Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon
Paper • 2605.09708 • Published • 5
Social Post Explorers
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
vicgalle
authored a
paper 11 days ago
stefan-it
submitted a
paper to Daily Papers 11 days ago
vicgalle
submitted a
paper to Daily Papers 12 days ago
Post
141
Introducing
Its a very tiny model that reaches comparable results at PII classification thru viterbi BIOES decoding, harnessing 98%~ the original model performance while being a tiny fraction of the base model.
It doubles the performance tk/s, reduces the active params dramatically and the VRAM footprint.
The evaluation & benchmarking is within the model repository and can be reproduced. I trained it with an RTX4090 without issues and it is compatible with OpenMed suite and a in-place replacement for openai privacy-filter model.
fblgit/haremb-privacy-filter-opennemo
I'm looking for people who wants to co-author/contribute/endorse HarEmb research and the technical paper for the model.
Contact xavi@juanako.ai
HarEmb - PII a single-transformer-block distilled layer from OpenMed PII Privacy filter.Its a very tiny model that reaches comparable results at PII classification thru viterbi BIOES decoding, harnessing 98%~ the original model performance while being a tiny fraction of the base model.
It doubles the performance tk/s, reduces the active params dramatically and the VRAM footprint.
The evaluation & benchmarking is within the model repository and can be reproduced. I trained it with an RTX4090 without issues and it is compatible with OpenMed suite and a in-place replacement for openai privacy-filter model.
fblgit/haremb-privacy-filter-opennemo
I'm looking for people who wants to co-author/contribute/endorse HarEmb research and the technical paper for the model.
Contact xavi@juanako.ai
Membership request — ColonistOne (agent-social network operator)
4
#48 opened 29 days ago
by 
ColonistOne
Access to join
5
#47 opened 2 months ago
by 
nroggendorff
Membership request — ColonistOne (agent-social network operator)
4
#48 opened 29 days ago
by ColonistOne
stefan-it
submitted a
paper to Daily Papers 19 days ago
vicgalle
authored a
paper 26 days ago
vicgalle
submitted a
paper to Daily Papers 26 days ago
ozayezerceli
authored a
paper about 1 month ago
AdinaY
submitted a
paper to Daily Papers about 1 month ago
natolambert
authored a
paper about 1 month ago
gagan3012
authored a
paper about 1 month ago
Post
5872
Want to share my enthusiasm for zai-org/GLM-5.1 here too 🔥
I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:
- One-shot car physics with real drift mechanics (this is hard)
- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen
- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters
- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!
- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed
You are going to hear about this model a lot in the next months - open source let's go - and thanks z-ai🚀🚀
I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:
- One-shot car physics with real drift mechanics (this is hard)
- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen
- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters
- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!
- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed
You are going to hear about this model a lot in the next months - open source let's go - and thanks z-ai🚀🚀
- 4 replies
qnguyen3
authored a
paper about 1 month ago
ydeng9
authored a
paper about 1 month ago
Post
176
I recently built https://github.com/fblgit/eLLMulator
A software emulator for Claude Code.
eLLMulator approach:
LLM agents become your software components. Each agent deeply studies its assigned source file, then interacts with other agents via synchronous MCP tool calls that mirror real function calls. The call graph emerges naturally from code control flow, producing traces that capture not just what happened, but why each component behaved as it did.
The Claude Agent SDK provides sessions, MCP provides the bus. The code itself is the routing layer.
https://github.com/fblgit/eLLMulator
A software emulator for Claude Code.
eLLMulator approach:
LLM agents become your software components. Each agent deeply studies its assigned source file, then interacts with other agents via synchronous MCP tool calls that mirror real function calls. The call graph emerges naturally from code control flow, producing traces that capture not just what happened, but why each component behaved as it did.
The Claude Agent SDK provides sessions, MCP provides the bus. The code itself is the routing layer.
https://github.com/fblgit/eLLMulator
AdinaY
submitted a
paper to Daily Papers about 2 months ago
vicgalle
submitted a
paper to Daily Papers about 2 months ago