haoming-codes

DIFUSCO

Code of NeurIPS paper: arxiv.org/abs/2302.08224

DiGress

code for the paper "DiGress: Discrete Denoising diffusion for graph generation"

moccasin

This repo reproduces the paper "Moccasin: Efficient Tensor Rematerialization for Neural Networks"

np-hard-deep-reinforcement-learning

pytorch neural combinatorial optimization

OmniQuant

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

preference-mpc

This repo reproduces the paper "A Cost-Effective Framework for Preference Elicitation and Aggregation"

pytorch-generative-model-collections

Collection of generative models in Pytorch version.

rockmate

str-withheld

This repo reproduces the paper "Classification with Strategically Withheld Data"

time-to-rank

This repo reproduces the paper "Minimizing Time-to-Rank: A Learning and Recommendation Approach"

haoming-codes/moccasin

This repo reproduces the paper "Moccasin: Efficient Tensor Rematerialization for Neural Networks"

haoming-codes/DIFUSCO

Code of NeurIPS paper: arxiv.org/abs/2302.08224

haoming-codes/DiGress

code for the paper "DiGress: Discrete Denoising diffusion for graph generation"

haoming-codes/np-hard-deep-reinforcement-learning

pytorch neural combinatorial optimization

haoming-codes/OmniQuant

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

haoming-codes/preference-mpc

This repo reproduces the paper "A Cost-Effective Framework for Preference Elicitation and Aggregation"

haoming-codes/pytorch-generative-model-collections

Collection of generative models in Pytorch version.

haoming-codes/rockmate

haoming-codes/str-withheld

This repo reproduces the paper "Classification with Strategically Withheld Data"

haoming-codes/time-to-rank

This repo reproduces the paper "Minimizing Time-to-Rank: A Learning and Recommendation Approach"