Nishith Jain's picture

Nishith Jain

KingNish

·

AI & ML interests

AI is fun actually.

Recent Activity

updated a dataset 1 day ago

KingNish/nonee

published a dataset 1 day ago

KingNish/nonee

upvoted a paper 4 days ago

Extracting alignment data in open models

View all activity

Organizations

upvoted a paper 4 days ago

Extracting alignment data in open models

Paper • 2510.18554 • Published 27 days ago • 8

upvoted a paper 5 days ago

TiDAR: Think in Diffusion, Talk in Autoregression

Paper • 2511.08923 • Published 6 days ago • 83

upvoted a paper 11 days ago

Kosmos: An AI Scientist for Autonomous Discovery

Paper • 2511.02824 • Published 13 days ago • 3

upvoted a paper 15 days ago

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

Paper • 2510.25602 • Published 19 days ago • 69

upvoted a collection 22 days ago

interesting architecture

25 items • Updated 28 days ago • 3

upvoted a paper 22 days ago

Latent Diffusion Model without Variational Autoencoder

Paper • 2510.15301 • Published Oct 17 • 48

upvoted an article 25 days ago

Article

Sentence Transformers is joining Hugging Face!

27 days ago

•

82

upvoted a collection 29 days ago

🎆 October 2025 - China Open Source Highlights

30 items • Updated 12 days ago • 12

upvoted a paper about 1 month ago

Learning to Reason as Action Abstractions with Scalable Mid-Training RL

Paper • 2509.25810 • Published Sep 30 • 5

upvoted a paper about 2 months ago

RLP: Reinforcement as a Pretraining Objective

Paper • 2510.01265 • Published Sep 26 • 40

upvoted an article about 2 months ago

Article

There is no such thing as a tokenizer-free lunch

Sep 25

•

88

upvoted a collection about 2 months ago

neucodec

We introduce NeuCodec, a 0.8kbps audio codec that outputs audio at 24kHz. • 6 items • Updated Oct 9 • 4

upvoted a changelog 2 months ago

Changelog

Emoji Autocomplete in Discussions and Posts

Sep 11

• 67

upvoted an article 2 months ago

Article

Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers

Sep 11

•

163

upvoted a collection 3 months ago

DeepSeek-V3.1

4 items • Updated Sep 22 • 245

upvoted a paper 3 months ago

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float

Paper • 2504.11651 • Published Apr 15 • 31

upvoted a collection 4 months ago

SmolDocling datasets

Datasets used to train SmolDocling • 6 items • Updated Jul 31 • 31

upvoted a paper 4 months ago

Seedance 1.0: Exploring the Boundaries of Video Generation Models

Paper • 2506.09113 • Published Jun 10 • 102

upvoted an article 4 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

Jul 8

•

724

upvoted a collection 4 months ago

🧠 SmolLM3

Smol, multilingual, long-context reasoner • 14 items • Updated Oct 9 • 84