arXiv:2609.04108v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) and on-policy distillation (OPD) have emerged as…
Category: AI
CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation
arXiv:2609.04083v1 Announce Type: cross Abstract: MLLM-based embedding models remain limited in compositional retrieval, often failing to distinguish…
A Non-Formulable Theorem: A Fundamental Limit of Finite Syntactic Systems and Its Consequences for Security and AI
arXiv:2609.04086v1 Announce Type: cross Abstract: For every coherent and sufficiently expressive finite syntactic system S, we prove the existence of at…
PatchBench: Evaluating AI Agents for Vulnerability Patching
arXiv:2609.04075v1 Announce Type: cross Abstract: AI agents have recently demonstrated strong performance in automated vulnerability patching. However,…
Subspace Inference Enables Efficient Active Reward Learning from Preferences
arXiv:2609.04066v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) has emerged as a powerful yet sample-inefficient…
Architecting memory and storage in the AI era
The era of AI inference has arrived. Imagine a healthcare system analyzing millions of data points in real time to accelerate life-saving medical…
TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation Models
arXiv:2609.04071v1 Announce Type: cross Abstract: Pathology foundation models improve transferable representation learning for histopathology, but recent…
Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach
arXiv:2609.04028v1 Announce Type: cross Abstract: The geometric morphology of deposited filaments can significantly influence the structural performance…
Representational alignment yields generalizable safety in language models
arXiv:2609.04022v1 Announce Type: cross Abstract: Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods…
The Blind Spot in 2D Infants’ Pose Estimation:Robust Learning from Noisy Annotations
arXiv:2609.04009v1 Announce Type: cross Abstract: Noisy annotations pose a significant challenge for supervised deep learning, as neural networks rely on…