Calibration Across Layers: Understanding Calibration Evolution in LLMs
arxiv.org·1d
🧠Large Language Models (LLMs)
Flag this post
Balanced Multimodal Learning via Mutual Information
arxiv.org·1d
🧠Large Language Models (LLMs)
Flag this post
Identifying the Periodicity of Information in Natural Language
arxiv.org·2d
🧠Large Language Models (LLMs)
Flag this post
Beyond Visualization: Building Decision Intelligence Through Iterative Dashboard Refinement
arxiv.org·2d
🔍Retrieval-augmented generation
Flag this post
Personalized AI Scaffolds Synergistic Multi-Turn Collaboration in Creative Work
arxiv.org·2d
🔍Retrieval-augmented generation
Flag this post
ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
arxiv.org·1d
🔍Retrieval-augmented generation
Flag this post
Analyzing Sustainability Messaging in Large-Scale Corporate Social Media
arxiv.org·1d
🧠Large Language Models (LLMs)
Flag this post
Application of predictive machine learning in pen & paper RPG game design
arxiv.org·1d
📊AI Performance Profiling
Flag this post
Ideology-Based LLMs for Content Moderation
arxiv.org·5d
🧠Large Language Models (LLMs)
Flag this post
PORTool: Tool-Use LLM Training with Rewarded Tree
arxiv.org·5d
🧠Large Language Models (LLMs)
Flag this post
Deep Learning Approach to Anomaly Detection in Enterprise ETL Processes with Autoencoders
arxiv.org·1d
Model optimizations in LLMs
Flag this post
Reevaluating Self-Consistency Scaling in Multi-Agent Systems
arxiv.org·1d
🧠Large Language Models (LLMs)
Flag this post
Measuring Machine Companionship: Scale Development and Validation for AI Companions
arxiv.org·1d
🧠Large Language Models (LLMs)
Flag this post
Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories
arxiv.org·1d
🤖Agents using LLMs
Flag this post
PROPEX-RAG: Enhanced GraphRAG using Prompt-Driven Prompt Execution
arxiv.org·1d
🧠Large Language Models (LLMs)
Flag this post
FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts
arxiv.org·1d
🧠Large Language Models (LLMs)
Flag this post