Scalable Question Answering on Long Documents with Divide-and-Conquer

Code for the paper "Searching Privacy Risks in Multi-Agent Systems via Simulation"

Code for the paper: Generative Interfaces for Language Models

[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents

Specification for creating reliable LLM-based conversational agents

Framework and toolkits for building and evaluating collaborative agents that can work together with humans.

Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups

Code for the paper: Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping

[ICLR 2025, Oral] EmbodiedSAM: Online Segment Any 3D Thing in Real Time

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Crawl a site to generate knowledge files to create your own custom GPT from a URL

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

This is the oficial repository for "DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules".

This is the pytorch implementation for the paper: *Anyview: Generalizable Indoor 3D Object Detection with Variable Frames*

Official Implementation of Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization

[ICLR 2024] Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"

✨✨Latest Advances on Multimodal Large Language Models

MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips

OpenChat: Advancing Open-source Language Models with Imperfect Data

Code/Data for the paper: "LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding"

Code for Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach

[ECCV 2024] 3D Small Object Detection with Dynamic Spatial Pruning

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

Code/Data for the paper: "Auditing Gender Presentation Differences in Text-to-Image Models"

Source codes for the paper "Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints"

A playbook for systematically maximizing the performance of deep learning models.

Source codes for the paper "Robustness of Demonstration-based Learning Under Limited Data Scenario"