Show newer

CRAFT: Cost-aware Expert Replica Allocation with Fine-Grained Layerwise Estimations arxiv.org/abs/2603.28768 .DC .LG

Spark-LLM-Eval: A Distributed Framework for Statistically Rigorous Large Language Model Evaluation arxiv.org/abs/2603.28769 .DC .CL .LG

ZEUS: An Efficient GPU Optimization Method Integrating PSO, BFGS, and Automatic Differentiation arxiv.org/abs/2603.28770 .DC

Ray Tracing Cores for General-Purpose Computing: A Literature Review arxiv.org/abs/2603.28771 .DC

Federated Inference for Heterogeneous LLM Communication and Collaboration arxiv.org/abs/2603.28772 .DC

UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG arxiv.org/abs/2603.28773 .IR .CL .LG

DF-ACBlurGAN: Structure-Aware Conditional Generation of Internally Repeated Patterns for Biomaterial Microtopography Design arxiv.org/abs/2603.28776 .CV .AI .LG

Bridge-RAG: An Abstract Bridge Tree Based Retrieval Augmented Generation Algorithm With Cuckoo Filter arxiv.org/abs/2603.26668 .IR .AI .CL

ReCQR: Incorporating conversational query rewriting to improve Multimodal Image Retrieval arxiv.org/abs/2603.26669 .IR .AI .LG

Mitigating Forgetting in Continual Learning with Selective Gradient Projection arxiv.org/abs/2603.26671 .OC .LG

Can AI be a Teaching Partner? Evaluating ChatGPT, Gemini, and DeepSeek across Three Teaching Strategies arxiv.org/abs/2603.26673 .CY .AI

Co-designing a Social Robot for Newcomer Children's Cultural and Language Learning arxiv.org/abs/2603.26674 .RO .CY .HC

GeoBlock: Inferring Block Granularity from Dependency Geometry in Diffusion Language Models arxiv.org/abs/2603.26675 .CL .LG

Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift arxiv.org/abs/2603.26676 .CY .AI .HC

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.