5 papers
FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation
Jing Zuo, Lingzhou Mu, Fan Jiang +3
Achieving human-level performance in Vision-and-Language Navigation (VLN) requires an embodied agent to jointly understand multimodal instructions and visual-spatial context while…
SkyReels-V2: Infinite-length Film Generative Model
Guibin Chen, Dixuan Lin, Jiangping Yang +22
Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual qual…
CASteer: Cross-Attention Steering for Controllable Concept Erasure
Tatiana Gaintseva, Andreea-Maria Oncescu, Chengcheng Ma +5
Diffusion models have transformed image generation, yet controlling their outputs to reliably erase undesired concepts remains challenging. Existing approaches usually require task…
From Attention to Activation: Unravelling the Enigmas of Large Language Models
Prannay Kaul, Chengcheng Ma, Ismail Elezi +1
We study two strange phenomena in auto-regressive Transformers: (1) the dominance of the first token in attention heads; (2) the occurrence of large outlier activations in the hidd…
Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning
Chengcheng Ma, Ismail Elezi, Jiankang Deng +2
We address the challenging problem of Long-Tailed Semi-Supervised Learning (LTSSL) where labeled data exhibit imbalanced class distribution and unlabeled data follow an unknown dis…