Papers by Anton Razzhigaev

8 papers
Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images (2025.naacl-srw)

Copied to clipboard

Challenge: Existing methods to measure image common sense inconsistentness are difficult to implement because of their complexity.
Approach: They propose a visual commonsense model that leverages large vision-language models to extract atomic facts from images and a compact attention-pooling classifier to fine-tune it over encoded atomic fact.
Outcome: The proposed method outperforms existing methods on the WHOOPS! and WEIRD datasets while maintaining a compact attention-pooling classifier over encoded atomic facts.
MEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answering (2022.acl-srw)

Copied to clipboard

Challenge: Existing methods to embed learning use a standard Neural Networks (NN) backward mechanism, duplicating its memory consumption.
Approach: They propose a memory-efficient KG embedding model that embeds knowledge graphs as 3rd-order binary tensors.
Outcome: The proposed model yields comparable performance on link prediction and KG-based question answering tasks.
Your Transformer is Secretly Linear (2024.acl-long)

Copied to clipboard

Challenge: a novel linear characteristic exclusive to transformer decoders is revealed: embedding transformations between sequential layers exhibit almost perfect linearity.
Approach: They propose a cosine-similarity-based regularization to reduce layer linearity in transformer decoders.
Outcome: The proposed method improves performance metrics on Tiny Stories and SuperGLUE but also decreases the linearity of the models.
The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models (2024.findings-eacl)

Copied to clipboard

Challenge: Embeddings in transformers encode vast amounts of linguistic nuances and patterns.
Approach: They investigate the anisotropy dynamics and intrinsic dimension of embeddings in transformers . they found that transformer decoders exhibit a bell-shaped anisotropie profile .
Outcome: The investigated embeddings exhibit a bell-shaped curve with the highest anisotropy concentrations in the middle layers . the intrinsic dimension increases in the initial phases of training, indicating an expansion into higher-dimensional space.
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) encode and store contextual information, but internal mechanisms are opaque.
Approach: They propose a toolkit that assesses token-level nonlinearity, evaluates contextual memory, visualizes intermediate layer contributions and measures intrinsic dimensionality of representations.
Outcome: The proposed framework assesses token-level nonlinearity, evaluates contextual memory, visualizes intermediate layer contributions, and measures the intrinsic dimensionality of representations.
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders (2025.findings-acl)

Copied to clipboard

Challenge: Existing algorithms for AI text detection lack interpretability, limiting their reliability in highstakes applications.
Approach: They extend existing ATD frameworks by using Sparse Autoencoders to extract features from Gemma-2-2b residual stream.
Outcome: The proposed algorithms can extract human-interpretable features from Gemma-2-2b model.
Kandinsky: An Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion (2023.emnlp-demo)

Copied to clipboard

Challenge: Experimental evaluations demonstrate FID score of 8.03 on the COCO-30K dataset, marking our model as the top open source performer in terms of measurable image generation quality.
Approach: They propose a latent diffusion-based model that combines image prior and latent diffusive techniques to create a text-to-image architecture.
Outcome: The proposed model achieves the highest FID score among open-source models . it is compared with the state-of-the-art models on the COCO-30K dataset .
A System for Answering Simple Questions in Multiple Languages (2023.acl-demo)

Copied to clipboard

Challenge: Existing knowledge graph question answering systems are limited to simple questions, but they can be used to answer complex questions.
Approach: They propose a multilingual Knowledge Graph Question Answering technique that orders potential responses based on the distance between the question’s text embeddings and the answer’s graph embedds.
Outcome: The proposed method consistently outperforms baseline systems, including seq2seq QA models and complex rule-based pipelines.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations