- Seattle
- https://xinw.ai/
- @xinw_ai
Stars
When do we not need larger vision models?
Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 40+ benchmarks
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Official code for "TOAST: Transfer Learning via Attention Steering"
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023
Official code for "Top-Down Visual Attention from Analysis by Synthesis" (CVPR 2023 highlight)
MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts (ICLR 2022)
Official repo of our ECCV 2022 paper "GIMO: Gaze-Informed Human Motion Prediction in Context"
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning (CoRL 2021)
Pretrained language model with 100B parameters
Aqueduct is no longer being maintained. Aqueduct allows you to run LLM and ML workloads on any cloud infrastructure.
Official code for `Visual Attention Emerges from Recurrent Sparse Reconstruction' (ICML 2022)
User-friendly secure computation engine based on secure multi-party computation
source code for CVPR'22 paper "Unknown-Aware Object Detection: Learning What You Don’t Know from Videos in the Wild"
CVPR 2022, Robust Contrastive Learning against Noisy Views
Codebase for Image Classification Research, written in PyTorch.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Code and models for ICCV2021 paper "Robust Object Detection via Instance-Level Temporal Cycle Confusion".
A scheduler for spatial DNN accelerators that generate high-performance schedules in one shot using mixed integer programming (MIP)
Official implementation of the CVPR 2022 paper "DETReg: Unsupervised Pretraining with Region Priors for Object Detection".
A curated list of egocentric (first-person) vision and related area resources
Is a geometric model required to synthesize novel views from a single image?
Simple project webpage template. Originally used in Colorful Image Colorization. ECCV, 2016.
Quasi-Dense Similarity Learning for Multiple Object Tracking, CVPR 2021 (Oral)