1 9 9

aman prakash

MLap

AI & ML interests

None yet

Recent Activity

reacted to clem's post with 🔥 5 days ago

I was chatting with @peakji , one of the cofounders of Manu AI, who told me he was on Hugging Face (very cool!). He shared an interesting insight which is that agentic capabilities might be more of an alignment problem rather than a foundational capability issue. Similar to the difference between GPT-3 and InstructGPT, some open-source foundation models are simply trained to 'answer everything in one response regardless of the complexity of the question' - after all, that's the user preference in chatbot use cases. Just a bit of post-training on agentic trajectories can make an immediate and dramatic difference. As a thank you to the community, he shared 100 invite code first-come first serve, just use “HUGGINGFACE” to get access!

liked a model 14 days ago

tomg-group-umd/huginn-0125

upvoted a paper 14 days ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

View all activity

Organizations

None yet

MLap's activity

upvoted a paper 14 days ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7 • 123

upvoted an article about 1 month ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.16k

upvoted 3 articles about 2 months ago

Article

We now support VLMs in smolagents!

Jan 24

• 92

Article

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

Jan 23

• 153

Article

SmolVLM - small yet mighty Vision Language Model

Nov 26, 2024

• 220

upvoted a collection about 2 months ago

Small VLM

Collection

9 items • Updated Jul 5, 2024 • 7

upvoted an article about 2 months ago

Article

Simplifying Alignment: From RLHF to Direct Preference Optimization (DPO)

•

Jan 19

• 15

upvoted a paper 3 months ago

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion

Paper • 2412.04424 • Published Dec 5, 2024 • 61