Small 7B reasoning models were fine-tuned on synthetic and curated QFT problems using RL and SFT, yielding performance gains, error analysis, and public release of data and traces.
Tina: Tiny reasoning models via LoRA.arXiv preprint arXiv:2504.15777, 2025b
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
ALTO accelerates LoRA tuning up to 13.8x by monitoring loss trajectories for early stopping, using fused grouped GEMM with rank-local adapter parallelism, and combining intra- and inter-task scheduling for heterogeneous workloads without quality loss.
RL for LLM reasoning acts as sparse policy selection at high-entropy tokens already present in the base model, enabling ReasonMaxxer—an efficient contrastive method that recovers most RL gains at three orders of magnitude lower cost.
Alpha in LoRA outperforms learning-rate scaling, follows a square-root law with rank, and enables a minimalist LoRA-alpha method that improves performance across tasks.
Mixed-complexity procedural datasets provide up to 5x sample efficiency for RLVR on small models in low-data regimes, with low-to-high complexity generalization observed across counting, graph, and spatial tasks.
PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.
An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.
citing papers explorer
-
Low-Rank Adaptation Redux for Large Models
An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.