cập nhật 43 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5263, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

26
When Shuffling Fails: Token Recovery from Obfuscated KV Caches
📄 Paper arXiv cs.CR 18 giờ trước

arXiv:2611.24276v1 Announce Type: new Abstract: LLM serving systems store, offload, and share KV caches, exposing token-level representations to infrastructure operators and co-tenants. Shuffled obfuscation combines secret linear transforms with fresh permutations, claiming secu…

🅲 hạng C
25
HalluProbe: Exploiting VLM Hallucinations for Backdoor Detection
📄 Paper arXiv cs.CR 2 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
23
BOS Summary: The First Token Matters
📄 Paper arXiv cs.AI 18 giờ 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
23
LoopFill: Pipelined Multi-Token Speculative Decoding for Looped Transformers
📄 Paper HF Daily Papers 6 ngày trước

Looped Transformers improve parameter efficiency by repeatedly applying the same Transformer layers. During autoregressive decoding, however, generating each token requires several sequential passes through these layers, leading to high decoding latency. Pipelined self-speculativ…

🅲 hạng C
23
DNeo: Your Parallel Draft Model Needs Better Target Feature Encoding
📄 Paper arXiv cs.AI 1 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.21925v1 Announce Type: new Abstract: Speculative-diffusion decoding uses a small parallel drafter model to generate b draft tokens in one forward pass, which then undergo parallel verification via a larger target model. Faster inference can be achieved when multiple d…

🅲 hạng C
22
Late Entry in Looped Language Models
📄 Paper HF Daily Papers 2 ngày trước

Looped language models deepen reasoning at a compact parameter count by iterating a shared layer stack T times per token, turning recurrence depth directly into sequential decoding latency. Conventional early-exit decoding halts after initial passes without cache completion, trun…

🅲 hạng C
22
Fine-Grained Japanese Clinical Named Entity Recognition: A Controlled Comparison of BERT and Open-Weight Large Language Models
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.22219v1 Announce Type: new Abstract: Background: Generative large language models (LLMs) offer an alternative to encoder-based clinical named entity recognition (NER), but their performance on fine-grained Japanese extraction tasks and sensitivity to generation settin…

🅲 hạng C
22
The Fragility of Reasoning-Importance Attribution for Pruning Language Models
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.22234v1 Announce Type: new Abstract: Attribution-guided pruning scores components by their causal contribution and protects the important ones, and it is increasingly applied to compress reasoning language models without destroying their chain of thought. Its reliabil…

🅲 hạng C
21
Chorus: Shared N-gram Embeddings with Layer-wise Adaptation
📄 Paper HF Daily Papers 3 ngày trước

Language models can gain capacity at little computational cost from n-gram embedding tables: large tables of learned vectors for short sequences of consecutive tokens, which are looked up and added to the model's input or to its intermediate layers. Recent designs commonly use a …

🅲 hạng C
21
Out of Sight, Still in Mind: Token Compression for Omni-LLMs
📄 Paper HF Daily Papers 3 ngày trước

The goal of this paper is to reduce the input token cost of Omni-modal large language models (Omni-LLMs) at inference time. Omni-LLMs reason jointly over audio, video and text, but the cost of the three streams is highly unbalanced: visual tokens account for the vast majority of …

🅲 hạng C
21
BiCAT: Bimanual Coordination Action Tokenization
📄 Paper HF Daily Papers 3 ngày trước

Autoregressive vision-language-action (VLA) models predict discrete action tokens with the next-token objective of their vision-language backbone, so the action tokenizer defines the interface between the policy and the robot. In bimanual manipulation, the two arms share a repert…

🅲 hạng C