How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-Dimens…
When LLM Decompilers Recompile More and Preserve Less
RegionFed: Federated Learning for Personalized Query Understanding in Heterogeneous Retai…
Not All LLM Reasoning is Visible in the Chain-of-Thought
Phase Transition Frequency as a Training Time Predictor of Test Accuracy in ResNets
A Human-in-the-Loop Framework for AI-Assisted Scoring in Large-Scale Writing Assessment
Beyond Co-purchase Relation: Evolution of Complementary Recommendations at Allegro
MCPO: Modality-Contrastive Preference Optimization for Multimodal Chain-of-Thought Compre…
VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition
How a Chatbot's Response Style Shapes a Classroom: A Multi-Agent Simulation of Students C…
One Diffusion Model, Two Roles: Guided Trajectory Planning and Safety-Critical Scenario G…
How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human…
TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks
Qlippy: A Retrieval-Augmented GenAI Assistant for Reproducible Quantum Workflows and Expe…
Beyond Stationarity in Time Series: Discovering Causal Structures and Latent Regimes via …
ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems
RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training
SimFuse3D: Source-Guided Target Simulation and Confidence-Guided Multi-Stage Localization…
Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand…
Attention-guided super-resolution of 4D flow MRI in carotid arteries
RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Re…
PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmar…
Adaptation Interfaces for In-Context Tabular Foundation Models in Time-to-Event Prediction
Dynamic Heterogeneous Graph Representation Learning: A Survey
Can Activation Steering Capture Multidimensional Authorship Style?
Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution
Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models