Stealth Pretraining Seeding plants persistent unsafe behaviors in LLMs via diffuse poisoned web content that activates on precise triggers and evades standard evaluation.
Advances in Neural Information Processing Systems (NeurIPS) , year =
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
dataset 1polarities
use dataset 1representative citing papers
A 149M-parameter distributional energy-based verifier with low-rank adapter ensemble reduces constraint violations in structured LLM reasoning and outperforms or matches much larger models on five benchmarks.
DynamicRad achieves 1.7x-2.5x inference speedups in long video diffusion with over 80% sparsity by grounding adaptive selection in a radial locality prior, using dual-mode static/dynamic strategies and offline BO with a semantic motion router.
ConsistNav is a new training-free framework that uses a semantic executive controller, persistent candidate memory, and stability-aware action control to close the action consistency gap in zero-shot object navigation, reporting SOTA results on HM3D and MP3D with 11.4% SR and 7.9% SPL gains on MP3D.
An explanatory book that supplies a clear mental map and intuition for how Vision-Language Models combine vision and language capabilities.
citing papers explorer
-
PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training
Stealth Pretraining Seeding plants persistent unsafe behaviors in LLMs via diffuse poisoned web content that activates on precise triggers and evades standard evaluation.
-
Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning
A 149M-parameter distributional energy-based verifier with low-rank adapter ensemble reduces constraint violations in structured LLM reasoning and outperforms or matches much larger models on five benchmarks.
-
DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion
DynamicRad achieves 1.7x-2.5x inference speedups in long video diffusion with over 80% sparsity by grounding adaptive selection in a radial locality prior, using dual-mode static/dynamic strategies and offline BO with a semantic motion router.
-
ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Control
ConsistNav is a new training-free framework that uses a semantic executive controller, persistent candidate memory, and stability-aware action control to close the action consistency gap in zero-shot object navigation, reporting SOTA results on HM3D and MP3D with 11.4% SR and 7.9% SPL gains on MP3D.
-
From Pixels to Prompts: Vision-Language Models
An explanatory book that supplies a clear mental map and intuition for how Vision-Language Models combine vision and language capabilities.