SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities Paper • 2502.12025 • Published 23 days ago
CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models Paper • 2406.12257 • Published Jun 18, 2024
Stronger Models are NOT Stronger Teachers for Instruction Tuning Paper • 2411.07133 • Published Nov 11, 2024 • 36
MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities Paper • 2408.00765 • Published Aug 1, 2024 • 14
Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data? Paper • 2407.16607 • Published Jul 23, 2024 • 23
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates Paper • 2406.12935 • Published Jun 17, 2024 • 2
MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos Paper • 2406.08407 • Published Jun 12, 2024 • 28
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding Paper • 2402.08983 • Published Feb 14, 2024 • 4
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs Paper • 2402.11753 • Published Feb 19, 2024 • 6
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models Paper • 2401.12242 • Published Jan 20, 2024 • 1
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing Paper • 2406.08464 • Published Jun 12, 2024 • 67
List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs Paper • 2404.16375 • Published Apr 25, 2024 • 18
GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation Paper • 2311.07562 • Published Nov 13, 2023 • 14
MM-VID: Advancing Video Understanding with GPT-4V(ision) Paper • 2310.19773 • Published Oct 30, 2023 • 20
DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design Paper • 2310.15144 • Published Oct 23, 2023 • 14