papers

Publications (8)

cs.LG2026

QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill

Dalton Jones, Junyoung Park, Matthew Morse +3

We present QUOKA: Query-oriented KV selection for efficient attention, a training-free and hardware agnostic sparse attention algorithm for accelerating transformer inference under…

cs.LG2021

Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces

Bert Moons, Parham Noorzad, Andrii Skliar +4

Current state-of-the-art Neural Architecture Search (NAS) methods neither efficiently scale to multiple hardware platforms, nor handle diverse architectural search-spaces. To remed…

cs.CL2025

VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs

Raghavv Goel, Sudhanshu Agrawal, Mukul Gagrani +9

In this paper, we introduce a simple training-free technique to improve the performance of drafter-based speculative decoding (SpD) methods that incorporates language modeling head…

cs.CL2026

A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs

Raghavv Goel, Risheek Garrepalli, Sudhanshu Agrawal +3

Autoregressive (AR) language models build representations incrementally via left-to-right prediction, while diffusion language models (dLLMs) are trained through full-sequence deno…

cs.LG2025

CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction

Raghavv Goel, Junyoung Park, Mukul Gagrani +5

While long context support of large language models has extended their abilities, it also incurs challenges in memory and compute which becomes crucial bottlenecks in resource-rest…

cs.CL2026

Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing

Raghavv Goel, Mukul Gagrani, Mingu Lee +1

Large Language Models (LLMs) possess latent multi-token prediction (MTP) abilities despite being trained only for next-token generation. We introduce ESP (Embedding-Space Probing),…