papers

Publications (25)

cs.CL2026

BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs

Abbas Ghaddar, Ivan Kobyzev, Boxing Chen +1

Post-training hybridization of large language models (LLMs) often replaces quadratic self-attention with sliding-window attention (SWA) to reduce KV cache usage and improve latency…

stat.ML2020

Normalizing Flows: An Introduction and Review of Current Methods

Ivan Kobyzev, Simon J. D. Prince, Marcus A. Brubaker

Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article…

math.KT2018

Anti-Yetter-Drinfeld Modules for Quasi-Hopf Algebras

Ivan Kobyzev, Ilya Shapiro

We apply categorical machinery to the problem of defining anti-Yetter-Drinfeld modules for quasi-Hopf algebras. While a definition of Yetter-Drinfeld modules in this setting, extra…

cs.LG2022

Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization

Aref Jafari, Ivan Kobyzev, Mehdi Rezagholizadeh +2

Knowledge Distillation (KD) has been extensively used for natural language understanding (NLU) tasks to improve a small model's (a student) generalization by transferring the knowl…

cs.CL2023

Attribute Controlled Dialogue Prompting

Runcheng Liu, Ahmad Rashid, Ivan Kobyzev +2

Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. However, both discrete prompting and…

cs.CL2025

Integral Transformer: Denoising Attention, Not Too Much Not Too Little

Ivan Kobyzev, Abbas Ghaddar, Dingtao Hu +1

Softmax self-attention often assigns disproportionate weight to semantically uninformative tokens such as special tokens and punctuation, a phenomenon known as attention noise. Whi…

cs.CL2024

OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection

Chenyang Huang, Abbas Ghaddar, Ivan Kobyzev +3

Recently, there has been considerable attention on detecting hallucinations and omissions in Machine Translation (MT) systems. The two dominant approaches to tackle this task invol…

cs.CL2021

A Short Study on Compressing Decoder-Based Language Models

Tianda Li, Yassir El Mesbahi, Ivan Kobyzev +6

Pre-trained Language Models (PLMs) have been successful for a wide range of natural language processing (NLP) tasks. The state-of-the-art of PLMs, however, are extremely large to b…

cs.LG2022

Learning Functions on Multiple Sets using Multi-Set Transformers

Kira Selby, Ahmad Rashid, Ivan Kobyzev +2

We propose a general deep architecture for learning functions on multiple permutation-invariant sets. We also show how to generalize this architecture to sets of elements of any di…

cs.LG2023

Mathematical Challenges in Deep Learning

Vahid Partovi Nia, Guojun Zhang, Ivan Kobyzev +8

Deep models are dominating the artificial intelligence (AI) industry since the ImageNet challenge in 2012. The size of deep models is increasing ever since, which brings new challe…

cs.LG2020

Representation Learning for Dynamic Graphs: A Survey

Seyed Mehran Kazemi, Rishab Goel, Kshitij Jain +4

Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance. Traditionally, machine learni…

cs.CL2024

Resonance RoPE: Improving Context Length Generalization of Large Language Models

Suyuchen Wang, Ivan Kobyzev, Peng Lu +2

This paper addresses the challenge of train-short-test-long (TSTL) scenarios in Large Language Models (LLMs) equipped with Rotary Position Embedding (RoPE), where models pre-traine…

cs.CL2021

Polarized-VAE: Proximity Based Disentangled Representation Learning for Text Generation

Vikash Balasubramanian, Ivan Kobyzev, Hareesh Bahuleyan +2

Learning disentangled representations of real-world data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute label…

cs.CL2025

ReGLA: Refining Gated Linear Attention

Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh +2

Recent advancements in Large Language Models (LLMs) have set themselves apart with their exceptional performance in complex language modelling tasks. However, these models are also…

cs.CL2022

Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging

Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh +3

Knowledge Distillation (KD) is a commonly used technique for improving the generalization of compact Pre-trained Language Models (PLMs) on downstream tasks. However, such methods i…

cs.CL2024

Hyperparameter Optimization for Large Language Model Instruction-Tuning

Christophe Tribes, Sacha Benarroch-Lelong, Peng Lu +1

The fine-tuning of Large Language Models (LLMs) has enabled them to recently achieve milestones in natural language processing applications. The emergence of ever larger LLMs has p…

cs.CL2023

DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation

Mojtaba Valipour, Mehdi Rezagholizadeh, Ivan Kobyzev +1

With the ever-growing size of pretrained models (PMs), fine-tuning them has become more expensive and resource-hungry. As a remedy, low-rank adapters (LoRA) keep the main pretraine…

cs.LG2022

Equivariant Finite Normalizing Flows

Avishek Joey Bose, Marcus Brubaker, Ivan Kobyzev

Generative modeling seeks to uncover the underlying factors that give rise to observed data that can often be modeled as the natural symmetries that manifest themselves through inv…

cs.CL2024

Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity

Michael R. Metel, Peng Lu, Boxing Chen +2

We present a simple on the fly method for faster inference of large language models. Unlike other (self-)speculative decoding techniques, our method does not require fine-tuning or…

math.KT2018

A categorical approach to cyclic cohomology of quasi-Hopf algebras and Hopf algebroids

Ivan Kobyzev, Ilya Shapiro

We apply categorical machinery to the problem of defining cyclic cohomology with coefficients in two particular cases, namely quasi-Hopf algebras and Hopf algebroids. In the case o…

cs.LG2025

LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization

Peng Lu, Ahmad Rashid, Ivan Kobyzev +2

Regularization techniques are crucial to improving the generalization performance and training efficiency of deep neural networks. Many deep learning algorithms rely on weight deca…

cs.CL2020

Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory

Nabiha Asghar, Ivan Kobyzev, Jesse Hoey +2

State-of-the-art neural dialogue systems excel at syntactic and semantic modelling of language, but often have a hard time establishing emotional alignment with the human interacta…

cs.CL2022

KronA: Parameter Efficient Tuning with Kronecker Adapter

Ali Edalati, Marzieh Tahaei, Ivan Kobyzev +3

Fine-tuning a Pre-trained Language Model (PLM) on a specific downstream task has been a well-known paradigm in Natural Language Processing. However, with the ever-growing size of P…

cs.LG2023

Do we need Label Regularization to Fine-tune Pre-trained Language Models?

Ivan Kobyzev, Aref Jafari, Mehdi Rezagholizadeh +5

Knowledge Distillation (KD) is a prominent neural model compression technique that heavily relies on teacher network predictions to guide the training of a student model. Consideri…

math.ST2020

Tails of Lipschitz Triangular Flows

Priyank Jaini, Ivan Kobyzev, Yaoliang Yu +1

We investigate the ability of popular flow based methods to capture tail-properties of a target density by studying the increasing triangular maps used in these flow methods acting…