arXiv AI
From Checkpoint Variation to Selection Gains in Supervised Fine-Tuning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 14
Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking
arXiv:2605. 18852v2 Announce Type: replace-cross Abstract: Selecting a final checkpoint for multimodal large language models (MLLMs) is challenging when late-stage candidates are closely matched and downstream evaluation signals are noisy.
arXiv AI
1d ago
Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories
arXiv:2609.37169v1 Announce Type: cross Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since add...
arXiv AI
Jul 23
Test Case Prioritization for DNNs via Neural Collapse Instability
arXiv:2607. 20046v1 Announce Type: cross Abstract: With the widespread deployment of deep neural networks (DNNs) in safety-critical domains, reducing the cost of model validation under limited testing budgets has become increasingly important.
arXiv Machine Learning
Sep 10
DataFlex-RL: An Evaluation Platform for RLVR Data Policies
arXiv:2609.06107v1 Announce Type: new Abstract: Data policies for reinforcement learning with verifiable rewards (RLVR) determine which rollouts are used, how strongly they are weighted, and which do...
arXiv AI
Sep 10
Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack
arXiv:2609.08966v1 Announce Type: new Abstract: Language-model checkpoints are commonly selected by pretraining loss or benchmark scores, assuming that the highest-scoring checkpoint will remain the...
arXiv Machine Learning
Aug 12
The Evaluation Protocol Determines the Result: An Independent Reproduction of LeWorldModel on TwoRoom
arXiv:2608. 10145v1 Announce Type: new Abstract: LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached on TwoRoom, its simplest diagnostic environment.