Adversarial Training for Robust Coverage Network under Worst-case Facility Losses
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective P…
Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis
Model Merging on Loss Landscape: A Geometry Perspective
Beyond Linearity in Attention Projections: The Case for Nonlinear Queries
RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and…
Olaf-World: Orienting Latent Actions for Video World Modeling
MatFormBench: A Benchmarking Evaluation Framework for Target-Driven Materials Formulation
MetaSICL: Adapting Audiroty LLM via Meta Speech In-Context Learning
Beyond Transfer Accuracy: Faithful Circuits for Controlled Low-Resource Adaptation
Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Le…
Faithfulness Evaluation for Decoder-only LLM Attributions with Controlled Retained Inform…
An In-Vitro Study on Cross-Lingual Generalization in Language Models
Continual Model-Based Reinforcement Learning with Hypernetworks
Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behaviora…
DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning
To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs
AnchorDiff: Training-Free Concept Grounding for MM-DiTs via Anchor-Based Graph Propagation
Anchor: Mitigating Artifact Drift in Agent Benchmark Generation
Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory
Modeling Agentic Technical Debt and Stochastic Tax: A Standalone Framework for Measuremen…
Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable…
Emergent Causal-Geometric Dynamics Across Depth in Large Language Models
Graph is a Substrate Across Data Modalities
When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Contr…
Managing Uncertainty in LLM-Generated Procedural Knowledge for Virtual Laboratory Planning
Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction