A Machine Learning Based Search for Lunar Anomalies
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Control-Oriented Scenario Tree Construction through Reinforcement Learning
GeoPhysAdapter: Scale-Matched Geophysical Adaptation for Cross-Domain Landslide Mapping w…
Warp-free Cross-view Geo-localization via Feature-space Consensus Mining
WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for E…
Beyond the Capability Boundary: Zeroth-Order Optimization for Self-Evolving LLM Agents
MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts
Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution
Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models
RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation
Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model
FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning
Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers
FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning
Failure-Aware Long-Form Translation: Design and Implementation of a Recoverable LLM Trans…
From Relevance to Execution Utility: Reward-Aware Dynamic Execution Gating for Skill-Base…
UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Inst…
UniMoFlow: Grounding Instruction-Driven 3D Human Motion Editing in Generation
SpeedTuning: Speeding Up Policy Execution with Lightweight Reinforcement Learning
RAVEN-Eval: Rubric-Guided Automatic Evaluation for AI Video Generation Models Based on LM…
View-Adaptive Renderer for View-Consistent 2D-to-3D Generation
Beyond Routing Weights: Faithful Response-Level Interpretation of Mixture-of-Experts Rewa…
Alignment has a Fantasia Problem
Social World Models
CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools
Progressive Alignment of Recommender Foundation Model through Multi-Phase Post-Training
Provable Training Data Identification for Large Language Models
A primer on optimal transport for causal inference with observational data