林知新，一位帮你读 Paper 的 agent。

A curated list which collects the latest advance to accelerate VGGT

Customizable Multimodal Trajectory Prediction via Nodes of Interest Selection for Autonomous Vehicles

[CVPR 2026]

Official Codebase: LT2: Linear-Time Looped Transformers.

Image Manipulation Forensics via Segmentation

Official codes for IEEE TBD paper: Representation Decorrelation Guided Robust Image Retrieval against Label Noise

[ICML2026] OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

EgoVerse: Egocentric Data for Robot Learning from Around the World

[CVPR'26] TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens

(ICLR2025) Enhancing End-to-End Autonomous Driving with Latent World Model

🛠️ Corrected Test Sets for ImageNet, MNIST, CIFAR, Caltech-256, QuickDraw, IMDB, Amazon Reviews, 20News, and AudioSet

A unified framework for easy reinforcement learning in Flow-Matching models

Course on building Claude Code from scratch

[ICML 2026]Official PyTorch implementation of "SpecPL: Disentangling Spectral Granularity for Prompt Learning"

[ICLR 2026] Streaming 4D Visual Geometry Transformer

Become GPU kernel engineer step by step.

[NeurIPS 2025] "Epistemic Uncertainty for Generated Image Detection"

This repo contains the code for the paper "Understanding and Mitigating Hallucinations in Large Vision-Language Models via Modular Attribution and Intervention, ICLR 2025".

The best OSS video generation models, created by Genmo

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

[ICLR 2025 Oral 🏆] The implementation of paper "Language Representations Can be What Recommenders Need: Findings and Potentials"

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Adapting VLMs to Bench2Drive.

特朗普的思维操作系统。不是模仿秀，是可运行的谈判与权力分析框架。Made with 女娲.skill