papers

Publications (11)

cs.CL2024

LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference

Qichen Fu, Minsik Cho, Thomas Merth +3

The inference of transformer-based large language models consists of two sequential stages: 1) a prefilling stage to compute the KV cache of prompts and generate the first token, a…

cs.CV2023

Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation

Qichen Fu, Xingyu Liu, Ran Xu +2

Accurately estimating 3D hand pose is crucial for understanding how humans interact with the world. Despite remarkable progress, existing methods often struggle to generate plausib…

cs.LG2023

eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models

Minsik Cho, Keivan A. Vahid, Qichen Fu +5

Since Large Language Models or LLMs have demonstrated high-quality performance on many complex language tasks, there is a great interest in bringing these LLMs to mobile devices fo…

cs.CV2022

Domain Adaptive Hand Keypoint and Pixel Localization in the Wild

Takehiko Ohkawa, Yu-Jhe Li, Qichen Fu +3

We aim to improve the performance of regressing hand keypoints and segmenting pixel-level hand masks under new imaging conditions (e.g., outdoors) when we only have labeled images…

cs.CV2022

Ego4D: Around the World in 3,000 Hours of Egocentric Video

Kristen Grauman, Andrew Westbury, Eugene Byrne +82

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outd…

cs.AI2026

Apple Intelligence Foundation Language Models

Tom Gunter, Zirui Wang, Chong Wang +152

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large serv…

cs.CV2024

Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers

Yuxin Wen, Qingqing Cao, Qichen Fu +2

Recent advancements in vision-language models (VLMs) have expanded their potential for real-world applications, enabling these models to perform complex reasoning on images. In the…

cs.CL2024

Speculative Streaming: Fast LLM Inference without Auxiliary Models

Nikhil Bhendawade, Irina Belousova, Qichen Fu +3

Speculative decoding is a prominent technique to speed up the inference of a large target language model based on predictions of an auxiliary draft model. While effective, in appli…

cs.CV2023

FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline

Chien-Yu Lin, Qichen Fu, Thomas Merth +2

Super-resolution (SR) techniques have recently been proposed to upscale the outputs of neural radiance fields (NeRF) and generate high-quality images with enhanced inference speeds…

cs.CV2022

Sequential Voting with Relational Box Fields for Active Object Detection

Qichen Fu, Xingyu Liu, Kris M. Kitani

A key component of understanding hand-object interactions is the ability to identify the active object -- the object that is being manipulated by the human hand. In order to accura…

cs.CL2024

Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation

Thomas Merth, Qichen Fu, Mohammad Rastegari +1

Despite the successes of large language models (LLMs), they exhibit significant drawbacks, particularly when processing long contexts. Their inference cost scales quadratically wit…