Jiaxin Zhang

Awesome-LLM-RAG. Awesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language Models

Awesome-LLM-Uncertainty-Reliability-Robustness. Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

Awesome-LLM-Prompt-Optimization. Awesome-LLM-Prompt-Optimization: a curated list of advanced prompt optimization and tuning methods in Large Language Models

MatDesINNe. Inverse materials design via invertible neural networks

awesome-LLM-controlled-decoding-generation. awesome-LLM-controlled-constrained-generation

Awesome-OOD-detection. SOTA work about out-of-distribution detection

awesome-LMM-Hallucination. List of papers on Hallucination in LMM

awesome-energy-based-model. Energy-based model

Awesome-LLM-Fine-Tuning-Alignment. LLM fine-tuning

awesome-normalizing-flows. A list of awesome resources on normalizing flows.

PGM. Probabilistic Graphical Model Construction

OptiMUS-2. Optimization Modeling Using mip Solvers and large language models

Robustness-and-Uncertainty. Robustness, uncertainty, safety and trustworthiness in deep learning, e.g., NLP, CV, multimodality

llama-lab. Python

Say-I-Dont-Know. [ICML'2024] Can AI Assistants Know What They Don't Know?

LLMLingua. To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

DataDreamer. DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

llm-datasets. High-quality datasets, tools, and concepts for LLM fine-tuning.

sammo. A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective Metaprompt Optimization)

Awesome-LLM4AD. A curated list of awesome LLM for Autonomous Driving resources (continually updated)

awesome-llm-powered-agent. Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

safe-rlhf. Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

dynamo. A Datacenter Scale Distributed Inference Serving Framework

ijepa. Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."

AdaCAD. Code for paper "AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge"

LLAMBO. Official Repository for LLAMBO "Large Language Models to Enhance Bayesian Optimization"

DExperts. code associated with ACL 2021 DExperts paper

ML-Papers-of-the-Week. 🔥Highlighting the top ML papers every week.

Awesome-LLM-Strawberry. A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

FineGrainedRLHF. Python

gfn-lm-tuning. Jupyter Notebook

Qwen-Agent. Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

long_hallucinations. Codebase for reproducing the experiments of the semantic uncertainty paper (paragraph-length experiments).

awesome-llm-role-playing-with-persona. Awesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas

awesome-auto-alignment. Collection of papers for scalable automated alignment.

llm-uncertainty. code repo for ICLR 2024 paper "Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs"

ERASE. Code and Data for "Language Modeling with Editable External Knowledge"

AlignLLMHumanSurvey. Aligning Large Language Models with Human: A Survey

CodeUltraFeedback. CodeUltraFeedback: aligning large language models to coding preferences

apricot. Source code of "Calibrating Large Language Models Using Their Generations Only", ACL2024

sami. Self-Supervised Alignment with Mutual Information

PackLLM. Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization

MetaAligner. Models, data, and codes for the paper: MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models

olmes. Reproducible, flexible LLM evaluations

LLM101n. LLM101n: Let's build a Storyteller

self-rewarding-lm-pytorch. Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

CRAG. Corrective Retrieval Augmented Generation

iprompt2. Finding semantically meaningful and accurate prompts.

Awesome-LLMOps. An awesome & curated list of best LLMOps tools for developers

opro. official code for "Large Language Models as Optimizers"

finetuner. :dart: Task-oriented embedding tuning for BERT, CLIP, etc.

SelfAware. Do Large Language Models Know What They Don’t Know?

awesome-production-machine-learning. A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

cookbook. Jupyter Notebook

CriticBench. Repo for "CriticBench: Benchmarking LLMs for Critique-Correct Reasoning"