Tag
论文提出 Temporal Activation Injection (TAI)，通过分析 VideoLLM 中帧序反转引发的层间表征差异（temporal divergence vector），在推理时沿实测衰减曲线重新注入时序信息，无需训练即可在三个 VideoLLM 和四个基准上一致提升时序推理能力。
TempCloze is a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs, requiring models to identify missing video segments from distractors to reduce linguistic shortcuts in semantics, alignment, and progression.
LiteFrame proposes a lightweight video encoder with Compressed Token Distillation training that reduces latency and enables processing 8x more frames for long-form video understanding in Video LLMs, improving accuracy while reducing compute.