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

upvoted a collection 3 days ago

Nemotron-H

liked a model 12 days ago

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

upvoted a collection 19 days ago

MedGemma Release

View all activity

Organizations

KrishnaKaasyap's activity

upvoted a collection 3 days ago

Nemotron-H

Collection

Mamba-Transformer hybrid models • 10 items • Updated 4 days ago • 25

liked a model 12 days ago

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

Text Generation • Updated 13 days ago • 200k • • 722

upvoted a collection 19 days ago

MedGemma Release

Collection

Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 4 items • Updated 12 days ago • 157

upvoted 2 collections about 1 month ago

Qwen2.5-Omni

Collection

End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 7 items • Updated 21 days ago • 143

Qwen3

Collection

40 items • Updated 21 days ago • 748

liked 3 models about 2 months ago

upvoted a collection 2 months ago

Llama 4

Collection

Llama 4 release • 13 items • Updated Apr 29 • 526

liked 3 models 3 months ago

Qwen/Qwen2.5-Omni-7B

Any-to-Any • Updated Apr 30 • 354k • 1.65k

CohereLabs/c4ai-command-a-03-2025

Text Generation • Updated May 1 • 5.53k • • 352

Qwen/QwQ-32B

Text Generation • Updated Mar 11 • 293k • • 2.77k

New activity in RekaAI/reka-flash-3 3 months ago

Context length and reasoning length?

#6 opened 3 months ago by

KrishnaKaasyap

liked a model 3 months ago

RekaAI/reka-flash-3

Updated Mar 13 • 3.63k • 373

liked 2 models 4 months ago

deepseek-ai/Janus-Pro-1B

Any-to-Any • Updated Feb 1 • 20.6k • 444

deepseek-ai/Janus-Pro-7B

Any-to-Any • Updated Feb 1 • 98k • 3.41k

liked a model 5 months ago

deepseek-ai/DeepSeek-R1-Distill-Llama-70B

Text Generation • Updated Feb 24 • 199k • • 688

New activity in deepseek-ai/DeepSeek-R1 5 months ago

Is this the same as DeepSeek-R1 (Preview) mentioned on LiveCodeBench?

❤️ 1

#10 opened 5 months ago by

KrishnaKaasyap

New activity in deepseek-ai/DeepSeek-R1-Zero 5 months ago

Hail CCP!!! God bless Chyna!

❤️ 😎 19

#3 opened 5 months ago by

mnemojeet

Thank you deepseek

👍 ❤️ 29

#8 opened 5 months ago by

teknium