Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Trai…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts
Hyperbolic Geometry for Open-World Object Detection in Remote Sensing Imagery
Synergistic Vision-Language Reinforcement Enables Scalable On-Demand Analysis across Dive…
Elsewise: Authoring Open-ended Interactive Narrative with Possibility Space Visualization
Meta-RL with Bayesian Linear Task Models
Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?
Tactile Memory with Soft Robot: Robust Object Insertion via Masked Encoding and Soft Wrist
Generative AI for Analysts
Teacher Geometry Shapes Learnability in Teacher-Student Networks
Distilling Image Prototypes for Guided Test-Time Adaptation
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in…
LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents
One Loop, Two Gains: Can Active Learning win the Lottery for Free?
From Plausible to Actionable: A Position on LLM Self-Explanations
Kernel-Complexity Edge Sanitization for Training-Free Defense against Structural Graph At…
PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations
False positive bias in AI-powered speech-based cognitive screening for multilingual Engli…
Characterizing Text Branch Sensitivity in Medical Vision-Language Segmentation via Eviden…
Cascading Gradient Inversion via LT-Code Inspired Peeling in Federated Learning
Improving Cross-Lingual Token Representations by Adding a Pinch of SALT
Revisiting the Shape Convention of Transformer Language Models
Spec-Harness: Measuring and Improving Behavioral Adequacy of LLM-Synthesized Formal Speci…
RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems
Shifting Relational Paradigms for Affective Computing: Affective Resonance, Vitality Affe…
RobustSGPO: Search-Space Control for Agent Harness Evolution
CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi…
Myocardial Strain Drift Correction in Deep Learning Based Ultrasound Tracking
RAU: Reference-based Anatomical Understanding with Vision Language Models
Predicting Estimated Times of Restoration for Electrical Outages Using Longitudinal Tabul…