Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal Classification
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for…
Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against …
A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-C…
Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting
(Whose defaults?) Is artificial intelligence reorienting archaeological methods?
Geospatial AI, Dataverse Metadata, and the Study of Place-Based Government
X-RACE: XAI-assisted Recurrent neural network Attribution for Channel Estimation
Domain Elastic Transform: Bayesian Function Registration for High-Dimensional Scientific …
Automated multi-class wound assessment using dedicated instance segmentation models for b…
GRIPNet: Gaussian Radial Intensity Prior Guided Architecture for Pulmonary Nodule Detecti…
Counterfactual Marginalisation: Framework for Evaluating Robustness to Nuisance Variables
Studying Without a Syllabus: Task-Agnostic Environment Preprocessing
Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
When Validation Stops Learning: Auditing Update Admission for Continual Embodied Agents
Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real Wor…
Less can be More: What Aspects of Speech Drive End-of-Turn Detection
Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning
Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal…
New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models
A Fragility Spectrum for Recursive Language-Model Training
Exploring Second-Order Pattern Recognition in Speaker Recognition
A Mathematical Theory of Pragmatic Information
EGGROLL, Unrolled: Understanding and Improving Low-Rank Evolution Strategies at Scale
SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control
BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evalua…
Your Model Already Knows Don't Teach It, Learn to Ask It: Soft Prompting for Few-Shot Ada…
Extending SMT Solving with Non-Ground Clause Learning