Cs-Ai
HQP: Sensitivity-Aware Hybrid Quantization and Pruning for Ultra-Low-Latency Edge AI Inference
Allocate Marginal Reviews to Borderline Papers Using LLM Comparative Ranking
Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity
JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks
Learning a Generative Meta-Model of LLM Activations
SaDiT: Efficient Protein Backbone Design via Latent Structural Tokenization and Diffusion Transformers
Bridging Explainability and Embeddings: BEE Aware of Spuriousness
Autoregressive Models for Knowledge Graph Generation
Calibration and Transformation-Free Weight-Only LLMs Quantization via Dynamic Grouping
Multimodal Iterative RAG for Knowledge-Intensive Visual Question Answering
Reparameterization Proximal Policy Optimization
Emergent Cognitive Convergence via Implementation: Structured Cognitive Loop Reflecting Four Theories of Mind
D-SCoRE: Document-Centric Segmentation and CoT Reasoning with Structured Export for QA-CoT Data Generation
Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia
FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models
Knowledgeable Language Models as Black-Box Optimizers for Personalized Medicine
Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement
Feature Identification via the Empirical NTK
Multi-view biomedical foundation models for molecule-target and property prediction
Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration
Next-generation cyberattack detection with large language models: anomaly analysis across heterogeneous logs
A Unified Framework for LLM Watermarks
