AIConfPaper
← Search

Ashish Khetan

11 accepted papers

2026

When LLMs get significantly worse: A statistical approach to detect model degradations

Jonas M. Kübler, Kailash Budhathoki, Matthäus Kleindessner, Xiong Zhou, Junming Yin, Ashish Khetan +1
ICLR 2026poster

Minimizing the inference cost and latency of foundation models has become a crucial area of research. Optimization approaches include theoretically lossless methods and others without accuracy guarantees like quantization. In all of these cases it is crucial to ensure that the model quality has not…

Cited by 0Source ↗code ↗Scholar ↗
2023

Representation Projection Invariance Mitigates Representation Collapse

Anastasia Razdaibiedina, Ashish Khetan, Zohar Karnin, Daniel Khashabi, Vivek Madan
EMNLP 2023long findings

Fine-tuning contextualized representations learned by pre-trained language models remains a prevalent practice in NLP. However, fine-tuning can lead to representation degradation (also known as representation collapse), which may result in instability, sub-optimal performance, and weak generalizatio…

Cited by 0Source ↗Scholar ↗
2022

Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection

Xin Huang, Ashish Khetan, Rene Bidart, Zohar Karnin
ACL 2022long

Transformer-based language models such as BERT (CITATION) have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive. A recent line of works use various heuristics to successively shorten sequence length while transforming tokens through encoders, in tas…

Cited by 21Source ↗PDF ↗Scholar ↗
2018

PacGAN: The power of two samples in generative adversarial networks

Zinan Lin, Ashish Khetan, Giulia Fanti, Sewoong Oh
NeurIPS 2018poster

Generative adversarial networks (GANs) are a technique for learning generative models of complex data distributions from samples. Despite remarkable advances in generating realistic images, a major shortcoming of GANs is the fact that they tend to produce samples with little diversity, even when tra…

Cited by 461Source ↗PDF ↗code ↗Scholar ↗
2018

Robustness of conditional GANs to noisy labels

Kiran K Thekumparampil, Ashish Khetan, Zinan Lin, Sewoong Oh
NeurIPS 2018spotlight

We study the problem of learning conditional generators from noisy labeled samples, where the labels are corrupted by random noise. A standard training of conditional GANs will not only produce samples with wrong labels, but also generate poor quality samples. We consider two scenarios, depending on…

Cited by 353Source ↗PDF ↗code ↗Scholar ↗