PEEK: Picking Essential frames via Efficient Knowledge distillation
Paper • 2605.31029 • Published • 20
AI & ML interests
Democratizing access to useful AI tools and resources for journalists
Recent Activity
View all activity
YannisTevissen
authored a
paper about 1 month ago
Post
215
Reinforcement learning can sometimes lead to emergent behavior through much simpler training setups compared to large scale pre-training.
I explored this idea by running a small GRPO experiment on Qwen3.5 4B, and the results were pretty exciting.
Hypothesis: improving visual mathematical reasoning may also improve the model’s ability to transcribe LaTeX from images.
I wrote a short breakdown of the experiment here:
https://hanzlajavaid.github.io/blog/grpo-experiment-exploring-emergent-properties/
I explored this idea by running a small GRPO experiment on Qwen3.5 4B, and the results were pretty exciting.
Hypothesis: improving visual mathematical reasoning may also improve the model’s ability to transcribe LaTeX from images.
I wrote a short breakdown of the experiment here:
https://hanzlajavaid.github.io/blog/grpo-experiment-exploring-emergent-properties/
1aurent
authored a
paper 4 months ago
1aurent
authored a
paper 5 months ago
vumichien
authored 2
papers 9 months ago
brunatrevelin
authored a
paper about 1 year ago
Share Datasets of News Broadcasts
#14 opened about 1 year ago
by 
constantinSch
fdaudens
updated a
Space about 1 year ago
[Media Reporter Seeking Journalists Who Use AI in Their Work — Even if It’s Under the Radar]
#13 opened about 1 year ago
by 
xeutrope
aiscraper
#4 opened about 1 year ago
by 
cyberconnectbel
fdaudens
updated a
Space over 1 year ago
fdaudens
published a
Space over 1 year ago
Post
2199
Hi community,
Few days back, I posted about my ongoing research on making reasoning mamba models and I found great insights from the community.
Today, I am announcing an update to the model weights. With newer checkpoints, the Falcon3 Mamba R1 model now outperforms very large transformer based LLMs (including Gemini) for Formal Logic questions of MMLU. It scores 60% on formal logic which is considered a tough subset of questions in MMLU.
I would highly appreciate your insights and suggestions on this new checkpoint.
Model Repo: hanzla/Falcon3-Mamba-R1-v0
Chat space: hanzla/Falcon3MambaReasoner
Few days back, I posted about my ongoing research on making reasoning mamba models and I found great insights from the community.
Today, I am announcing an update to the model weights. With newer checkpoints, the Falcon3 Mamba R1 model now outperforms very large transformer based LLMs (including Gemini) for Formal Logic questions of MMLU. It scores 60% on formal logic which is considered a tough subset of questions in MMLU.
I would highly appreciate your insights and suggestions on this new checkpoint.
Model Repo: hanzla/Falcon3-Mamba-R1-v0
Chat space: hanzla/Falcon3MambaReasoner
fdaudens
updated a
Space over 1 year ago
fdaudens
updated 2
collections over 1 year ago
Post
4120
Hello community,
I want to share my work of creating a reasoning mamba model
I used GRPO over Falcon3 Mamba Instruct to make this model. It generates blazing fast response while building good logic to answer challenging questions.
Give it a try:
Model repo: hanzla/Falcon3-Mamba-R1-v0
Space: hanzla/Falcon3MambaReasoner
Looking forward to community feedback.
I want to share my work of creating a reasoning mamba model
I used GRPO over Falcon3 Mamba Instruct to make this model. It generates blazing fast response while building good logic to answer challenging questions.
Give it a try:
Model repo: hanzla/Falcon3-Mamba-R1-v0
Space: hanzla/Falcon3MambaReasoner
Looking forward to community feedback.
- 2 replies
Post
1276
Gemma 3 is a game changer for on device multimodal applications.
Try for yourself how a 4 billion parameter model can be so good.
hanzla/PlaygroundGemma3
Try for yourself how a 4 billion parameter model can be so good.
hanzla/PlaygroundGemma3
- 1 reply
fdaudens
published a
Space over 1 year ago