Vimal Thilak

Publication Activity (10 Years)

Years Active: 2002-2024
Publications (10 Years): 10

Top Topics

Word Error Rate

Document Length

Noisy Observations

Language Modelling

Top Venues

Trans. Mach. Learn. Res.

Publications

Noam Razin, Hattie Zhou, Omid Saremi, Vimal Thilak, Arwen Bradley, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin
Vanishing Gradients in Reinforcement Finetuning of Language Models. ICLR (2024)
Vimal Thilak, Chen Huang, Omid Saremi, Laurent Dinh, Hanlin Goh, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures. ICLR (2024)
Etai Littwin, Omid Saremi, Madhu Advani, Vimal Thilak, Preetum Nakkiran, Chen Huang, Joshua M. Susskind
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks. CoRR (2024)
Vimal Thilak, Etai Littwin, Shuangfei Zhai, Omid Saremi, Roni Paiss, Joshua M. Susskind
The Slingshot Effect: A Late-Stage Optimization Anomaly in Adaptive Gradient Methods. Trans. Mach. Learn. Res. 2024 (2024)
Noam Razin, Hattie Zhou, Omid Saremi, Vimal Thilak, Arwen Bradley, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin
Vanishing Gradients in Reinforcement Finetuning of Language Models. CoRR (2023)
Vimal Thilak, Chen Huang, Omid Saremi, Laurent Dinh, Hanlin Goh, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures. CoRR (2023)
Samira Abnar, Omid Saremi, Laurent Dinh, Shantel Wilson, Miguel Ángel Bautista, Chen Huang, Vimal Thilak, Etai Littwin, Jiatao Gu, Josh M. Susskind, Samy Bengio
Adaptivity and Modularity for Efficient Generalization Over Task Complexity. CoRR (2023)
Vimal Thilak, Etai Littwin, Shuangfei Zhai, Omid Saremi, Roni Paiss, Joshua M. Susskind
The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon. CoRR (2022)
Etai Littwin, Omid Saremi, Shuangfei Zhai, Vimal Thilak, Hanlin Goh, Joshua M. Susskind, Greg Yang
Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks. CoRR (2021)
Shih-Yu Sun, Vimal Thilak, Etai Littwin, Omid Saremi, Joshua M. Susskind
Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks. CoRR (2021)
Vimal Thilak, Charles D. Creusere, David G. Voelz
Material Classification using Passive Polarimetric Imagery. ICIP (4) (2007)
Vimal Thilak, Charles D. Creusere
Tracking of extended size targets in H.264 compressed video using the probabilistic data association filter. EUSIPCO (2004)
Aria Nosratinia, Vimal Thilak
Robust bandlimited watermarking with trellis coded modulation. ICIP (2) (2002)