cập nhật 51 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.2 giờ sau khi CVE được công bố (n = 5286, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

31
tencent/Hy4-flash
🛠️ Công cụ AI HF Trending Models 1 ngày trước

Tencent phát hành Hy4-flash, một mô hình multimodal dạng image-text-to-text được tối ưu hóa cho tốc độ xử lý nhanh. Thích hợp cho các tác vụ suy luận thị giác kết hợp ngôn ngữ cần độ trễ thấp.

🅲 hạng C
24
HalluProbe: Exploiting VLM Hallucinations for Backdoor Detection
📄 Paper arXiv cs.CR 4 ngày trước

arXiv:2611.19868v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are vulnerable to backdoor attacks introduced through data poisoning, making effective backdoor detection a critical security challenge. In this paper, we uncover a novel connection between VLM halluci…

🅲 hạng C
22
ChronoPatch: Black-Box Energy-Latency Attacks on Vision-Language Models
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.26117v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed as generative inference services, where autoregressive decoding makes response length a key determinant of latency and computational cost. This creates an availability risk: a…

🅲 hạng C
22
ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brain
📄 Paper HF Daily Papers 3 ngày trước

Representative vision-language navigation (VLN) methods typically couple a vision-language model (VLM) brain with a learnable action head and fine-tune the VLM brain on navigation-domain data to predict geometric goals. However, such adaptation can substantially alter base VLM we…

🅲 hạng C
21
BOS Summary: The First Token Matters
📄 Paper arXiv cs.AI 2 ngày trước

arXiv:2611.23508v1 Announce Type: new Abstract: Large vision-language models (LVLMs) and language models (LLMs) often exhibit attention sinks, whereby particular positions, such as the beginning-of-sequence (BOS) token, receive a disproportionate share of attention. Under standa…

🅲 hạng C
21
RoughCut-Bench: A Benchmark for Automatic Video Rough-Cut with Large Vision-Language Models
📄 Paper HF Daily Papers 4 ngày trước

Video rough-cut is a core stage in media production workflows, organizing raw media materials into an initial video cut. Despite recent advances in large vision-language models (LVLMs) for video-related tasks, automatic rough-cut remains underexplored, without a comprehensive ben…

🅲 hạng C
20
ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters
📄 Paper HF Daily Papers 6 ngày trước

Frontier Vision-Language Models (VLMs) such as GPT-6 Astra have demonstrated remarkable capabilities in robot control, suggesting that broad pretraining provides knowledge valuable for physical action. Yet most Vision-Language-Action (VLA) policies still rely on much smaller VLM …

🅲 hạng C