OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning
Explorar
Noticias de IA
21272 elementos — filtrados, clasificados y sin duplicados
Generic Interpretation Approach for Transformer Models Incorporating Heterogenous Attenti…
Can We Formally Verify Neural PDE Surrogates? SMT Compilation of Small Fourier Neural Ope…
Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-…
Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning
VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild
Quantum Machine Learning-based 6G edge Network: Enabling Adaptive Communication and Model…
Measuring Massive Multitask Chinese Understanding
RAGe: A Retrieval-Augmented Generation Evaluation Framework
Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities
Manboformer: Learning Gaussian Representations via Spatial-temporal Attention Mechanism
EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection
ASTRA: Communication-Efficient Acceleration for Multi-Device Transformer Inference
Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an An…
Clinical Validation of the Melanoscope AI Mobile Dermoscopy Clinical Decision Support Sys…
Supervised Distributional Reduction via Optimal Transport and Dependence Maximization
Developing an Intelligent Job Recommendation System Using Semantic Retrieval and Explaina…
PrunePath: Towards Highly Structured Sparse Language Models
Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning
HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning
The Optimal Sample Complexity of Linear Contracts
EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization …
Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via …
Evaluation of AI Ethics Tools in Language Models: A Developers' Perspective Case Study
Can Quantum Federated Learning Withstand Circuit-Level Backdoors?
UniMaia: Steering Chess Policies with Language for Human-like Play
Locality-Aware Redundancy Pruning for LLM Depth Compression
Snippet-Driven Supply Chain Discovery with LLMs: Scaling Visibility in China
Efficient Pre-Training of LLMs through Truncated SVD Layers
When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?