Trending

Optimizing Tool Selection for LLM Workflows with Differentiable Programming

Parametric shape optimization with differentiable FEM simulation

Just Ask for Generalization

Nvidia Is Full of Shit

A new, 200% faster DeepSeek R1-0528 variant appears from German lab

You will own nothing and be happy (Stop Killing Games)

Chasing Lost Languages

LooksMapping

AV1@Scale: Film Grain Synthesis, The Awakening

128GB VRAM for ~$600. Qwen3 MOE 235B.A22B reaching 20 t/s. 4x AMD MI50 32GB.

[D] What resources would Theoretical ML researchers recommend to understand to pursue research.

An analytic theory of creativity in convolutional diffusion models.

[R] Post Transformer Architecture R&D

Finetuning a youtuber persona without expensive hardware or buying expensive cloud computing

[P] Training Cascade R-CNN (ResNet-101 + FPN) on Custom Dataset for Solar Panel Detection

Need help building a real-time voice AI agent

Displays, imaging and sensing: New blue fluorophore breaks efficiency records in both solids and solutions

Anyone else feel like working with LLM libs is like navigating a minefield ?

chatdoc.com

Save item

OCRFlux-3B

Task: image-text-to-text

DeepSeek

Save item

DeepSeek-R1-0528

Kyutai

Save item

stt-1b-en_fr

Task: automatic-speech-recognition

lightx2v

Save item

Wan2.1-T2V-14B-StepDistill-CfgDistill

Task: text-to-video

OpenAI

Save item

whisper-large-v3

Task: automatic-speech-recognition

NVIDIA

Save item

Cosmos-Predict2-2B-Text2Image

Task: text-to-image

Guande He

Save item

Self-Forcing

Task: text-to-video

Tencent

Save item

HunyuanVideo-Avatar

Task: image-to-video

Beijing Academy of Artificial Intelligence

Save item

RoboBrain2.0-7B

Task: robotics

sdatkinson

Save item

neural-amp-modeler

Neural network emulator for guitar amplifiers.

jax-ml

Save item

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

NVIDIA

Save item

Megatron-LM

Ongoing research training transformer models at scale

mikel-brostrom

Save item

boxmot

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

microsoft

Save item

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

danielgatis

Save item

rembg

Rembg is a tool to remove images background

Sanster

Save item

IOPaint

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

coqui-ai

Save item

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

deepspeedai

Save item

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.