Emily Cheng
@sparse_emcheng
Followers
151
Following
112
Media
4
Statuses
46
Apple MLR intern and PhD @colt_upf in computational linguistics What is the happiest state? Maryland 💅🏼 Before: MIT CSAIL, ENS
Joined April 2022
RT @meanwhileina: PostDoc position (3.5y) available in interdisciplinary Collaborative Research Center "Common Ground". 🎯 Topic: Pragmati….
0
12
0
RT @bkhmsi: 🚨New Preprint!!. Thrilled to share with you our latest work: “Mixture of Cognitive Reasoners”, a modular transformer architectu….
0
83
0
RT @f14bertolotti: This paper is a bit heavy; however, the insights are good. The authors characterize the requirements for two representat….
0
31
0
@tomjiralerspong Work led by @jinleewastaken and @tomjiralerspong , with Jade Yu and Yoshua Bengio . Updated preprint:
0
0
4
We'll be presenting this at #ACL2025 ! Come find me and @tomjiralerspong in Vienna :).
New paper! 🌟How does LM representational geometry encode compositional complexity? . A: it depends on how we define compositionality! . We distinguish compositionality of form vs. meaning, and show LMs encode form complexity linearly and meaning complexity nonlinearly. 1/9
1
2
10
RT @ValeMaiorca: I'm so glad this paper finally lost the "release date procrastination" race against GTA6! 🥹.
0
1
0
RT @GeelingC: Come find us in Hall 3! Can’t wait to meet you and talk about modeling brain data across heterogeneous datasets! https://t.co….
0
4
0
RT @gkreiman: Brains, Minds and Machines Summer Course 2025. Application deadline: Mar 24, 2025 See more informatio….
0
21
0
RT @elegualdoni: Thank you so much to all the people that came to discuss our research! This paper was such a fun and exciting collaboratio….
0
3
0
RT @NogaZaslavsky: If you're at #NeurIPS2024 today, check out our paper "Bridging semantics and pragmatics in information-theoretic emergen….
0
10
0
RT @DiegoDoimo: I just landed in Vancouver to present @NeurIPSConf the findings of our new work!. Few-shot learning and fine-tuning change….
0
5
0
RT @andrea_dittadi: Why do NNs often learn similar representations? Existing identifiability results offer theoretical insights, but applyi….
0
9
0
RT @colt_upf: 🔊New EMNLP paper from @elegualdoni & Gemma Boleda! . Why do objects have many names? . Human lexicons contain different words….
0
4
0
RT @NogaZaslavsky: I'm recruiting PhD students this cycle! My lab works at the intersection of information theory, cognition, language, and….
0
100
0
RT @scaperex: I’ll be presenting our work on predicting human reading comprehension from eye movements 👀🎯at #EMNLP2024!. Tomorrow, Nov 12 (….
0
4
0
RT @su1001v: New paper💡!. Certain networks can't perform certain tasks due to lacking the right prior 😢. Can we make these untrainable netw….
0
3
0
RT @agopal42: Excited to present "Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery" at #NeurIPS2024!.TL;DR: Our mo….
0
41
0
Overall, semantic and agreement-related (functional) pressures shape grammatical systems. 1⃣Semantics determines the set of grammatical features, and.2⃣Functional pressures disperse them across the lexicon. Emily Cheng & Francesca Franzon.Preprint: 6/6.
0
0
4