Ties
PulseAugur coverage of Ties — every cluster mentioning Ties across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Research: Non-uniform LoRA ranks boost AI model merging accuracy
A new research paper challenges the conventional practice of using uniform LoRA ranks when merging fine-tuned AI models. The study demonstrates that allowing individual experts to have different LoRA ranks can improve m…
-
New AlignMerge framework preserves LLM alignment during model merging
Researchers have developed AlignMerge, a novel framework for merging large language models (LLMs) that explicitly preserves alignment and safety properties. Unlike previous methods that can inadvertently degrade alignme…
-
New study explores adapting ASR for child speech while retaining adult performance
Researchers have explored methods for adapting Automatic Speech Recognition (ASR) systems to better understand child speech while retaining performance on adult speech. The study compared techniques like full fine-tunin…
-
New method InterCorrect enhances fairness in speech recognition for diverse groups
Researchers have developed a new method called InterCorrect to improve the fairness of Automatic Speech Recognition (ASR) systems, particularly for individuals belonging to multiple demographic groups. The approach invo…
-
New method InterCorrect enhances ASR fairness for diverse demographic groups
Researchers have developed a new method called InterCorrect to improve the fairness of automatic speech recognition (ASR) systems, particularly for individuals belonging to multiple demographic groups. The approach invo…
-
New framework optimizes AI model merging using Bayesian optimization
Researchers have developed MOBO-Merge, a novel framework for optimizing model merging parameters. This approach treats merge-parameter selection as a multi-objective Bayesian optimization problem, allowing for efficient…
-
Model merging creates unified cross-domain code clone detector
Researchers have explored model merging techniques to create a unified model for cross-domain clone detection, addressing the fragmentation crisis caused by specialized deep learning detectors. Methods like parameter me…
-
Model merging matches joint RL in AppWorld benchmark, study finds
A new research paper analyzes the effectiveness of model merging techniques in reinforcement learning, comparing them to joint multi-task training. The study found that merging independently trained Qwen3-8B models on t…
-
Researchers explore model merging techniques for combining AI capabilities
Two new arXiv papers explore the emerging field of model merging, which combines independently trained neural networks without requiring access to original training data. The first paper introduces algorithms like C$^2$…