cập nhật 1 giờ trước

⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5335, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

26
Cognitive Multi-Agent Search and Rescue: Language-Grounded Hierarchical Reinforcement Learning for Collaborative Robotics
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.13161v1 Announce Type: new Abstract: Effective search and rescue (SAR) operations require autonomous systems capable of coordinating multiple heterogeneous agents, adapting to dynamic hazards, and aligning with human mission intent. Existing language-guided reinforcem…

🅲 hạng C
24
LoRAWeaver: Directional Adapter Routing in LoRA Representation Space
📄 Paper arXiv cs.AI 15 giờ 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
24
An Operationalization of Opaque Serial Depth
📄 Paper arXiv cs.AI 15 giờ trước

arXiv:2611.17495v1 Announce Type: new Abstract: Chain-of-thought (CoT) is currently a valuable tool for overseeing AI models, but some architectural shifts could significantly reduce CoT monitorability. We operationalize a measure that serves as a proxy for the amount of unverba…

🅲 hạng C
24
Safety Side Effects of Preventative Persona Steering: An Empirical Audit
📄 Paper arXiv cs.AI 15 giờ trước

arXiv:2611.17620v1 Announce Type: new Abstract: High-level behaviors such as sycophancy and hallucination correspond to directions in a model's activation space (Chen et al., 2025). These directions, known as persona vectors, can suppress undesirable traits either at inference t…

🅲 hạng C
24
Is Abliteration Getting Harder? Not Uniformly: Refusal Removal by Direction-Based Ablation and ARA in Heretic on the Qwen3.8, Gemma 4, Olmo 3.1 and Mistral Small 3.2 LLMs Versus Their Predecessors
📄 Paper arXiv cs.AI 15 giờ trước

arXiv:2611.17846v1 Announce Type: new Abstract: Abliteration, a fine-tuning-free weight edit, removes refusal from open-weight large language models (LLMs). The developer of Arbitrary-Rank Ablation (ARA), an optimisation-based variant, reports that direction-based abliteration, …

🅲 hạng C
24
Pairing AIS with RF: Analysis of a Markovian Approach for Maritime Data Fusion
📄 Paper arXiv cs.CR 15 giờ trước

arXiv:2611.18563v1 Announce Type: cross Abstract: Monitoring maritime activities is important for safety and security, particularly for detecting illegal activities, but remains challenging due to the size and complexity of the maritime domain. The Automatic Identification Syste…

🅲 hạng C
23
AutoAssumption: Searching over Assumptions Discovers ML-Systems Algorithms
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.14844v1 Announce Type: new Abstract: Many advances in ML systems came from breaking an assumption that earlier methods took for granted: speculative decoding dropped the assumption that a model needs one forward pass per token. Yet algorithms rarely state their assump…

🅲 hạng C
23
A physics-constrained deep reinforcement learning method for autonomous mission planning of Titan deep space probes
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.15389v1 Announce Type: new Abstract: Titan is a compelling target for future deep space exploration, while its extreme Earth-Titan distance and complex environment make continuous ground-in-the-loop planning impractical. Existing planning methods, primarily developed …

🅲 hạng C
21
JVT: Just Video Transformer makes pixel-space video diffusion simple
📄 Paper HF Daily Papers 4 ngày trước

Direct diffusion modeling of high-dimensional raw video data is challenging, and existing pixel-space methods often rely on specialized architectures. We introduce JVT (Just Video Transformer), a simple large-patch DiT-style Transformer for pixel-space video diffusion, without a …

🅲 hạng C
21
Incrementally Verifiable Oracle Aided Computation
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.14698v1 Announce Type: new Abstract: Incrementally verifiable computation (IVC) allows a prover to maintain a short proof that can be efficiently updated after each computation step, without retaining or recomputing the preceding execution. Standard IVC schemes do not…

🅲 hạng C
20
HALO: Human-Aligned Data Collection for WhoLe-body MObile Manipulation
📄 Paper HF Daily Papers 5 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
20
W-ISA: Transactional Execution of Weight-Space Intervention Programs
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.13232v1 Announce Type: new Abstract: We present W-ISA, a software instruction set and transactional runtime for executing weight-space intervention programs on pretrained language models. Shape-checked instructions express parameter updates, projections, ablations, an…

🅲 hạng C
20
NCP: Verifier-Guided Optimization of Weight-Space Control Policies
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.13236v1 Announce Type: new Abstract: We present the Neural Control Plane (NCP), a closed-loop system that observes language-model execution, synthesizes candidate weight-space intervention rules, evaluates them, and maintains a versioned table of admitted policies. NC…

🅲 hạng C
20
Gradient Inversion through Linear and Affine Subspace Constraints
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.13976v1 Announce Type: new Abstract: Federated learning enables multiple clients to collaboratively train a machine-learning model without directly sharing their local datasets. However, as prior works have shown, the gradients exchanged during training may reveal sen…

🅲 hạng C
20
Latent Barrier Steering: Hierarchical Safety for Generative Planning
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.13227v1 Announce Type: cross Abstract: We introduce Latent Barrier Steering (LBS), a hierarchical semantic-to-path framework for safe flow-matching-based generative planning. Existing control-barrier-function (CBF) safety filters for diffusion and flow-matching planne…

🅲 hạng C
20
Beyond Prompt Attacks: Least-Action Auditing of Concept Erasure
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.10106v1 Announce Type: new Abstract: Concept erasure, or concept unlearning, in text-to-image diffusion models is usually audited with prompt attacks. A prompt attack tests whether one conditioning string still retrieves the erased concept. It does not measure the pro…

🅲 hạng C
20
Towards Lightweight IoT Intrusion Detection: Feature Optimization and Explainable Machine Learning for Resource-Constrained Environment
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.10707v1 Announce Type: new Abstract: Machine learning-based intrusion detection systems (IDSs) can improve IoT security but often rely on large feature sets that increase computational overhead and limit deployment on resource-constrained devices. This paper presents …

🅲 hạng C