Mizhi - A lightweight vehicle detection and viewpoint classification model optimized for mobile browsers

[CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

A repo to train your own small sarvam-30b model

ECCV 2026 paper template

Hypernetworks that update LLMs to remember factual information

official code for the paper "GenSeg-R1: RL-Driven Vision–Language Grounding for Fine-Grained Referring Segmentation"

🚀 Daily AI Research Digest: Tracking breakthroughs in AI/NLP/CV/Robotics with dynamic updates and paper navigation.

Masked Depth Modeling for Spatial Perception

Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"

Interactive visualizations of the geometric intuition behind diffusion models.

Full course on becoming AI researcher from scratch

A Mixture Density RNN for generating musical touchscreen interactions.

A playground for Mixture Density Networks.

Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding

RL gym for vision language models written in JAX

[NeurIPS 2025 Spotlight] "SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation."

ONNX models of VGGT

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

[TPAMI 2025] Towards Visual Grounding: A Survey

Morphology-adaptive muscle-driven locomotion via attention mechanisms

Solve Visual Understanding with Reinforced VLMs