cập nhật 34 phút trước

⏱ Độ trễ thật của tab này: trung bình 7.1 giờ sau khi CVE được công bố (n = 5350, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

27
PolicySniff: Inferring Agent Policy States through Shared-GPU Execution
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.16158v1 Announce Type: new Abstract: LLM agents apply approval settings, such as whether to ask before a consequential tool call, through instructions in their system prompt, and operators keep these settings confidential by restricting access to prompts and responses…

🅲 hạng C
23
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
Advancing Weighted Partial MaxSAT Solving via Differentiable GPU Guidance
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.15091v1 Announce Type: new Abstract: We present a GPU-CPU hybrid framework for Weighted Partial MaxSAT (WPMAX-SAT) that complements state-of-the-art CPU solvers with differentiable GPU optimization. The GPU stage directly optimizes instance-specific categorical decisi…

🅲 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
LoRazor: Trimming Adapter Execution for Efficient Multi-LoRA Serving
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.10049v1 Announce Type: new Abstract: LoRA offers a parameter-efficient adaptation strategy, supporting multi-user workloads via customized adapters on a shared backbone. However, serving concurrent requests with different adapters introduces substantial computation an…

🅲 hạng C
20
Multi-GPU MoE Inference with Adaptive Expert Offloading
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.10219v1 Announce Type: new Abstract: Modern Mixture-of-Experts (MoE) inference is constrained by GPU memory. This constraint is mitigated by expert offloading, which stores part of the model's weight in host memory and executes on demand. Though MoE architecture has c…

🅲 hạng C
20
CAROUSEL: GPU-Accelerated Private Vector Search via Homomorphic Sketching
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.10622v1 Announce Type: new Abstract: Vector search on untrusted infrastructure exposes the \emph{query embedding}, a faithful summary of the user's intent. Fully homomorphic encryption can hide the query, but existing approaches still require a full scan followed by r…

🅲 hạng C
20
Are Dense Rewards Worth Their Tokens in GRPO?
📄 Paper HF Daily Papers 6 ngày trước

RLVR trains language models to reason by rewarding correct final answers. A widely used algorithm, group-relative policy optimization (GRPO), gives every token of a solution the same credit, so dense process rewards have been proposed to credit intermediate steps, for example wit…

🅲 hạng C