cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5463, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

29
Aligning AI Teams
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.17820v1 Announce Type: new Abstract: Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment trans…

🅲 hạng C
28
STA: A Split Temporal Adversary Method for Evaluating Robustness of Multimodal RL-based Driving Policies
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.20765v1 Announce Type: new Abstract: Multimodal reinforcement learning (MRL) offers a promising paradigm for autonomous driving by jointly leveraging complementary sensor observations to learn effective decision-making policies. However, its effectiveness critically d…

🅲 hạng C
28
Aligning AI Teams
📄 Paper HF Daily Papers 5 ngày trước

Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment transfer to multi-agent LLM teams. We focus on two sof…

🅲 hạng C
25
Auditors Struggle to Catch Sabotage In End-to-End Transcripts of AI Safety Research
📄 Paper arXiv cs.AI 3 giờ trước

arXiv:2611.21832v1 Announce Type: new Abstract: As AI systems are increasingly used to automate AI R&D, misaligned systems could sabotage research intended to improve model safety and alignment. To stress-test defenses against such sabotage, we use a human expert as a proxy sabo…

🅲 hạng C
24
Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment
📄 Paper HF Daily Papers 2 ngày trước

Abstention, the withholding of a response by a large language model (LLM) under uncertainty or safety risks, is essential for trustworthy models. The causes of abstention fall into three perspectives: ambiguity in the Query (Q), limits of Model Knowledge (MK), and misalignment wi…

🅲 hạng C
23
Designing Deceptive Model Organisms that Successfully Evade Auditing
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.20459v1 Announce Type: new Abstract: AI models can exhibit deceptive behaviors such as strategically underperforming on evaluations (sandbagging), faking alignment, or covertly acting on behalf of a hidden principal. Safe deployment therefore requires auditing techniq…

🅲 hạng C
23
VRMaaS: Verifiable Reward-Model-as-a-Service for Trustworthy LLM Alignment
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.14984v1 Announce Type: new Abstract: Reward models (RMs) are increasingly deployed as service components in LLM alignment pipelines, where payment, audit, moderation, and governance workflows act on the scores they return. An inference proof alone does not show whethe…

🅲 hạng C
22
LoRAWeaver: Directional Adapter Routing in LoRA Representation Space
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool complic…

🅲 hạng C
21
Flexible Multi-Stack Super-Resolution of Clinical Brain MRI Using Hetero-Orientation Variational Encoding: Expert Reader Evaluation in a Nigerian Cohort
📄 Paper HF Daily Papers 2 ngày trước

High-resolution brain MRI is important for neuroradiological assessment, yet routine clinical protocols often rely on fast, anisotropic 2D acquisitions, particularly in resource-constrained settings. These acquisitions may differ in orientation, alignment and anatomical coverage,…

🅲 hạng C
20
TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models
📄 Paper HF Daily Papers 6 ngày trước

Decoder-only Large View Synthesis Models (LVSMs) with KV-cache have recently achieved state-of-the-art quality by regressing novel views from neural networks without reconstructing 3D geometry, while Test-Time Training (TTT) layers save computation but sacrifice quality. We propo…

🅲 hạng C
20
HALO: Human-Aligned Data Collection for WhoLe-body MObile Manipulation
📄 Paper HF Daily Papers 6 ngày trước

Learning whole-body mobile manipulation requires demonstrations that coordinate bimanual actions with locomotion across extended workspaces. However, existing interfaces trade off direct robot control, perception and action alignment, and natural operator mobility, making such de…

🅲 hạng C