Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Sp…
arXiv cs.AI Research & Papers
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Soci…
arXiv cs.AI Research & Papers
GENESIS: Harnessing AI Agents for Autonomous 6G RAN Synthesis, Research, and Testing
arXiv cs.AI Research & Papers
Tracing Computation Density in LLMs
arXiv cs.AI Research & Papers
GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Pos…
arXiv cs.AI Research & Papers
Constructing Industrial-Scale Optimization Modeling Benchmark
arXiv cs.AI Research & Papers
Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended L…
arXiv cs.AI Research & Papers
Developing a Totally Unimodular Linear Program for Optimal Conformance Checking: When and…
arXiv cs.AI Research & Papers
Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty
arXiv cs.AI Research & Papers
Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts …
arXiv cs.AI Research & Papers
From Norms to Indicators (N2I-RAG): An Agentic Retrieval-Augmented Generation Framework f…
arXiv cs.AI Research & Papers
Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User Hist…
arXiv cs.AI Research & Papers
GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation
arXiv cs.AI Research & Papers
VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents
arXiv cs.AI Research & Papers
Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and…
arXiv cs.AI Research & Papers
Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions
arXiv cs.AI Research & Papers
Geometrically Constrained Outlier Synthesis
arXiv cs.AI Research & Papers
Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility
arXiv cs.AI Research & Papers
Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcem…
arXiv cs.AI Research & Papers
DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation …
arXiv cs.AI Research & Papers
Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Reliability
arXiv cs.AI Research & Papers
Plans for Evaluating Structured Generative Search Summaries
arXiv cs.AI Research & Papers
GEM: Geometric Entropy Mixing for Optimal LLM Data Curation
arXiv cs.AI Research & Papers
Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
arXiv cs.AI Research & Papers
Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Te…
arXiv cs.AI Research & Papers
Strategies for Guiding LLMs to Use Software Design Patterns: A Case of Singleton
arXiv cs.AI Research & Papers
When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Det…
arXiv cs.AI Research & Papers
Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models
arXiv cs.AI Research & Papers
FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-…
arXiv cs.AI Research & Papers
When Does Adaptive Guidance Help? Belief-Aware Privileged Distillation for Autonomous Dri…