activity
20242026
collaborators

6 papers

cs.CL2026

Weight Tying Biases Token Embeddings Towards the Output Space

Antonio Lopardo, Avyukth Harish, Catherine Arnett +1

Weight tying, i.e. sharing parameters between input and output embedding matrices, is common practice in language model design, yet its impact on the learned embedding space remain…

cs.CL2025

Sylber: Syllabic Embedding Representation of Speech from Raw Audio

Cheol Jun Cho, Nicholas Lee, Akshat Gupta +4

Syllables are compositional units of spoken language that efficiently structure human speech perception and production. However, current neural speech representations lack such str…

cs.LG2025

Geometric Interpretation of Layer Normalization and a Comparative Analysis with RMSNorm

Akshat Gupta, Atahan Ozdemir, Gopala Anumanchipalli

This paper presents a novel geometric interpretation of LayerNorm and explores how LayerNorm influences the norm and orientation of hidden vectors in the representation space. With…

cs.CL2025

PokerBench: Training Large Language Models to become Professional Poker Players

Richard Zhuang, Akshat Gupta, Richard Yang +3

We introduce PokerBench - a benchmark for evaluating the poker-playing abilities of large language models (LLMs). As LLMs excel in traditional NLP tasks, their application to compl…

cs.LG2024

A Unified Framework for Model Editing

Akshat Gupta, Dev Sajnani, Gopala Anumanchipalli

ROME and MEMIT are largely believed to be two different model editing algorithms, with the major difference between them being the ability to perform batched edits. In this paper,…

cs.CL2024

Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing

Akshat Gupta, Sidharth Baskaran, Gopala Anumanchipalli

Recent work using Rank-One Model Editing (ROME), a popular model editing method, has shown that there are certain facts that the algorithm is unable to edit without breaking the mo…