Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics
Hybrid Retrieval-Augmented Generation with Knowledge Graph Expansion, RRF Fusion, and Per…
HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models
Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Rein…
Collective creativity in hybrid societies
Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Cli…
A Survey of Transformer-based Language Models with Focus on Efficiency
From Feature Interaction to Feature Transport - A Unified Block for Scalable Recommendati…
A Data-Driven Multimodal Method for Early Detection of Coordinated Abnormal Behaviors in …
ClaimReceipt: Verifying Evidence Sufficiency and Coverage in Agent Evaluations
Convergence Theory of Knowledge Distillation in Asynchronous P2P Gossip Learning Network
Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models
Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge
Post-Training Language Models for Gold-Medal Performance in Coding Competitions
CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
Thinking effort aligns between humans and reasoning models in abductive reasoning
Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimization
LoRA-GA$^2$: Low Rank Adaptation with Multi-step Gradient Adaptive Alignment
OutageDiT: A Generative Foundation Model for Power Outage Forecasting and Scenario Simula…
Agent Memory Is a Surface for Endogenous Authorization Laundering
Loom: Weaving Diagnostic Strands into Free-Text Consensus via Embedding-Space Reweighting
Accurate in space, unreliable in time: how LLMs represent national cultural change
Interpretable Symptom Vectors for Depression in a Large Language Model
CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging
Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-W…
Zeta-Lite: A Concurrent, Branchable In-Browser SQL Database for Agentic Memory
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance