SeqRoute: Global Budget-Aware Sequential LLM Routing via Offline Reinforcement Learning
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Subspace-Guided Semantic and Topological Invariant Registration for Annotation-Free Ultra…
Constraint-Anchored Attribution: Feasibility-Certified Counterfactuals and Bonferroni-PAC…
Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
KYA: A Framework-Agnostic Trust Layer for Autonomous Systems with Verifiable Provenance a…
AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachroni…
A general tensor-structured compression scheme for efficient large language models
READER: Reasoning-Enhanced AI-Generated Text Detection
SafeCtrl-RL: Inference-Time Adaptive Behaviour Control for LLM Dialogue via RL-Driven Pro…
Specification-Based Code-Text-Code Reengineering for LLM-Mediated Software Evolution
Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised…
Influence-Inspired Spectral Rotations for Extreme Low-Bit LLM Quantization
Abduction-Deduction Entanglement: Domain Generalization via Representation Transplants
Inference-Time Alignment of Diffusion Models via Trust-Region Iterative Twisted Sequentia…
Generalizable Vision-Language Few-Shot Adaptation with Predictive Prompts and Negative Le…
FragmentNet: Adaptive Graph Fragmentation for Graph-to-Sequence Molecular Representation …
The Impact of Large Language Models on Open-source Innovation: Evidence from GitHub Copil…
Quantifying Empirical Compute-Supervision Tradeoffs in RLVR
Double Self-weighted Multi-view Clustering via Adaptive View Fusion
Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression
JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data
SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver
AI-generated podcasts: Synthetic Intimacy and Cultural Mistranslation in NotebookLM's Aud…
On the Epistemic Uncertainty of Overparametrized Neural Networks
A Two-Dimensional Framework for AI Agent Design Patterns: Cognitive Function and Executio…
AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games
UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
Learning Preference-Based Objectives from Clinical Narratives for Dynamic Sepsis Treatment