FDA differentially subtracts function-word cross-attention from original attention heads to cut attack success rates by 18-90% across models and tasks while dropping performance by at most 0.6%.
Learning transferable visual models from natural language supervi- sion
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2025 4representative citing papers
Scone unifies subject understanding and generation in a two-stage trained model to improve both composition and distinction in multi-subject image generation, outperforming prior open-source models on new benchmarks.
A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.
A training-free framework generates expressive, character-grounded dialogue and speech from scene prompts using vision-language encoders, LLMs, and a recursive narrative memory bank for cross-scene consistency.
citing papers explorer
-
Pay Less Attention to Function Words for Free Robustness of Vision-Language Models
FDA differentially subtracts function-word cross-attention from original attention heads to cut attack success rates by 18-90% across models and tasks while dropping performance by at most 0.6%.
-
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
Scone unifies subject understanding and generation in a two-stage trained model to improve both composition and distinction in multi-subject image generation, outperforming prior open-source models on new benchmarks.
-
PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.
-
Character-Centered Dialogue Generation from Scene-Level Prompts
A training-free framework generates expressive, character-grounded dialogue and speech from scene prompts using vision-language encoders, LLMs, and a recursive narrative memory bank for cross-scene consistency.