to solve complex challenges beyond just data scaling? In a new blogpost, @set….
0
22
0
@gingsmith
Virginia Smith
6 months
#4: Reviewing takes a lot of work and reviews themselves contain highly valuable information. In line with NeurIPS & ICLR, which have made accepted papers’ reviews public for years, reviews and discussions of all *accepted* ICML papers will be made public after the conference.
0
2
34
@gingsmith
Virginia Smith
6 months
#3: The use of GenAI tools for reviewing is prohibited, for two key reasons. First, allowing AI generated reviews can damage the credibility of reviewing. Second, submissions and reviews may contain privileged information that should not be inputted into such tools.
2
1
16