Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks15 from public data
- SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Models95
SPA-VL, as a large-scale, high-quality, and diverse dataset, represents a significant milestone in ensuring that VLMs achieve both harmlessness and helpfulness.
- Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety76
This survey provides a systematic review of current safety research on large models, covering Vision Foundation Models, Large Language Models, Vision-Language Pre-training models, Vision-Language Models, Diffusion Models, and large-model-powered Agents, and presents a comprehensive taxonomy of safety threats to these models.
- 17
- DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoning9
DAMID-X is introduced, the first dataset to pair AI-generated videos with detailed defect-level, temporal-spatial annotations and written rationales, and DAVID-XR1, a video-language model designed to deliver an interpretable chain of visual reasoning-including defect categorization, temporal-spatial localization, and natural language explanations.
- A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.58
Findings highlight that safety in frontier models is inherently multidimensional--shaped by modality, language, and evaluation design--underscoring the need for standardized, holistic safety assessments to better reflect real-world risk and guide responsible deployment.
- ModelLock: Locking Your Model With a Spell8
A diffusion-based framework dubbed ModelLock is proposed that explores text-guided image editing to transform the private finetuning data into unique styles or blend new objects into the background to open up a new direction for intellectual property protection of private models.
- BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos4
It is demonstrated that training existing video artifact detection models and multi-modal large language models (MLLMs) on BrokenVideos substantially enhances their ability to localize corrupted regions within generated content.
- T2UE: Generating Unlearnable Examples from Text Descriptions4
Text-to-Unlearnable Example (T2UE), a novel framework that enables users to generate UEs using only text descriptions, demonstrates the feasibility of ''zero-contact data protection', where personal data can be safeguarded based solely on their textual descriptions, eliminating the need for direct data exposure.
- SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation3
SyncThink is presented, a training-free and plug-and-play decoding method that reduces CoT overhead without modifying model weights, and finds that answer tokens attend weakly to early reasoning and instead focus on the special token"/think", indicating an information bottleneck.
- 2
- 2
- 1
- –
- –
- FedEGG: Federated Learning with Explicit Global Guidance–
A novel FL algorithm FedWalk is proposed that leverages an ex-ternal easy-to-converge task at the server side as a leash task to guide the local training of the clients.
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.