Code release for "SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers" [NeurIPS D&B, 2024]

Explore the Multimodal “Aha Moment” on 2B Model

The official repository for the RealSyn dataset

[NeurIPS 2024] From Instance Training to Instruction Learning: Task Adapters Generation from Instructions

Training Large Language Model to Reason in a Continuous Latent Space

PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant refe…

[NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models

稷丰-首个开源中文农业多模态大模型

A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!

Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

METEOR: Evolutionary Journey of Large Language Models from Guidance to Self-Growth

PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment

Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).

Collection of AWESOME vision-language models for vision tasks

Real-time, fine-grained LLM synthetic data involves data of, by, and for LLMs.

A brief and partial summary of RLHF algorithms.

A curated list of awesome LLM Inference-Time Self-Improvement (ITSI, pronounced "itsy") papers from our recent survey: A Survey on Large Language Model Inference-Time Self-Improvement.

Building a comprehensive and handy list of papers for GUI agents

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Official code for Attention-driven GUI Grounding, AAAI2025

定时获取谷歌学术和arxiv论文的相关更新 (代码只有一个py文件，较简单有注释)

This is a repository for listing papers on scene graph generation and application.

2024中国翻墙软件VPN推荐以及科学上网避坑，稳定好用。对比SSR机场、蓝灯、V2ray、老王VPN、VPS搭建梯子等科学上网与翻墙软件，中国最新科学上网翻墙梯子VPN下载推荐，访问Chatgpt。