LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring
arxiv.org·18h
🔧Systems-level optimizations for LLM serving
A Formal Framework for the Definition of 'State': Hierarchical Representation and Meta-Universe Interpretation
arxiv.org·18h
📊AI Performance Profiling
Building and Aligning Comparable Corpora
arxiv.org·18h
🧠Large Language Models (LLMs)
AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization
arxiv.org·18h
🧠Large Language Models (LLMs)
Lightweight Backbone Networks Only Require Adaptive Lightweight Self-Attention Mechanisms
arxiv.org·18h
⚙️AI Infrastructure Automation
HeQ: a Large and Diverse Hebrew Reading Comprehension Benchmark
arxiv.org·18h
🧠Large Language Models (LLMs)
Co-Reward: Self-supervised Reinforcement Learning for Large Language Model Reasoning via Contrastive Agreement
arxiv.org·1d
🧠Large Language Models (LLMs)
AI-Educational Development Loop (AI-EDL): A Conceptual Framework to Bridge AI Capabilities with Classical Educational Theories
arxiv.org·18h
⚡Real-time AI Systems
Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning
arxiv.org·18h
🧠Large Language Models (LLMs)
Relative Completeness of Incorrectness Separation Logic
arxiv.org·18h
✨Model optimizations in LLMs
Test-time Prompt Intervention
arxiv.org·18h
💬Prompt optimizations for LLM serving
Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation
arxiv.org·18h
🧠Large Language Models (LLMs)
MARS: A Meta-Adaptive Reinforcement Learning Framework for Risk-Aware Multi-Agent Portfolio Management
arxiv.org·18h
🤖Agents using LLMs
EHSAN: Leveraging ChatGPT in a Hybrid Framework for Arabic Aspect-Based Sentiment Analysis in Healthcare
arxiv.org·18h
🧠Large Language Models (LLMs)
ff4ERA: A new Fuzzy Framework for Ethical Risk Assessment in AI
arxiv.org·18h
📊AI Performance Profiling
Quantum-RAG and PunGPT2: Advancing Low-Resource Language Generation and Retrieval for the Punjabi Language
arxiv.org·18h
🧠Large Language Models (LLMs)
Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes
arxiv.org·18h
🧠Large Language Models (LLMs)
Stakeholder Perspectives on Digital Twin Implementation Challenges in Healthcare: Insights from a Provider Digital Twin Case Study
arxiv.org·18h
🔧Systems-level optimizations for LLM serving
Kernel-Based Sparse Additive Nonlinear Model Structure Detection through a Linearization Approach
arxiv.org·18h
🧠Large Language Models (LLMs)
Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR
arxiv.org·18h
🧠Large Language Models (LLMs)