Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning
arxiv.org·1d
🔍Retrieval-augmented generation
Likelihood Matching for Diffusion Models
arxiv.org·10h
✨Model optimizations in LLMs
MOPrompt: Multi-objective Semantic Evolution for Prompt Optimization
arxiv.org·1d
💬Prompt optimizations for LLM serving
FinKario: Event-Enhanced Automated Construction of Financial Knowledge Graph
arxiv.org·1d
🔍Retrieval-augmented generation
A Methodological Framework for LLM-Based Mining of Software Repositories
arxiv.org·1d
💬Prompt optimizations for LLM serving
HeQ: a Large and Diverse Hebrew Reading Comprehension Benchmark
arxiv.org·1d
🔍Retrieval-augmented generation
Integrating clinical reasoning into large language model-based diagnosis through etiology-aware attention steering
arxiv.org·2d
🔍Retrieval-augmented generation
A Scalable Pipeline for Estimating Verb Frame Frequencies Using Large Language Models
arxiv.org·6d
✨Model optimizations in LLMs
The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models
arxiv.org·5d
💬Prompt optimizations for LLM serving
Detecting COPD Through Speech Analysis: A Dataset of Danish Speech and Machine Learning Approach
arxiv.org·1d
✨Model optimizations in LLMs
Merge-based syntax is mediated by distinct neurocognitive mechanisms: A clustering analysis of comprehension abilities in 84,000 individuals with language defic...
arxiv.org·10h
🔍Retrieval-augmented generation
DACTYL: Diverse Adversarial Corpus of Texts Yielded from Large Language Models
arxiv.org·2d
🔍Retrieval-augmented generation
Toward a Trustworthy Optimization Modeling Agent via Verifiable Synthetic Data Generation
arxiv.org·10h
🔧Systems-level optimizations for LLM serving
Kernel-Based Sparse Additive Nonlinear Model Structure Detection through a Linearization Approach
arxiv.org·1d
🔢Quantization of LLMs
SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought
arxiv.org·2d
💬Prompt optimizations for LLM serving
KCR: Resolving Long-Context Knowledge Conflicts via Reasoning in LLMs
arxiv.org·1d
💬Prompt optimizations for LLM serving
Quantum-RAG and PunGPT2: Advancing Low-Resource Language Generation and Retrieval for the Punjabi Language
arxiv.org·1d
🔍Retrieval-augmented generation
ProKG-Dial: Progressive Multi-Turn Dialogue Construction with Domain Knowledge Graphs
arxiv.org·1d
💬Prompt optimizations for LLM serving
Industrial LLM-based Code Optimization under Regulation: A Mixture-of-Agents Approach
arxiv.org·10h
🔧Systems-level optimizations for LLM serving
A Novel Multimodal Framework for Early Detection of Alzheimers Disease Using Deep Learning
arxiv.org·10h
⚡Real-time AI Systems