Quantifying Edits Decay in Fine-tuned LLMs
arxiv.org·17h
Flag this post
Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time
arxiv.org·17h
Flag this post
Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs
arxiv.org·17h
Flag this post
Fuzzy Label: From Concept to Its Application in Label Learning
arxiv.org·17h
Flag this post
TimeSense:Making Large Language Models Proficient in Time-Series Analysis
arxiv.org·17h
Flag this post
A large expert-annotated single-cell peripheral blood dataset for hematological disease diagnostics
nature.com·2h
Flag this post
Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
arxiv.org·17h
Flag this post
Controlled Vocabularies
Flag this post
Anchors in the Machine: Behavioral and Attributional Evidence of Anchoring Bias in LLMs
arxiv.org·17h
Flag this post
CAMP-HiVe: Cyclic Pair Merging based Efficient DNN Pruning with Hessian-Vector Approximation for Resource-Constrained Systems
arxiv.org·17h
Flag this post
Wasm: A Pipeline for Constructing Structured Arabic Interleaved Multimodal Corpora
arxiv.org·17h
Flag this post
Walking the Tightrope of LLMs for Software Development: A Practitioners' Perspective
arxiv.org·17h
Flag this post
Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder
arxiv.org·17h
Flag this post
4 open‑source apps I use to run AI locally
xda-developers.com·7h
Flag this post
Loading...Loading more...