Search Results for author:
Found 19 papers, 12 papers with code
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning
Large Language Models (LLMs) fine-tuning technologies have achieved remarkable results.
MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
To these ends, we propose MambaQuant, a post-training quantization (PTQ) framework consisting of: 1) Karhunen-Loeve Transformation (KLT) enhanced rotation, rendering the rotation matrix adaptable to diverse channel distributions.
OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
We complement QSUR with mathematical derivations that examine the effects and limitations of various transformations, guiding our development of Orthogonal and Scaling Transformation-based Quantization (OSTQuant).
GSRender: Deduplicated Occupancy Prediction via Weakly Supervised 3D Gaussian Splatting
Consequently, we propose GSRender, which naturally employs 3D Gaussian Splatting for occupancy prediction, simplifying the sampling process.
MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues
3D single object tracking is essential in autonomous driving and robotics.
PTQ4RIS: Post-Training Quantization for Referring Image Segmentation
Specifically, we first conduct an in-depth analysis of the root causes of performance degradation in RIS model quantization and propose dual-region quantization (DRQ) and reorder-based outlier-retained quantization (RORQ) to address the quantization difficulties in visual and text encoders.
Sub-SA: Strengthen In-context Learning via Submodular Selective Annotation
In Sub-SA, we design a submodular function that facilitates effective subset selection for annotation and demonstrates the characteristics of monotonically and submodularity from the theoretical perspective.
P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds
Moreover, under the same point-based representation, P2P-point outperforms the previous motion tracker M$^2$Track by \textbf{3. 3\%} and \textbf{6. 7\%} on the KITTI and NuScenes, while running at a considerably high speed of \textbf{107 Fps} on a single RTX3090 GPU.
PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram
To address above issue, we first unveil the importance of different input information during PFE and identify the height dimension as a key factor in enhancing 3D detection performance.
I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models
Post-training quantization (PTQ) serves as a potent technique to accelerate the inference of large language models (LLMs).
PillarTrack: Redesigning Pillar-based Transformer Network for Single Object Tracking on Point Clouds
LiDAR-based 3D single object tracking (3D SOT) is a critical issue in robotics and autonomous driving.
WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More
Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process.
LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
To our knowledge, for the very first time in lidar-based 3D detection tasks, the PTQ INT8 model's accuracy is almost the same as the FP32 model while enjoying $3\times$ inference speedup.
RobustCalib: Robust Lidar-Camera Extrinsic Calibration with Consistency Learning
Current traditional methods for LiDAR-camera extrinsics estimation depend on offline targets and human efforts, while learning-based approaches resort to iterative refinement for calibration results, posing constraints on their generalization and application in on-board systems.
FastPillars: A Deployment-friendly Pillar-based 3D Detector
The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios.
Real-time 3D Single Object Tracking with Transformer
PTT module in the voting stage could model the interactions among point patches, which learns context-dependent features.
3D Object Tracking with Transformer
By using cross-attention, the transformer decoder fuses features and includes more target cues into the current point cloud feature to compute the region attentions, which makes the similarity computing more efficient.
PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds
Our code is open-sourced for the robotics community at https://github. com/shanjiayao/PTT.
3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud
Then, to fuse the information of features in the two branches and obtain their similarity, we propose two cross correlation modules, named Pointcloud-wise and Point-wise respectively.
