We have 7 of 115 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Large language model (LLM) serving requires substantial memory to store model weights and KV caches. As models grow larger and contexts become longer, memory capacity and bandwidth increasingly become bottlenecks for serving performance. Agentic workloads compound this pressure through repeated interactions over growin...
LeapQuant is proposed, a training-free method that achieves near-lossless performance under 8-bit recurrent-state quantization and substantially reduces memory and compute costs during inference.
SketchSSM is introduced, which preserves full-state updates while approximating reads in hybrid-attention models, and preserves recall on four RULER retrieval tasks.
Video diffusion models repeatedly process long spatiotemporal token sequences during denoising, making attention a major computational bottleneck. Linear attention offers an appealing alternative and has been widely adopted in recent large language models, but directly applying it to video models often fails to preserv...
This work designs an end-to-end integer-only quantization approach to eliminate expensive floating-point computations on Flash compute-in-memory devices, and designs a dictionary-based KV cache compression strategy based on sparse dictionary coding that represents each KV vector as a linear combination of static dictio...
GaussianDet3D is presented, the first method to apply 3D Gaussian Splatting from multi-view images to 3D object detection in the context of autonomous driving, treating predicted Gaussian primitives as a pseudo-LiDAR point cloud fed into a sparse LiDAR detector.
Frontier open-weight models are increasingly available, but serving them still largely assumes datacenter infrastructure. We present FreeToken, an edge-native MoE serving system that treats a personal machine not as a small GPU, but as a unified, elastic inference platform. FreeToken co-designs the full serving stack,...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
