Search Results for author:
Found 14 papers, 4 papers with code
BASS: Batched Attention-optimized Speculative Sampling
Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models.
CodeFort: Robust Training for Code Generation Models
Code generation models are not robust to small perturbations, which often lead to inconsistent and incorrect generations and significantly degrade the performance of these models.
Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs
This study introduces bifurcated attention, a method designed to enhance language model inference in shared-context batch decoding scenarios.
Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars
Large Language Models are powerful tools for program synthesis and advanced auto-completion, but come with no guarantee that their output code is syntactically correct.
Greener yet Powerful: Taming Large Code Generation Models with Quantization
Such large models incur significant resource usage (in terms of memory, latency, and dollars) as well as carbon footprint.
ReCode: Robustness Evaluation of Code Generation Models
Most existing works on robustness in text or code tasks have focused on classification, while robustness in generation tasks is an uncharted area and to date there is no comprehensive benchmark for robustness in code generation.
Multi-lingual Evaluation of Code Generation Models
Using these benchmarks, we are able to assess the performance of code generation models in a multi-lingual fashion, and discovered generalization ability of language models on out-of-domain languages, advantages of multi-lingual models over mono-lingual, the ability of few-shot prompting to teach the model new languages, and zero-shot translation abilities even on mono-lingual settings.
Logical Credal Networks
This paper introduces Logical Credal Networks, an expressive probabilistic logic that generalizes many prior models that combine logic and probability.
An Ensemble Approach Towards Adversarial Robustness
The new techniques are evaluated on MNIST and Fashion-MNIST, with no adversarial training.
Oriole: Thwarting Privacy against Trustworthy Deep Learning Models
Deep Neural Networks have achieved unprecedented success in the field of face recognition such that any individual can crawl the data of others from the Internet without their explicit permission for the purpose of training high-precision face recognition models, creating a serious violation of privacy.
Logical Neural Networks
We propose a novel framework seamlessly providing key properties of both neural nets (learning) and symbolic logic (knowledge and reasoning).
With Great Dispersion Comes Greater Resilience: Efficient Poisoning Attacks and Defenses for Linear Regression Models
To this end, we analyze and develop a new poisoning attack algorithm.
Neural Belief Reasoner
The second is supervised learning: a robust MNIST classifier for 4 and 9, which is the most challenging pair of digits.
L2-Nonexpansive Neural Networks
This paper proposes a class of well-conditioned neural networks in which a unit amount of change in the inputs causes at most a unit amount of change in the outputs or any of the internal layers.
