Showing 21–40 of 43 results
/ Date/ Name
Jan 8, 2026Token-Level LLM Collaboration via FusionRouteMay 1, 2026ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language ModelsApr 6, 2026ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic SystemsFeb 27, 2024Securing Reliability: A Brief Overview on Enhancing In-Context Learning for Foundation ModelsMay 29, 2025SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language ModelsMar 19, 2025MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation ModelsOct 18, 2024Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language AlignmentApr 27, 2025Anyprefer: An Agentic Framework for Preference Data SynthesisOct 14, 2024MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language ModelsOct 1, 2025Efficient Multi-modal Large Language Models via Progressive Consistency DistillationJun 18, 2025Poly-Guard: Massive Multi-Domain Safety Policy-Grounded Guardrail DatasetOct 28, 2025SafeVision: Efficient Image Guardrail with Robust Policy Adherence and ExplainabilityJan 16, 2025Beyond Reward Hacking: Causal Rewards for Large Language Model AlignmentDec 9, 2024Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout DecodingJul 15, 2025The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMsNov 28, 2024GRAPE: Generalizing Robot Policy via Preference AlignmentNov 21, 2024Beyond Training: Dynamic Token Merging for Zero-Shot Video UnderstandingApr 15, 2024RankCLIP: Ranking-Consistent Language-Image PretrainingMar 1, 2024HALC: Object Hallucination Reduction via Adaptive Focal-Contrast DecodingMay 22, 2025From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization