Nishith Jain

KingNish's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

Nested Learning: The Illusion of Deep Learning Architectures

Paper • 2512.24695 • Published 6 days ago • 27

upvoted an article 15 days ago

view article

Article

Decoding Strategies in Large Language Models

• 

Oct 29, 2024

•

102

upvoted an article 25 days ago

view article

Article

New in llama.cpp: Model Management

• 

26 days ago

•

104

upvoted an article 28 days ago

view article

Article

Muon vs MuonClip vs Muon+AdamW for Fine-Tuning

• 

28 days ago

•

13

upvoted an article about 1 month ago

view article

Article

Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand

• 

Dec 4, 2025

•

63

upvoted 2 papers about 1 month ago

PretrainZero: Reinforcement Active Pretraining

Paper • 2512.03442 • Published Dec 3, 2025 • 47

Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate

Paper • 2501.17703 • Published Jan 29, 2025 • 59

upvoted 6 collections about 2 months ago

Kandinsky 5.0 Video Lite

Collection

Kandinsky 5.0 Video Lite is a lightweight 2B model that generates up to 10-second SD videos from English and Russian prompts with high visual quality. • 9 items • Updated 23 days ago • 13

Kandinsky 5.0 Video Lite Diffusers

Collection

Kandinsky 5.0 Video Lite is a lightweight 2B model that generates up to 10-second SD videos from English and Russian prompts with high visual quality. • 8 items • Updated 23 days ago • 5

Kandinsky 5.0 Video Pro Diffusers

Collection

Kandinsky 5.0 Video Pro is a 19B model that generates high-quality HD videos from English and Russian prompts with controllable camera motion. • 4 items • Updated 23 days ago • 10

Kandinsky 5.0 Video Pro

Collection

Kandinsky 5.0 Video Pro is a 19B model that generates high-quality HD videos from English and Russian prompts with controllable camera motion. • 5 items • Updated 23 days ago • 15

Kandinsky 5.0 Image Lite

Collection

Kandinsky 5.0 Image Lite is a 6B DiT-based model that generates and edits HD images from English and Russian text prompts with high visual quality. • 4 items • Updated 23 days ago • 16

Kandinsky 5.0 Image Lite Diffusers

Collection

4 items • Updated 23 days ago • 8

upvoted 3 papers about 2 months ago

MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism

Paper • 2511.11373 • Published Nov 14, 2025 • 12

Extracting alignment data in open models

Paper • 2510.18554 • Published Oct 21, 2025 • 9

TiDAR: Think in Diffusion, Talk in Autoregression

Paper • 2511.08923 • Published Nov 12, 2025 • 120

upvoted 2 papers 2 months ago

Kosmos: An AI Scientist for Autonomous Discovery

Paper • 2511.02824 • Published Nov 4, 2025 • 6

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

Paper • 2510.25602 • Published Oct 29, 2025 • 77

upvoted a collection 2 months ago

interesting architecture

Collection

27 items • Updated 5 days ago • 4

upvoted a paper 2 months ago

Latent Diffusion Model without Variational Autoencoder

Paper • 2510.15301 • Published Oct 17, 2025 • 49