Distributionally Robust Listwise Preference Optimization
Explorar
Noticias de IA
22318 elementos — filtrados, clasificados y sin duplicados
COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows
Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editi…
Separating Expert Retention from Autonomous Source Inference in Raw-ECG-Replay-Free Conti…
Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry
Autonomous discovery of traffic laws with AI traffic scientists
Spatial Support Matters: Geometry-Aware Graph Fusion for Rainfall Field Reconstruction
Profit-Based Counterfactual Explanations for Product Improvement: A Case Study of Manga S…
Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Sym…
Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation
Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian W…
When Should Service Agents Reconsider? Difficulty-Routed Control in Customer-Service Oper…
Auto-FL-Research: Agentic Search for Federated Learning Algorithms
Agentic AI 101 Survey Research Paper: The Stack Between a Model and a System
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
From SRA to Self-Flow: Data Augmentation or Self-Supervision?
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Inter…
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
Optimal Stabilizer Testing and Learning with Limited Quantum Memory
WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs
GAP-GDRNet: Geometry-Aware Monocular Visual Pose Sensing on a Single-Target Synthetic Spa…
SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios
NEvo: Neural-Guided Evolutionary Video Synthesis for Dynamic Visual Selectivity
A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets
Dual-Selective Network for Domain-Incremental Change Detection
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval
AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom Netw…