Xinhao Xu (Ocean-627)

Ocean-627

Geek Repo

Company:Tsinghua University

Location:Beijing

Github PK Tool:Github PK Tool

Xinhao Xu's starred repositories

llama.cpp

LLM inference in C/C++

yolov10

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

Language:PythonLicense:AGPL-3.0Stargazers:9877Issues:51Issues:411

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

Language:PythonLicense:MITStargazers:7428Issues:46Issues:1046

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Language:PythonLicense:MITStargazers:6643Issues:65Issues:82

YOLO-World

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Language:PythonLicense:GPL-3.0Stargazers:4617Issues:39Issues:450

mPLUG-Owl

mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

Language:PythonLicense:MITStargazers:2309Issues:30Issues:229

Awesome-LLMs-for-Video-Understanding

🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.

Awesome-LLM-Long-Context-Modeling

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

LLaMA-VID

LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models (ECCV 2024)

Language:PythonLicense:Apache-2.0Stargazers:728Issues:14Issues:109

arena-hard-auto

Arena-Hard-Auto: An automatic LLM benchmark.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:626Issues:7Issues:27

LongLM

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

Language:PythonLicense:MITStargazers:610Issues:10Issues:37

Awesome-MLLM-Hallucination

đź“– A curated list of resources dedicated to hallucination of multimodal large language models (MLLM).

LEval

[ACL'24 Outstanding] Data and code for L-Eval, a comprehensive long context language models evaluation benchmark

Language:PythonLicense:GPL-3.0Stargazers:355Issues:4Issues:17

ChunkLlama

[ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"

Language:PythonLicense:Apache-2.0Stargazers:351Issues:7Issues:21

TimeChat

[CVPR 2024] TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding

Language:PythonLicense:BSD-3-ClauseStargazers:283Issues:5Issues:45

FastV

[ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

long-llms-learning

A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks

Language:Jupyter NotebookStargazers:253Issues:8Issues:2

LongAlign

[EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs

Language:PythonLicense:Apache-2.0Stargazers:211Issues:8Issues:11

Awesome_Long_Form_Video_Understanding

Awesome papers & datasets specifically focused on long-term videos.

CEPE

[ACL 2024] Long-Context Language Modeling with Parallel Encodings

Language:PythonLicense:MITStargazers:141Issues:5Issues:5

SCLIP

Official implementation of SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

amazon-sagemaker-ground-truth-task-uis

Example task UIs for Amazon SageMaker Ground Truth

Language:HTMLLicense:MIT-0Stargazers:108Issues:10Issues:13

ControlMLLM

[NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'

Language:PythonLicense:Apache-2.0Stargazers:85Issues:3Issues:5

HA-DPO

Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization

Language:PythonLicense:Apache-2.0Stargazers:63Issues:4Issues:8

PAI

[ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs

Language:PythonLicense:MITStargazers:62Issues:2Issues:4

hallucination-foundation-model-survey

A Survey of Hallucination in Large Foundation Models

Q-LLM

This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"

VideoHallucer

VideoHallucer, The first comprehensive benchmark for hallucination detection in large video-language models (LVLMs)

Language:PythonLicense:MITStargazers:22Issues:5Issues:2

gist-icl

Repository for "GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks", NAACL'25 Best Student Paper.