Papers by Basura Fernando

5 papers
Flow Matching for Conditional Text Generation in a Few Sampling Steps (2024.eacl-short)

Copied to clipboard

Challenge: Current diffusion models face multiple drawbacks including slow sampling, noise schedule sensitivity, and misalignment between training and sampling stages.
Approach: They propose a method which leverages flow matching for conditional text generation.
Outcome: The proposed method can generate text in a few steps by training with a novel anchor loss, alleviating the need for expensive hyperparameter optimization of the noise schedule prevalent in diffusion models.
PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Large language models demonstrate remarkable capabilities across various domains, including mathematics and logic reasoning.
Approach: They propose a physics-based reasoning benchmark that includes physics theorems and constraints and a Physics Solution Auto Scoring Framework to evaluate physics based reasoning in large language models.
Outcome: The proposed framework enables models to achieve less than 60% on answer-level evaluation, with performance dropping from knowledge questions (75.11%) to hard problems (31.99%).
Diagram-Driven Course Questions Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Visual Question Generation (VQG) research focuses on natural images while neglecting diagrams, a critical component of educational materials.
Approach: They propose a diagram-driven course questions generation task to generate diagram-relevant questions for specific courses.
Outcome: The proposed framework outperforms existing models on DiagramQG while maintaining strong generalizability across natural image datasets.
Semi-supervised multimodal coreference resolution in image narrations (2023.emnlp-main)

Copied to clipboard

Challenge: a semi-supervised approach is used to resolve multimodal coreferences and narrative grounding in a multimodal context.
Approach: They propose a semi-supervised approach that utilizes image-narration pairs to resolve coreferences and narrative grounding in a multimodal context.
Outcome: The proposed approach outperforms baselines quantitatively and qualitatively for coreference resolution and narrative grounding in a multimodal context.
Memory-efficient Temporal Moment Localization in Long Videos (2023.eacl-main)

Copied to clipboard

Challenge: Temporal Moment Localization is a multi-modal task that requires understanding the temporal relationships in the entire input video.
Approach: They propose a stochastic sampling module that can process long videos at a constant memory footprint.
Outcome: The proposed model can process videos as long as 18 minutes at a constant memory footprint and achieves faster and faster results than competing models.

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