activity
20242026
collaborators
Showing 2025Show all

6 papers · 1 filter

cs.CL2025

Leveraging Parameter Space Symmetries for Reasoning Skill Transfer in LLMs

Stefan Horoi, Sangwoo Cho, Supriyo Chakraborty +4

Task arithmetic is a powerful technique for transferring skills between Large Language Models (LLMs), but it often suffers from negative interference when models have diverged duri…

cs.CL2025

SPEAR-MM: Selective Parameter Evaluation and Restoration via Model Merging for Efficient Financial LLM Adaptation

Berkcan Kapusuzoglu, Supriyo Chakraborty, Renkun Ni +2

Large language models (LLMs) adapted to financial domains often suffer from catastrophic forgetting of general reasoning capabilities essential for customer interactions and comple…

cs.LG2025

Optimizing Reasoning Efficiency through Prompt Difficulty Prediction

Bo Zhao, Berkcan Kapusuzoglu, Kartik Balasubramaniam +3

Reasoning language models perform well on complex tasks but are costly to deploy due to their size and long reasoning traces. We propose a routing approach that assigns each proble…

cs.CL2025

T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning

Amartya Chakraborty, Paresh Dashore, Nadia Bathaee +6

Large Language Models (LLMs) have demonstrated impressive capabilities as intelligent agents capable of solving complex problems. However, effective planning in scenarios involving…

cs.LG2025

Dense Backpropagation Improves Training for Sparse Mixture-of-Experts

Ashwinee Panda, Vatsal Baherwani, Zain Sarwar +4

Mixture of Experts (MoE) pretraining is more scalable than dense Transformer pretraining, because MoEs learn to route inputs to a sparse set of their feedforward parameters. Howeve…

cs.LG2025

Continual Pre-training of MoEs: How robust is your router?

Benjamin Thérien, Charles-Étienne Joseph, Zain Sarwar +7

Sparsely-activated Mixture of Experts (MoE) transformers are promising architectures for foundation models. Compared to dense transformers that require the same amount of floating-…