Selectivity and Shape in the Design of Forward-Forward Goodness Functions
Paper • 2604.13081 • Published
Social Post Explorers
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Q-bert
authored a
paper 15 days ago
qnguyen3
authored a
paper 26 days ago
Post
169
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
Muennighoff
submitted a
paper to Daily Papers about 1 month ago
1aurent
authored a
paper about 1 month ago
Q-bert
submitted a
paper to Daily Papers about 1 month ago
Q-bert
authored a
paper about 1 month ago
Post
1472
Releasing Flimmer today — a video LoRA training toolkit for WAN 2.1 and 2.2 that covers the full pipeline from raw footage to trained checkpoint.
The standout feature is phased training: multi-stage runs where each phase has its own learning rate, epochs, and dataset, with the checkpoint carrying forward automatically. Built specifically with WAN 2.2's dual-expert MoE architecture in mind.
Data prep tools are standalone and output standard formats — they work with any trainer, not just Flimmer.
Early release, building in the open. LTX support coming next.
http://github.com/alvdansen/flimmer-trainer
The standout feature is phased training: multi-stage runs where each phase has its own learning rate, epochs, and dataset, with the checkpoint carrying forward automatically. Built specifically with WAN 2.2's dual-expert MoE architecture in mind.
Data prep tools are standalone and output standard formats — they work with any trainer, not just Flimmer.
Early release, building in the open. LTX support coming next.
http://github.com/alvdansen/flimmer-trainer
gsarti
authored 2
papers 2 months ago
chargoddard
authored a
paper 2 months ago
Post
1862
Just open-sourced LoRA Gym with Timothy - production-ready training pipeline for character, motion, aesthetic, and style LoRAs on Wan 2.1/2.2, built on musubi-tuner.
16 training templates across Modal (serverless) and RunPod (bare metal) covering T2V, I2V, Lightning-merged, and vanilla variants.
Our current experimentation focus is Wan 2.2, which is why we built on musubi-tuner (kohya-ss). Wan 2.2's DiT uses a Mixture-of-Experts architecture with two separate experts gated by a hard timestep switch - you're training two LoRAs per concept, one for high-noise (composition/motion) and one for low-noise (texture/identity), and loading both at inference. Musubi handles this dual-expert training natively, and our templates build on top of it to manage the correct timestep boundaries, precision settings, and flow shift values so you don't have to debug those yourself. We've also documented bug fixes for undocumented issues in musubi-tuner and validated hyperparameter defaults derived from cross-referencing multiple practitioners' results rather than untested community defaults.
Also releasing our auto-captioning toolkit for the first time. Per-LoRA-type captioning strategies for characters, styles, motion, and objects. Gemini (free) or Replicate backends.
Current hyperparameters reflect consolidated community findings. We've started our own refinement and plan to release specific recommendations and methodology as soon as next week.
Repo: github.com/alvdansen/lora-gym
- 2 replies
1aurent
authored a
paper 3 months ago
alokabhishek
submitted a
paper to Daily Papers 3 months ago
alokabhishek
authored a
paper 3 months ago
Post
949
After tinkering with Gemma Scope 2, I now have an mechanistic explanation of why Winsorization was as effective as it was in my ablation experiments on Gemma 3 12B Instruct. In short, the activation for the BOS token overwhelms everything else. Gemma Scope 2 deliberately did not train on the BOS token. Winsorization capped the magnitude of the BOS token, allowing the activations of other tokens to be compared.
google/gemma-scope-2-12b-it
google/gemma-scope-2-12b-it
Post
524
The contrarian in me is wary of the irrational exuberance over MoltBook. Nothing so far has struck me as being unpredictable. We knew already that LLMs were good at roleplay, to the point where some users started to think of their chatbots as soulmates (only to lament when the underlying model was pulled), and that chatbots can fall into conversational basins when even two instances are allowed to chat with each other at length. The appearance of memes that postdate training cutoff is suspect, which implies at the very least that humans have injected something at the level of prompts or content/context to introduce them into conversation like a Chekhov's Gun. And we know that security holes are common in vibe coding, attended or not.
- 12 replies
Beegbrain
authored 2
papers 3 months ago
Beegbrain
submitted a
paper to Daily Papers 3 months ago