collaborators

5 papers

cs.LG2026

Conditional Optimal Bridge for Riemannian Activation Steering

Seyed Arshan Dalili, Ajay Narayanan Sridhar, Vijaykrishnan Narayanan +1

Activation steering offers a lightweight alternative to fine-tuning for controlling large language models at inference time. While many existing methods implicitly optimize a log-d…

cs.LG2026

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability

Seyed Arshan Dalili, Mehrdad Mahdavi

Sparse Autoencoders (SAEs) are widely used for mechanistic interpretability in large language models, yet their formulation assigns each latent feature a single decoder direction,…

cs.LG2025

Model Merging via Multi-Teacher Knowledge Distillation

Seyed Arshan Dalili, Mehrdad Mahdavi

Model merging has emerged as a lightweight alternative to joint multi-task learning (MTL), yet the generalization properties of merged models remain largely unexplored. Establishin…

cs.CL2025

AIMA at SemEval-2024 Task 3: Simple Yet Powerful Emotion Cause Pair Analysis

Alireza Ghahramani Kure, Mahshid Dehghani, Mohammad Mahdi Abootorabi +3

The SemEval-2024 Task 3 presents two subtasks focusing on emotion-cause pair extraction within conversational contexts. Subtask 1 revolves around the extraction of textual emotion-…

cs.CL2025

AIMA at SemEval-2024 Task 10: History-Based Emotion Recognition in Hindi-English Code-Mixed Conversations

Mohammad Mahdi Abootorabi, Nona Ghazizadeh, Seyed Arshan Dalili +3

In this study, we introduce a solution to the SemEval 2024 Task 10 on subtask 1, dedicated to Emotion Recognition in Conversation (ERC) in code-mixed Hindi-English conversations. E…