Manuel Cherep
@manuelcherep
Followers
150
Following
196
Media
3
Statuses
28
PhD student @MIT working on behavioral machine learning. https://t.co/Y7iH2tW5LV
Cambridge, MA
Joined March 2016
✨Contrastive Learning from Synthetic Audio Doppelgängers #ICLR2025✨ w/ @nikhilsinghmus. Our method learns useful audio representations with randomly synthesized sounds (often better than real data!). 🌐Project: 📄Paper: 🧵1/3
4
9
26
RT @medialab: Congratulations to @fluidinterfaces PhD student @manuelcherep and group head Prof. Pattie Maes on receiving a 2024 Amazon Res….
0
4
0
RT @ShayneRedford: Thrilled our global data ecosystem audit was accepted to #ICLR2025!. Empirically, we find:. 1⃣ Soaring synthetic text da….
0
22
0
Are we sure AGI isn't available through Google Cloud, but we just can't find it?.
0
0
3
The code for Audio Doppelgängers is also open-source. We hope you find it useful for further exploring how and why we can learn from synthetic data. 💻 🧵3/3.
0
1
4
In CTAG (ICML24), we show how a simple synth (from SynthAX ⚡️) can recover properties of real-world sounds. Audio Doppelgängers use the same power to learn to listen from what can be perceived as just noise. CTAG: SynthAX: 🧵2/3.
1
1
2
RT @ShayneRedford: ✨New Report✨ Our data ecosystem audit across text, speech, and video (✏️,📢,📽️) finds:. 📈 Rising reliance on web, synthet….
0
43
0
If you're at NeurIPS, and interested in this topic, come chat! We're working to extend this line of work and value feedback from the community. 🧵 3/3.
0
0
3
In a complex decision-making task, we show how LM-based agents' choices superficially resembled humans', but exhibit suboptimal information acquisition strategies and extreme susceptibility to a simple nudge. 🧵 2/3.
1
0
3
Excited to present our new paper on nudging LLMs (👉🤖) as a spotlight talk at the NeurIPS Behavioral ML Workshop! @NeurIPSConf @BehavioralML . w/ Nikhil Singh* (@nikhilsinghmus) and Pattie Maes. 🔗 🧵1/3
1
2
9
RT @mattgroh: I'm recruiting a PhD student to join the Human AI Collaboration lab at @KelloggSchool @northwesterncs @NICOatNU. If you're e….
0
83
0
A great opportunity to work on your PhD with @nikhilsinghmus, one of the most incredible people I've ever met!.
Thrilled to join @DartmouthCS as Assistant Professor in Jan 2025! I’m seeking 1-2 PhD students to join in Fall 2025. Application is by December 15th; please feel free to reach out with any questions. More details here:
1
0
4
RT @nikhilsinghmus: Thrilled to join @DartmouthCS as Assistant Professor in Jan 2025! I’m seeking 1-2 PhD students to join in Fall 2025. A….
0
41
0
Excited to be (jet lagged) at ICML presenting "Creative Text-to-Audio Generation via Synthesizer Programming". Let's talk ML for audio 🤖, synthesizers 🎹🎶, etc. (work @icmlconf w/ @nikhilsinghmus @jessicashand_).
0
3
24
RT @ShayneRedford: ✨New Preprint ✨ How are shifting norms on the web impacting AI?. We find:. 📉 A rapid decline in the consenting data comm….
0
94
0
RT @medialab: Congratulations to Media Lab student @manuelcherep on being selected for the 2024–2026 "la Caixa" Fellowship! .
0
4
0
RT @medialab: At #ICML2024, Media Lab researchers @manuelcherep, @nikhilsinghmus, and @jessicashand_ will present “Creative Text-to-Audio G….
0
2
0
📢 The code for CTAG is now available! You can easily generate sound from prompts by using a modular synthesizer (SynthAX ⚡️).
0
2
14
RT @oriolbarbany: An appealing solution to tackle data scarcity in 🤖 learning is realying on simulators. But how good are they?.Huge effort….
0
2
0
By interpolating the parameters between different sounds generated by CTAG, we enable some cool smooth transitions. 📢Code will be out very soon!
0
0
2