REACH: Interpretability-Driven Feature Identification and Architecture Compression for Mu…
Explorar
Noticias de IA
22116 elementos — filtrados, clasificados y sin duplicados
Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions
TextHOI-3D: Text-to-3D Hand-Object Interaction via Discrete Multi-View Generation and Joi…
Last-Iterate Convergence of Optimistic Multiplicative Weight Update
Automated Creativity Evaluation of Language Models Across Open-Ended Tasks
RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation
Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent wi…
Can AI Reason Like an Urban Planner? Benchmarking Large Language Models Against Professio…
Probabilistic Salary Prediction with Graph Attention Networks and a Mixture Density Netwo…
TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search
Sparse probes and murky physics: a case study of interpretability challenges in a foundat…
Tree-Structured Orthonormal Decomposition of the Aitchison Simplex
Improving Cross-Format Robustness in Language Models with Multi-Format Training
Janus: A Benchmark for Goal-Conditioned Information Distortion in LLMs
Geometrically Averaged Hard Target Updates for Linear Q-Learning
Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Proce…
SCOPE: Sequential Causal Optimization of Process Interventions
HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent
MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean…
Adoption of Generative Artificial Intelligence in the German Software Engineering Industr…
Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models
Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept…
Divide-and-Conquer Modeling for the CTF-4-Science Lorenz Benchmark
TaCarla: A comprehensive benchmarking dataset for end-to-end autonomous driving
Quantifying Uncertainty in AI Visibility: A Statistical Framework for Generative Search M…
Temporal Sheaf Neural Networks with Dynamic Orthogonal Transport
Reasoning over Semantic IDs Enhances Generative Recommendation
The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
SAFE: An LLM-as-Verifier Framework for Evidence-Grounded Multi-Hop Reasoning
Prosociality by Coupling, Not Mere Observation: Homeostatic Sharing in an Inspectable Rec…