10 papers
HyLoVQA: Dynamic Hypernetwork-Generated Low-Rank Adaptation for Continual Visual Question Answering
Yiran Wang, Chenyi Xiong, Ziyue Qin +3
Continual Visual Question Answering (VQA) requires learning from non-stationary streams of visual inputs and questions while preserving past knowledge. Most prior methods adapt by…
DASH: Fast Differentiable Architecture Search for Hybrid Attention in Minutes on a Single GPU
Weizhe Chen, Miao Zhang, Junpeng Jiang +3
Hybrid attention architectures are becoming an increasingly important paradigm for improving LLM inference efficiency while preserving model quality, making hybrid architecture des…
PulseCol: Periodically Refreshed Column-Sparse Attention for Accelerating Diffusion Language Models
Yanyi Lyu, Letian Chen, Futing Sun +3
Inference in diffusion large language models (dLLMs) is computationally expensive, as full self-attention must be repeatedly executed at each step of the denoising process without…
Sustainable Intelligence for the Wild: Democratizing Ecological Monitoring via Knowledge-Adaptive Edge Expert Agents
Jiaxing Li, Hao Fang, Chi Xu +5
Rapid biodiversity loss underscore the urgency of effective monitoring, yet manual surveys remain resource-intensive. While on-device AI offers a scalable alternative, its performa…
Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation
Xuening Zhang, Qi Lv, Xiang Deng +3
View transformers process multi-view observations to predict actions and have shown impressive performance in robotic manipulation. Existing methods typically extract static visual…
TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models
Qianlong Xiang, Miao Zhang, Haoyu Zhang +3
Although text-to-image diffusion models exhibit remarkable generative power, concept erasure techniques are essential for their safe deployment to prevent the creation of harmful c…