🤖 AI 前沿资讯

HuggingFace

The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements

We consider the problem of support recovery for sparse binary signals from noisy linear measurements. For sparse Gaus...

AI 聚合

2026-09-11

HuggingFace

SchemeArena: Factorized Stress Testing of Scheming in LLM Agents

We study scheming in LLM agents, in which agents covertly pursue misaligned goals. Our focus is to understand how sch...

AI 聚合

2026-09-11

HuggingFace

A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware

AI-powered search products such as ChatGPT search, Google's AI Overviews, and Perplexity provide LLM-synthesized answ...

AI 聚合

2026-09-11

HuggingFace

PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

Sequential memory agents process long documents by reading chunks one after another while maintaining a compact memor...

AI 聚合

2026-09-11

arXiv

From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning

Plane geometry remains a significant challenge in AI, requiring the integration of visual perception and mathematical...

AI 聚合

2026-09-10

arXiv

Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs

Multimodal large language models (MLLMs) process hundreds or thousands of visual tokens per image, incurring prohibit...

AI 聚合

2026-09-10

arXiv

Cyber-Financial Contagion: Modeling the Propagation of an AI Vendor Compromise Through the Banking System

The banking system now depends on a small set of shared artificial intelligence vendors for fraud screening, credit d...

AI 聚合

2026-09-10

arXiv

OmniMed-FL: A Robust Multimodal Federated Learning Framework for Clinical Diagnosis

Simultaneous assessment of medical imaging and patient records is often required in clinical diagnosis. However, stan...

AI 聚合

2026-09-10

arXiv

PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving

We present the PACE, a framework for retrieval-augmented dialogue serving that formalizes Perceived Time-to-First-Res...

AI 聚合

2026-09-10

arXiv

MOONWALK: Mediating Operations with Intent-Evidence-Action Alignment Across Junior-Supervisor Review Workflows in Animation/VFX Pre-Production

Animation and VFX pre-production review requires teams to translate loosely specified creative intent--briefs, evolvi...

AI 聚合

2026-09-10

arXiv

Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization

The growing complexity of content moderation policies presents a critical challenge for their consistent operationali...

AI 聚合

2026-09-10

arXiv

Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs

Current LLM memory systems treat all personal facts identically, so stores grow without bound while retrieval precisi...

AI 聚合

2026-09-10