55 citations · 178 across the 29 of their papers we have counts for
40 papers
LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models
Mohammad Mozaffari, Younes Hourri, Mohammad Rastegari +1
Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm. State-of-t…
Apple Intelligence Foundation Language Models: Tech Report 2025
Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang +395
We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model opti…
From Dense to Dynamic: Token-Difficulty Driven MoEfication of Pre-Trained LLMs
Kumari Nishu, Sachin Mehta, Samira Abnar +6
Training large language models (LLMs) for different inference constraints is computationally expensive, limiting control over efficiency-accuracy trade-offs. Moreover, once trained…
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache
Rishabh Tiwari, Haocheng Xi, Aditya Tomar +7
Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings, creating a growing need for fast and efficient long-context inference. In th…
M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer Inference
Nikhil Bhendawade, Mahyar Najibi, Devang Naik +1
Residual transformations enhance the representational depth and expressive power of large language models (LLMs). However, applying static residual transformations across all token…
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…
SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
Rasoul Shafipour, David Harrison, Maxwell Horton +6
Large Language Models (LLMs) have transformed natural language processing, but face significant challenges in widespread deployment due to their high runtime cost. In this paper, w…
CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning
Qingqing Cao, Mahyar Najibi, Sachin Mehta
Pretraining robust vision or multimodal foundation models (e.g., CLIP) relies on large-scale datasets that may be noisy, potentially misaligned, and have long-tail distributions. P…
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…
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…
OpenELM: An Efficient Language Model Family with Open Training and Inference Framework
Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao +8
The reproducibility and transparency of large language models are crucial for advancing open research, ensuring the trustworthiness of results, and enabling investigations into dat…
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Sachin Mehta, Maxwell Horton, Fartash Faghri +5
Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise simi…
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…
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…
Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving
Mahyar Najibi, Jingwei Ji, Yin Zhou +4
Closed-set 3D perception models trained on only a pre-defined set of object categories can be inadequate for safety critical applications such as autonomous driving where new objec…
3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels
Zhenzhen Weng, Alexander S. Gorban, Jingwei Ji +3
Training a 3D human keypoint detector from point clouds in a supervised manner requires large volumes of high quality labels. While it is relatively easy to capture large amounts o…
GINA-3D: Learning to Generate Implicit Neural Assets in the Wild
Bokui Shen, Xinchen Yan, Charles R. Qi +5
Modeling the 3D world from sensor data for simulation is a scalable way of developing testing and validation environments for robotic learning problems such as autonomous driving.…
Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining
Chiyu Max Jiang, Mahyar Najibi, Charles R. Qi +2
Continued improvements in deep learning architectures have steadily advanced the overall performance of 3D object detectors to levels on par with humans for certain tasks and datas…
Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving
Mahyar Najibi, Jingwei Ji, Yin Zhou +4
Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of pr…
Revisiting 3D Object Detection From an Egocentric Perspective
Boyang Deng, Charles R. Qi, Mahyar Najibi +3
3D object detection is a key module for safety-critical robotics applications such as autonomous driving. For these applications, we care most about how the detections affect the e…
Offboard 3D Object Detection from Point Cloud Sequences
Charles R. Qi, Yin Zhou, Mahyar Najibi +4
While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely under-explored, suc…
Scale Normalized Image Pyramids with AutoFocus for Object Detection
Bharat Singh, Mahyar Najibi, Abhishek Sharma +1
We present an efficient foveal framework to perform object detection. A scale normalized image pyramid (SNIP) is generated that, like human vision, only attends to objects within a…
ASAP-NMS: Accelerating Non-Maximum Suppression Using Spatially Aware Priors
Rohun Tripathi, Vasu Singla, Mahyar Najibi +3
The widely adopted sequential variant of Non Maximum Suppression (or Greedy-NMS) is a crucial module for object-detection pipelines. Unfortunately, for the region proposal stage of…
DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes
Mahyar Najibi, Guangda Lai, Abhijit Kundu +7
We propose DOPS, a fast single-stage 3D object detection method for LIDAR data. Previous methods often make domain-specific design decisions, for example projecting points into a b…