PKU-Alignment / safe-sora
SafeSora is a human preference dataset designed to support safety alignment research in the text-to-video generation field, aiming to enhance the helpfulness and harmlessness of Large Vision Models (LVMs).
☆30Updated 8 months ago
Alternatives and similar repositories for safe-sora:
Users that are interested in safe-sora are comparing it to the libraries listed below
- Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).☆38Updated 11 months ago
- ☆40Updated 3 months ago
- The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation☆99Updated 5 months ago
- [NeurIPS 2024] Official Repository of Multi-Object Hallucination in Vision-Language Models☆28Updated 5 months ago
- [NeurIPS 2024] Efficient Large Multi-modal Models via Visual Context Compression☆55Updated 2 months ago
- [NeurIPS-2024] The offical Implementation of "Instruction-Guided Visual Masking"☆33Updated 5 months ago
- code for "Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization"☆54Updated 8 months ago
- Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223☆126Updated last month
- Multimodal RewardBench☆38Updated 2 months ago
- Official implementation of "Self-Improving Video Generation"☆63Updated last month
- ElasticTok: Adaptive Tokenization for Image and Video☆66Updated 5 months ago
- Empowering Unified MLLM with Multi-granular Visual Generation☆119Updated 3 months ago
- [ICML 2024] On Discrete Prompt Optimization for Diffusion Models - Google☆52Updated 8 months ago
- [NeurIPSw'24] This repo is the official implementation of "MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simu…☆87Updated 2 months ago
- ☆72Updated 2 weeks ago
- The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"☆86Updated 6 months ago
- Official implementation for "MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?"☆43Updated last month
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆69Updated last month
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆29Updated 2 months ago
- Official repository of S-Agents: Self-organizing Agents in Open-ended Environment☆25Updated last year
- ☆73Updated 3 months ago
- ☆25Updated this week
- [CVPR 2025 (Oral)] Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key☆48Updated 2 weeks ago
- ☆44Updated 2 months ago
- ☆116Updated 2 months ago
- Official repo of EmbodiedBench, a comprehensive benchmark designed to evaluate MLLMs as embodied agents.☆108Updated last week
- ☆40Updated 9 months ago
- ☆52Updated 6 months ago
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation☆79Updated 2 weeks ago
- [CVPR2024] This is the official implement of MP5☆99Updated 9 months ago