CacheTrap achieves 100% targeted attack success on five open-source LLMs by using an efficient search to locate and flip a single bit in the KV cache as a transient trigger, while preserving normal accuracy without the trigger.
Qwen2.5: A party of foundation models
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
HapticLDM is the first latent diffusion model that generates vibrotactile signals directly from text, using dynamic text curation and global denoising to improve realism and semantic alignment over autoregressive baselines.
VertMark embeds robust, training-free watermarks into vertical domain language models by creating hidden semantic equivalence between low-frequency triggers and high-frequency domain terms via parameter swaps, supporting reliable verification with negligible performance impact.
CoDA aligns cross-domain latent reasoning representations in LLMs via CoT distillation and MMD to enable effective knowledge transfer without in-domain demonstrations.
BackFlush detects backdoors via susceptibility amplification and eliminates them with RoPE unlearning to reach 1% ASR and 99% clean accuracy while preserving watermarks.
GELATO combines drift-plus-penalty Lyapunov control with generative entropy early exiting to adaptively offload tokens in device-edge speculative decoding, delivering higher throughput and lower energy use than prior distributed SD systems while preserving output quality.
This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.
citing papers explorer
-
CacheTrap: Unveiling a Stealthier Gray-Box Trojan against LLMs
CacheTrap achieves 100% targeted attack success on five open-source LLMs by using an efficient search to locate and flip a single bit in the KV cache as a transient trigger, while preserving normal accuracy without the trigger.
-
HapticLDM: A Diffusion Model for Text-to-Vibrotactile Generation
HapticLDM is the first latent diffusion model that generates vibrotactile signals directly from text, using dynamic text curation and global denoising to improve realism and semantic alignment over autoregressive baselines.
-
VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models
VertMark embeds robust, training-free watermarks into vertical domain language models by creating hidden semantic equivalence between low-frequency triggers and high-frequency domain terms via parameter swaps, supporting reliable verification with negligible performance impact.
-
CoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptation
CoDA aligns cross-domain latent reasoning representations in LLMs via CoT distillation and MMD to enable effective knowledge transfer without in-domain demonstrations.
-
BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models
BackFlush detects backdoors via susceptibility amplification and eliminates them with RoPE unlearning to reach 1% ASR and 99% clean accuracy while preserving watermarks.
-
GELATO: Generative Entropy- and Lyapunov-based Adaptive Token Offloading for Device-Edge Speculative LLM Inference
GELATO combines drift-plus-penalty Lyapunov control with generative entropy early exiting to adaptively offload tokens in device-edge speculative decoding, delivering higher throughput and lower energy use than prior distributed SD systems while preserving output quality.
-
A Survey of Large Language Models
This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.
- Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommenders