AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs
arxiv.org·7h
💬Prompt Engineering
Flag this post
Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
arxiv.org·7h
💬Prompt Engineering
Flag this post
Latent Domain Prompt Learning for Vision-Language Models
arxiv.org·7h
💬Natural Language Processing
Flag this post
Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
arxiv.org·7h
💬Prompt Engineering
Flag this post
The Illustrated NeurIPS 2025: A Visual Map of the AI Frontier
newsletter.languagemodels.co·21h
📝NLP
Flag this post
Effectiveness of LLMs in Temporal User Profiling for Recommendation
arxiv.org·7h
💬Prompt Engineering
Flag this post
Efficient Test-Time Retrieval Augmented Generation
arxiv.org·7h
💬Prompt Engineering
Flag this post
Do Math Reasoning LLMs Help Predict the Impact of Public Transit Events?
arxiv.org·7h
💬Prompt Engineering
Flag this post
A generative AI teaching assistant for personalized learning in medical education
nature.com·12h
💬Prompt Engineering
Flag this post
STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack
arxiv.org·7h
💬Natural Language Processing
Flag this post
FLoRA: Fused forward-backward adapters for parameter efficient fine-tuning and reducing inference-time latencies of LLMs
arxiv.org·7h
📝NLP
Flag this post
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
arxiv.org·7h
💬Prompt Engineering
Flag this post
Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
arxiv.org·7h
💬Prompt Engineering
Flag this post
Complex QA and language models hybrid architectures, Survey
arxiv.org·7h
💬Prompt Engineering
Flag this post
OpenAI Releases Double-Checking Tool For AI Safeguards That Handily Allows Customizations
forbes.com·4h
💬Prompt Engineering
Flag this post
Contrastive Knowledge Transfer and Robust Optimization for Secure Alignment of Large Language Models
arxiv.org·1d
💬Prompt Engineering
Flag this post
Deflanderization for Game Dialogue: Balancing Character Authenticity with TaskExecution in LLM-based NPCs
💬Prompt Engineering
Flag this post
Testing Unnatural Prompt Engineering Across Five Large Language Models
blog.codeminer42.com·3d
💬Prompt Engineering
Flag this post
Confounding Factors in Relating Model Performance to Morphology
arxiv.org·7h
💬Natural Language Processing
Flag this post
Loading...Loading more...