AlignPoison: Conditional Targeted Poisoning of Generative Recommenders via Decoding-Aligned Prefixes
cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Sources
- VIP5: Towards Multimodal Foundation Models for Recommendation
- MTGR: Industrial-Scale Generative Recommendation Framework in Meituan
- Adam: A Method for Stochastic Optimization
- A Content-Driven Micro-Video Recommendation Dataset at Scale
- Qwen2.5 Technical Report
- Robust Speech Recognition via Large-Scale Weak Supervision
- Recommender Systems with Generative Retrieval
- Masked Diffusion for Generative Recommendation
- Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
- CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation
- MiniCPM-V: A GPT-4V Level MLLM on Your Phone
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- OneRec Technical Report
- OneRec-V2 Technical Report
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems