TILR identifies low-rank invariant subspaces from contrastive latent trajectory differences in LLMs and constrains interventions to them, improving paraphrase consistency by ~10% and reducing variance by up to 50%.
Trgp: Trust region gradient projection for continual learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
FINCH is a loss-adaptive learning-rate schedule that reduces forgetting by 93% on average during LLM fine-tuning while matching standard task performance across several benchmarks.
C-Flat Turbo accelerates continual learning by skipping redundant flatness gradients via direction-invariance observations and linear adaptive scheduling, delivering 1-1.25x speedup with comparable accuracy.
citing papers explorer
-
Invariant Reasoning Directions in Latent Trajectories of Language Models
TILR identifies low-rank invariant subspaces from contrastive latent trajectory differences in LLMs and constrains interventions to them, improving paraphrase consistency by ~10% and reducing variance by up to 50%.
-
Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates
FINCH is a loss-adaptive learning-rate schedule that reduces forgetting by 93% on average during LLM fine-tuning while matching standard task performance across several benchmarks.
-
A Faster Path to Continual Learning
C-Flat Turbo accelerates continual learning by skipping redundant flatness gradients via direction-invariance observations and linear adaptive scheduling, delivering 1-1.25x speedup with comparable accuracy.