8 papers
When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding
Ke Li, Jiayu Chen, Maoliang Li +5
Efficient long-video understanding requires vision--language models (VLMs) to reason over a small number of frames selected as sparse visual evidence. Existing relevance-based meth…
EchoCache: Energy-Guided Cross-Modal Caching for Efficient Audio-Driven Video Generation
Jiayu Chen, Xiaoyu Wu, Rongshan Gao +6
Audio-driven video generation (A2V) has achieved promising progress in synthesizing temporally coherent and audio-visually aligned videos, yet its inference remains expensive due t…
DESI DR2 Baryon Acoustic Oscillations from the Lyman Alpha Forest Multipoles
N. G. Karaçaylı, A. Cuceu, J. Aguilar +55
We present an alternative measurement of the Baryon Acoustic Oscillation (BAO) using the Legendre multipole representation of the Ly forest correlation functions from the secon…
MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers
Maoliang Li, Haojing Chen, Jiayu Chen +4
Diffusion Transformers with Mixture-of-Experts (DiT-MoE) improve model capacity under sparse activation, but diffusion inference is still bottlenecked by redundant computation acro…
VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness
Zihao Zheng, Zhihao Mao, Xingyue Zhou +9
Vision-and-Language Navigation (VLN) increasingly relies on large vision-language models, but their inference cost conflicts with real-time deployment. Token caching is a promising…
GOMA: Geometrically Optimal Mapping via Analytical Modeling for Spatial Accelerators
Wulve Yang, Hailong Zou, Rui Zhou +5
General matrix multiplication (GEMM) on spatial accelerators is highly sensitive to mapping choices in both execution efficiency and energy consumption. However, the mapping space…