MDP-GRPO: Stabilized Group Relative Policy Optimization for Multi-Constraint Instruction …
Explorar
Noticias de IA
21864 elementos — filtrados, clasificados y sin duplicados
Metamorphic Testing with the Rashomon Set: Explanation Faithfulness in Machine Learning
ATT-CR: Adaptive Triangular Transformer for Cloud Removal
Deep Learning-based 3D Oral Cavity Reconstruction Using 2D Intraoral Images
World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Sy…
Learning of Robot Safety Policies via Adversarial Synthetic Scenarios
Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach
Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Adv…
LadderMan: Learning Humanoid Perceptive Ladder Climbing
Deciphering Two Training Clocks in Grokking via Deep Linear Network Theory with Condition…
EEGDancer: Dynamic Emotion Latent Space Masked Modeling with Reinforcement Learning for E…
GenTI: Benchmarking LLMs for Autonomous IDPS Rule Generation for Unseen Attacks
Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads
Benchmarks in Leipzig
Consistency Training Along the Transformer Stack
Emotion-Aware Image Generation from Korean Diary Text via LLM-based Prompt Translation an…
Human Oversight and Overload: Two Hidden and Costly Burdens of AI-Assisted Software Engin…
DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models
UNIVID: Unified Vision-Language Model for Video Moderation
Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models
Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form…
ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation
Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation
When Surface Form Changes Moderation Decisions: A Paired Study of Code-Mixed Workflow Ins…
Dimensionality Reduction for Cyberattack Classification: A Comparative Evaluation of PCA …
InfoShield: Privacy-Preserving Speech Representations for Mental Health Screening via Inf…
Conformal Risk-Averse Decision Making with Action Conditional Guarantee
ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer
Knowledge Activation: AI Skills as the Institutional Knowledge Primitive for Agentic Soft…
Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evalu…