Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
Our code for ICLR'24 paper "Energy-based Automated Model Evaluation".
Our code for ICMR'22 Oral paper "HybridVocab: Towards Multi-Modal Machine Translation via Multi-Aspect Alignment".
Our code for ICCV'23 paper "CAME: Contrastive Automated Model Evaluation".
Real-time updated, fine-grained reading list on LLM-synthetic-data.🔥
Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
This is the official repository of our paper "MaxSup: Overcoming Representation Collapse in Label Smoothing"
The official Pytorch implementation of S-DANE
Code Implementation, Evaluations, Documentation, Links and Resources for Min P paper
Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
Stealthy Imitation: Reward-guided Environment-free Policy Stealing (ICML 2024)
[ICML2024]Adaptive decoding balances the diversity and coherence of open-ended text generation.
Official implementation of Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS DB Track'24 Spotlight).
This is the official implementation of our ICML 2024 paper "MultiMax: Sparse and Multi-Modal Attention Learning""
FBX Python SDK for Python3.x
Visualkeras is a Python package to help visualize Keras (either standalone or included in TensorFlow) neural network architectures. It allows easy styling to fit most needs. This module supports la…
The official repository for CosPGD: a unified white-box adversarial attack for pixel-wise prediction tasks.
This repo contains the data used in "Towards Understanding Climate Change Perceptions: A Social Media Dataset"
This is the official implementation of our paper "Hypergraph Transformer for Skeleton-based Action Recognition."
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
[TIP 2022] The official implementation of "One-Stage Visual Relationship Referring With Transformers and Adaptive Message Passing".
Count the MACs / FLOPs of your PyTorch model.