8 papers
TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
Manish Nagaraj, Sakshi Choudhary, Utkarsh Saxena +2
Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, k…
TopoPrune: Robust Data Pruning via Unified Latent Space Topology
Arjun Roy, Prajna G. Malettira, Manish Nagaraj +1
Geometric data pruning methods, while practical for leveraging pretrained models, are fundamentally unstable. Their reliance on extrinsic geometry renders them highly sensitive to…
TraceNAS: Zero-shot LLM Pruning via Gradient Trace Correlation
Prajna G. Malettira, Manish Nagaraj, Arjun Roy +2
Structured pruning is essential for efficient deployment of Large Language Models (LLMs). The varying sensitivity of LLM sub-blocks to pruning necessitates the identification of op…
Coresets from Trajectories: Selecting Data via Correlation of Loss Differences
Manish Nagaraj, Deepak Ravikumar, Kaushik Roy
Deep learning models achieve state-of-the-art performance across domains but face scalability challenges in real-time or resource-constrained scenarios. To address this, we propose…
FEDORA: Flying Event Dataset fOr Reactive behAvior
Amogh Joshi, Adarsh Kosta, Wachirawit Ponghiran +2
The ability of resource-constrained biological systems such as fruitflies to perform complex and high-speed maneuvers in cluttered environments has been one of the prime sources of…
Energy-Efficient Autonomous Aerial Navigation with Dynamic Vision Sensors: A Physics-Guided Neuromorphic Approach
Sourav Sanyal, Amogh Joshi, Manish Nagaraj +2
Vision-based object tracking is a critical component for achieving autonomous aerial navigation, particularly for obstacle avoidance. Neuromorphic Dynamic Vision Sensors (DVS) or e…