Research desk
An annotated reading list. Every entry is credited to its original authors, with a note on what it changes once the idea meets a real system.
3 entries
Reformulates preference learning so the reward model can be folded into the policy in closed form. The result is a single supervised objective over preference pairs, with no separate reward model and no reinforcement learning loop.
Backpropagates through a frozen 4-bit quantized base model into a small set of low-rank adapters. The approach brings fine-tuning of large models down to a single consumer GPU while holding quality close to full 16-bit tuning.
Freezes the pretrained weights and injects trainable low-rank matrices into each layer instead. The number of trainable parameters drops by several orders of magnitude, adapters are small enough to swap at runtime, and training cost falls with them.
The architectures and pre-training results everything else stands on.
3 entries
Grounding a model in documents you actually own.
4 entries
Getting a model to show its work, and checking the work.
5 entries
Models that call tools, hold state, and finish multi-step jobs.
6 entries
Changing what a model does without retraining all of it.
3 entries
Steering outputs toward what a person would accept.
3 entries
How you know it works before a customer finds out it does not.
5 entries