Trending

Gemma 3 QAT Models: Bringing AI to Consumer GPUs

Show HN: Keep your PyTorch model in VRAM by hot swapping code

Turing-Drawings

Pushing the Limits of LLM Quantization via the Linearity Theorem

Novel color via stimulation of individual photoreceptors at population scale

An Image of the Australian Desert Illuminates Satellite Pollution

Packing Input Frame Context in Next-Frame Prediction Models for Video Generation

Cache loop and memory loss in GPT – a user-side fix (tested with GPT itself)

How to Write a Fast Matrix Multiplication from Scratch with Tensor Cores

[D] PhD (non-US) → Research Scientist jobs in CV/DL at top companies—how much DSA grind is essential?

When I Started Building AI Agents… Here's the Stack That Finally Made Sense

50 days building a tiny language model from scratch, what I’ve learned so far

The Qwen Tokenizer Seems to be better than the Deepseek Tokenizer - Testing a 50-50 SLERP merge of the same two models (Qwen3-8B and DeepSeek-R1-0528-Qwen3-8B) with different tokenizers

[P] TinyFT: A lightweight fine-tuning library

[R]Fine tuning of CLIP on a specific task

[R] A proxy for info encoding: a high condition number indicates that the unit has learned to selectively amplify & compress information. Through the lens of information theory, it indicates the unit's ability to transform high-entropy, uncertain input into lower-entropy, more predictable output.

[D] Applying COCONUT continuous reasoning into a learnt linear layer that produces sampling parameters (temp, top-k, top-p, etc.) for the current token?

Finished the Coursiv AI course. Here's what I learned and how it's actually helped me

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

Lym

Save item

Wan2.1-T2V-1.3B-Self-Forcing-VACE-Addon-Experiment

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

WongKinYiu

Save item

yolov7

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

microsoft

Save item

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

deepspeedai

Save item

DeepSpeed

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

huggingface

Save item

transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

modelscope

Save item

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

openxla

Save item

xla

A machine learning compiler for GPUs, CPUs, and ML accelerators