Search Results for author:
Found 11 papers, 8 papers with code
Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer
Recognizing that different task vector subspaces contribute variably to model performance, we introduce a novel method called Neural Parameter Search (NPS-Pruning) for slimming down fine-tuned models.
One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs
Investigating these attacks is crucial for uncovering model vulnerabilities.
MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
In the adversarial iterative optimization stage, the red-team model and the target model continuously improve their respective capabilities in interaction.
ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation
ProjectEval can evaluate the generated projects by user interaction simulation for execution, and by code similarity through existing objective indicators.
SWA-LDM: Toward Stealthy Watermarks for Latent Diffusion Models
In the rapidly evolving landscape of image generation, Latent Diffusion Models (LDMs) have emerged as powerful tools, enabling the creation of highly realistic images.
Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
Multi-hop question answering (MHQA) poses a significant challenge for large language models (LLMs) due to the extensive knowledge demands involved.
Toward Robust and Accurate Adversarial Camouflage Generation against Vehicle Detectors
However, existing methods often struggle to capture environmental characteristics during the rendering process or produce adversarial textures that can precisely map to the target vehicle.
Parameter Competition Balancing for Model Merging
Recently developed model merging techniques enable the direct integration of multiple models, each fine-tuned for distinct tasks, into a single model.
CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors
By sampling the optimal texture image from the diffusion model with a user-specific text prompt, our method can generate natural and customizable adversarial camouflage while maintaining high attack performance.
RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation
However, existing methods often struggle to capture environmental characteristics during the rendering process or produce adversarial textures that can precisely map to the target vehicle, resulting in suboptimal attack performance.
An Empirical Study on the Efficacy of Deep Active Learning for Image Classification
Third, performing data selection in the SSAL setting can achieve a significant and consistent performance improvement, especially with abundant unlabeled data.
