ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
Explorar
Noticias de IA
22318 elementos — filtrados, clasificados y sin duplicados
Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases
The Caf\'e in Amsterdam: When the Incumbent Becomes the Oracle
Classifying daily activities needs posture, reconstructing them needs motion
Evaluation Ability Does Not Imply Optimization Utility: LLM-as-a-Judge Signals in Closed-…
SteinGate: Tail-Sensitive Safe Reinforcement Learning via Stein Discrepancy
CoDiffGRN: Rethinking Gene Regulatory Network Inference via the BEELINE-KGC Benchmark and…
Active Beyond-Diagonal RIS Empowered Heterogeneous Edge Computing: A Distributional Reinf…
AI in Cyberpsychology: A systematic literature review of Cybersecurity enhancement by usi…
SemaDiff: Identifying Semantic-Changing Commits with Generated Code and Tests
Privacy Preserving Recommender Systems Balancing Personalization with Privacy
STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting
Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing
EdgeFaaS: A Function-based Framework for Edge Computing
Agentic orchestration: Enterprise AI organizations have a deployment problem, not a platf…
China Sends Robots Out Into the World to Learn How to Be Human
Dysco: Dynamic Subspace Boosting to Mitigate LoRA Interference in Federated Learning
Beyond scalar losses: calibrating segmentation models via gradient vector field surgery
SD-MAR: Multi-image Analytical Reasoning via Synthetic Data and Reinforcement Learning
AI Isn’t Smarter Than a Baby—Yet
Leveraging unlabelled data for generalizable neural population decoding
Linear Independent Component Analysis via Optimal Transport
MetaPerch: Learning from metadata for bioacoustics foundation models
Model Routing Is Simple. Until It Isn’t.
Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment f…
Early Adoption of Agentic Coding Tools by GitHub Projects
Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth
RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Ima…
PlumeQuant: Uncertainty-aware consistency assessment of methane plume masks and emission-…
SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning