4 papers
A Systolic Array Architecture for Nonlinear Activation Functions and Softmax Computation using Chebyshev Polynomials
Benedikt Schaible, Anirudh Suresh Bharadwaj, Ulf Schlichtmann +1
Neural Network Accelerators have gained popularity in recent years due to their greater efficiency than CPU-based platforms. Often, these accelerators utilize different hardware un…
VISTA: Video Interaction Spatio-Temporal Analysis Benchmark
Alejandro Aparcedo, Akash Kumar, Aaryan Garg +5
Existing benchmarks for Vision-Language Models (VLMs) primarily evaluate spatio-temporal understanding on simple single-action videos, closed attribute sets and restricted entity t…
Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models
Anirudh Bharadwaj, Chaitanya Malaviya, Nitish Joshi +1
Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over sub…
QR-LoRA: QR-Based Low-Rank Adaptation for Efficient Fine-Tuning of Large Language Models
Jessica Liang, Anirudh Bharadwaj
The growing scale of Large Language Models (LLMs) has necessitated the development of parameter-efficient fine-tuning techniques. Low-Rank Adaptation (LoRA) has emerged as a promis…