cập nhật 42 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.2 giờ sau khi CVE được công bố (n = 5317, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

25
Pandora's Toolbox Or Why Agent Safety Cannot Be Verified
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.25325v1 Announce Type: new Abstract: Present artificial intelligence agents are constructed by means of a coupling between a fixed language model with a general computing device. We show that this coupling makes safety undecidable. In particular, we show that given so…

🅲 hạng C
24
What Does an Agent Need? Bundle-Aware Agent Resource Composition
📄 Paper arXiv cs.AI 4 ngày trước

arXiv:2611.22030v1 Announce Type: new Abstract: An agent resource's value depends on its backbone and companion resources and is known only after execution. Token-based generators remain tied to their training catalog, while independent resource scoring misses complementarities …

🅲 hạng C
24
A Reinforcement Learning Method to Navigate SMEFT Operator Space
📄 Paper HF Daily Papers 6 ngày trước

In particle physics, discrepancies between experimental measurements and Standard Model (SM) predictions are commonly interpreted within new theoretical models. In this context, the Standard Model Effective Field Theory (SMEFT) provides a general framework encompassing a broad cl…

🅲 hạng C
22
MS-Point: Multi-Modal Hierarchical Spectral Learning for Point Cloud Understanding
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.25282v1 Announce Type: new Abstract: Point-image alignment learns useful object representations, but different local feature patterns can produce the same pooled descriptor and receive the same alignment signal. We introduce MS-Point, a cross-modal pretraining framewo…

🅲 hạng C
21
EgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video Captioning
📄 Paper HF Daily Papers 3 ngày trước

Egocentric video captioning requires fine-grained detail and accurate timing, yet current multimodal large language models (MLLMs) often miss brief actions, confuse their order, or misinterpret the wearer's motion. Existing caption formats also offer limited support for combining…

🅲 hạng C
21
When Lower Harm Misleads: Auditing Concept Corrections
📄 Paper arXiv cs.AI 4 ngày trước

arXiv:2611.22084v1 Announce Type: new Abstract: An expert who corrects a concept prediction, such as a BI-RADS descriptor in breast ultrasound, expects the diagnosis to improve. Objectives that reduce the harm of such corrections are judged by harm and accuracy, yet harm also fa…

🅲 hạng C
20
Operating-Point Failure of Frozen Guardrail Probes Under Backbone Updates
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.19216v1 Announce Type: new Abstract: We freeze a guardrail probe and threshold, then measure its operating point across 18 cells covering 16 public language-model updates. At a 1% target, the threshold fails closed in 8 of 9 cells in the first phase and either fails c…

🅲 hạng C
20
VideoNexus: Video Perception Beyond the Reasoning Context
📄 Paper HF Daily Papers 6 ngày trước

Understanding long videos requires locating evidence, resolving visual details, and integrating observations into an answer. Even when relevant evidence is present, performing these operations within long, dense visual sequences burdens both perception and reasoning. Video agents…

🅲 hạng C