Stars
Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average speedup of 34.93x
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
NSF CAREER proposal template: http://pgbovine.net/NSF-CAREER-proposal.htm
Embodied Agent Interface (EAI): Benchmarking LLMs for Embodied Decision Making (NeurIPS D&B 2024 Oral)
TStar is a unified temporal search framework for long-form video question answering
Training VLM agents with multi-turn reinforcement learning
Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
A paper list for spatial reasoning
A paper list that includes world models or generative video models for embodied agents.
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.
Pytorch code for Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners
CLASP - Contrastive Language-Aminoacid Sequence Pretraining
A curated list of Visual Question Answering(VQA)(Image/Video Question Answering),Visual Question Generation ,Visual Dialog ,Visual Commonsense Reasoning and related area.
A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).
Source code for UIUC_IE_PIPELINE_FINEGRAINED
Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
A Question Answering system built on top of the Apache UIMA framework.
A question answering system for biomedical literature
One single script to run IE pipeline
Pytorch code of for our CVPR 2018 paper "Neural Baby Talk"
An open-source NLP research library, built on PyTorch.