QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Models
"MLLMs" 相关文章
从 「会思考」到 「善创造」： 多模态大模型的深度推理与协同进化
NeurIPS 2025 | 电子科技大学联合A*STAR提出SCOPE：兼顾显著性与覆盖率，实现高效多模态大模型令牌剪枝
OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks
Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning
VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations
Mitigating Coordinate Prediction Bias from Positional Encoding Failures
Rethinking the Text-Vision Reasoning Imbalance in MLLMs through the Lens of Training Recipes
I Spy With My Model's Eye: Visual Search as a Behavioural Test for MLLMs
PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
RewardMap: 通过多阶段强化学习解决细粒度视觉推理的Sparse Reward
RewardMap: 通过多阶段强化学习解决细粒度视觉推理的Sparse Reward
RewardMap: 通过多阶段强化学习解决细粒度视觉推理的Sparse Reward
RewardMap: 通过多阶段强化学习解决细粒度视觉推理的Sparse Reward
RewardMap: 通过多阶段强化学习解决细粒度视觉推理的Sparse Reward
CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling
Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling
NeurIPS2025 | 攻破闭源多模态大模型：一种基于特征最优对齐的新型对抗攻击方法
