Matrix Phylogeny: Compact Spectral Fingerprints for Trap-Robust Preconditioner Selection
arxiv.orgยท1d
๐Ÿ”Retrieval-augmented generation
Flag this post
ShadowLogic: Backdoors in Any Whitebox LLM
arxiv.orgยท1d
๐Ÿ”งSystems-level optimizations for LLM serving
Flag this post
Bayesian Natural Gradient Fine-Tuning of CLIP Models via Kalman Filtering
arxiv.orgยท1d
โœจModel optimizations in LLMs
Flag this post
Learning Sparse Approximate Inverse Preconditioners for Conjugate Gradient Solvers on GPUs
arxiv.orgยท2d
๐Ÿง Large Language Models (LLMs)
Flag this post
Thought-For-Food: Reasoning Chain Induced Food Visual Question Answering
arxiv.orgยท1d
๐Ÿง Large Language Models (LLMs)
Flag this post
BeetleFlow: An Integrative Deep Learning Pipeline for Beetle Image Processing
arxiv.orgยท1d
โš™๏ธAI Infrastructure Automation
Flag this post
Eyes on Target: Gaze-Aware Object Detection in Egocentric Video
arxiv.orgยท1d
โšกReal-time AI Systems
Flag this post
Fleming-VL: Towards Universal Medical Visual Reasoning with Multimodal LLMs
arxiv.orgยท1d
๐Ÿง Large Language Models (LLMs)
Flag this post
CoT-Saliency: Unified Chain-of-Thought Reasoning for Heterogeneous Saliency Tasks
arxiv.orgยท1d
๐Ÿง Large Language Models (LLMs)
Flag this post
Region-Aware Reconstruction Strategy for Pre-training fMRI Foundation Model
arxiv.orgยท1d
๐Ÿ”Retrieval-augmented generation
Flag this post
VISTA Score: Verification In Sequential Turn-based Assessment
arxiv.orgยท2d
๐Ÿง Large Language Models (LLMs)
Flag this post
Coverage Analysis and Optimization of FIRES-Assisted NOMA and OMA Systems
arxiv.orgยท1d
๐Ÿ”งSystems-level optimizations for LLM serving
Flag this post
Adding New Capability in Existing Scientific Application with LLM Assistance
arxiv.orgยท1d
๐Ÿง Large Language Models (LLMs)
Flag this post
Progressive Translation of H&E to IHC with Enhanced Structural Fidelity
arxiv.orgยท1d
๐Ÿ”ขQuantization of LLMs
Flag this post
A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios
arxiv.orgยท1d
๐Ÿง Large Language Models (LLMs)
Flag this post