12 papers
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
Arash Akbari, Arman Akbari, Masih Eskandar +11
Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical. Aggressiv…
Flash-WAM: Modality-Aware Distillation for World Action Models
Arman Akbari, Ci Zhang, Arash Akbari +6
World-action models (WAMs) jointly generate future video and robot actions through iterative diffusion, achieving strong performance on manipulation benchmarks but requiring tens o…
STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models
Yiming Liang, Yixiao Chen, Yiyang Zhou +8
Many video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames. Existing methods built on large vision-language models (LVLMs) often a…
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Anyi Xu, Bangcai Lin +315
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…
Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density
Zhendong Mi, Yixiao Chen, Pu Zhao +4
Mixture-of-Experts (MoE) based Large Language Models (LLMs) have achieved superior performance, yet the massive memory overhead caused by storing multiple expert networks severely…
DyMixOp: A Neural Operator Designed from a Complex Dynamics Perspective with Local-Global Mixing for Solving PDEs
Pengyu Lai, Yixiao Chen, Dewu Yang +3
A primary challenge in using neural networks to approximate nonlinear dynamical systems governed by partial differential equations (PDEs) lies in recasting these systems into a tra…