10 papers
Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations
Kevin Y. Li, Asher Trockman, Ananda Theertha Suresh +1
Softmax attention is the cornerstone of modern large language models, but its memory scales linearly and compute quadratically with sequence length. Linear recurrent models, such a…
CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization
Soo Min Kwon, Ziteng Sun, Ananda Theertha Suresh +2
Group Relative Policy Optimization (GRPO) has emerged as a powerful algorithm for improving the reasoning capabilities of language models, but often fails to improve small models d…
On Robust Hypothesis Testing with respect to the Hellinger Distance
Eeshan Modak, Sivaraman Balakrishnan, Ananda Theertha Suresh
We study a variant of the simple hypothesis testing problem where observed samples do not necessarily come from either of the specified distributions, but rather from a close varia…
CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding
Ziteng Sun, Adrian Benton, Samuel Kushnir +4
Post-training quantization is an effective method for reducing the serving cost of large language models, where the standard approach is to use a round-to-nearest quantization leve…
Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe
Chong You, Rajesh Jayaram, Ananda Theertha Suresh +3
Dual encoder (DE) models, where a pair of matching query and document are embedded into similar vector representations, are widely used in information retrieval due to their simpli…
Coupling without Communication and Drafter-Invariant Speculative Decoding
Majid Daliri, Christopher Musco, Ananda Theertha Suresh
Suppose Alice has a distribution and Bob has a distribution . Alice wants to draw a sample and Bob a sample such that with as high of probabilit…