Composed Historical Image Retrieval by Modeling Temporal Representations
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Europe's Climate Ambition Under Scrutiny: Evidence from Deep Learning Emission Projections
An Empirical Benchmark of Deep Time-Series Models for Smart Meter Energy Forecasting
DynCur-Geo: Dynamic Curiosity Reward Shaping for Multimodal Active Geo-Localization
Reinforced Planning with Latent World Models
TranslatePsy-AfriSLM: High-Quality Data Scaling For Low-Resource Machine Translation
Change Point--Aware Evaluation and Re-Calibration of PPG-Based Blood Pressure Estimation
CDGP: Contrastive Dual Gaussian Processes for Weakly Supervised Anomaly Segmentation
Teach a Molmo2Fish: Towards interactive fish tracking with natural language guidance
Off-Manifold Collapse in Guided Protein Language Models
SPARC: Subspace Position-Aware Robust Few-Shot Calibration for Distribution-Shifted Indus…
Beyond receptive fields: sequence-pooled normalization can supply most of a sequence labe…
AI boosted homework scores, then exam scores dropped: study
NanoSleep: A Parameter-Efficient Hybrid Temporal Convolutional Network for Single-Channel…
SemanticSlider3D: Training-Free Continuous Semantic Editing for 3D Objects
FinRCA-Bench: Benchmarking Evidence Retrieval and Reasoning for Financial AI Systems
StateTrace: An Object-Centric Framework for Hidden-State Spatiotemporal Reasoning in Long…
Pairwise Ranking Outperforms Single-Action RL for Offline Explanation Selection: A Practi…
DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn …
GCNO: Gramian Chebyshev Neural Operator for Physics-Based Compression of Wireless Channels
A decodability criterion predicts when hidden-state selection beats majority voting in la…
DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt …
Toward Personal Intelligence Through Cooperative Observation
Memory Is Communication: The Frontier Between Remembering and Signaling
Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection
FairNVT: Fair Classification via Noise Injection in Vision Transformers
Self-Distillation as a Performance Recovery Mechanism for LLMs: Counteracting Compression…
Language Family Matters: Evaluating LLM-Based ASR Across Linguistic Boundaries
Adversarial Data Modeling in Epidemiology
ChannelFlow-Tools: A Configuration-Driven Pipeline for Generating Machine-Learning-Ready …