Krishna Kaasyap

KrishnaKaasyap

AI & ML interests

Test Time Training Multimodal & Inter-Modality Transfer Learning Mechanistic Interpretability Evolutionary Model Merging Swarm Intelligence of multiple models with different architectures and different algorithms MuZero approach to general tasks

Recent Activity

liked a model about 8 hours ago

baichuan-inc/Baichuan-M1-14B-Instruct

liked a model 5 days ago

microsoft/bitnet-b1.58-2B-4T

upvoted a collection 16 days ago

Llama 4

View all activity

Organizations

KrishnaKaasyap's activity

upvoted a collection 16 days ago

Llama 4

Collection

Llama 4 release • 10 items • Updated 16 days ago • 439

upvoted a collection 4 months ago

QwQ

Collection

Qwen with Questions • 6 items • Updated Mar 6 • 93

upvoted 2 collections 5 months ago

🎬 Video models

Collection

text-to-video & image-to-video models released by the Chinese community • 22 items • Updated 24 days ago • 4

🧠 Reasoning Models

Collection

9 items • Updated 24 days ago • 38

upvoted a collection 6 months ago

Llama-3.1-Nemotron-70B

Collection

SOTA models on Arena Hard and RewardBench as of 1 Oct 2024. • 6 items • Updated 7 days ago • 155

upvoted a paper 8 months ago

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Paper • 2408.12528 • Published Aug 22, 2024 • 52

upvoted 3 collections 8 months ago

upvoted an article 8 months ago

Article

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

Jul 23, 2024

• 232

upvoted a paper 8 months ago

VITA: Towards Open-Source Interactive Omni Multimodal LLM

Paper • 2408.05211 • Published Aug 9, 2024 • 49

upvoted 2 collections 9 months ago

Llama-3.1 Quantization

Collection

Neural Magic quantized Llama-3.1 models • 22 items • Updated Nov 22, 2024 • 44

Llama 3.1

Collection

This collection hosts the transformers and original repos of the Llama 3.1, Llama Guard 3 and Prompt Guard models • 11 items • Updated Dec 6, 2024 • 662

upvoted a paper 10 months ago

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Paper • 2406.16860 • Published Jun 24, 2024 • 61

upvoted 2 collections 10 months ago

SSMs

Collection

A collection of Mamba-2-based research models with 8B parameters trained on 3.5T tokens for comparison with Transformers. • 5 items • Updated 7 days ago • 27

Nemotron 4 340B

Collection

Nemotron-4: open models for Synthetic Data Generation (SDG). Includes Base, Instruct, and Reward models. • 4 items • Updated 7 days ago • 162