Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks60 from public data
- Point Transformer V3: Simpler, Faster, Stronger1,171
This paper presents Point Transformer V3 (PTv3), which prioritizes simplicity and efficiency over the accuracy of certain mechanisms that are minor to the over-all performance after scaling, such as replacing the precise neighbor search by KNN with an efficient serialized neighbor mapping of point clouds organized with specific patterns.
- 226
- GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving165
This work introduces GoalFlow, a novel method that effectively constrains the generative process to produce high-quality, multimodal trajectories, and achieves state-of-the-art performance, delivering robust multimodal trajectories for autonomous driving.
- Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers147
This technical report introduces the Lumina-T2X family - a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a unified framework designed to transform noise into images, videos, multi-view 3D objects, and audio clips conditioned on text instructions.
- Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model121
Conv-LoRA not only preserves SAM's extensive segmentation knowledge but also revives its capacity of learning high-level image semantics, which is constrained by SAM's foreground-background segmentation pretraining.
- GD-MAE: Generative Decoder for MAE Pre-Training on LiDAR Point Clouds108
This work proposes a Generative Decoder for MAE (GD-MAE) to automatically merges the surrounding context to restore the masked geometric knowledge in a hierarchical fusion manner and achieves comparable accuracy even with 20% of the labeled data on the Waymo dataset.
- 94
- UniPAD: A Universal Pre-Training Paradigm for Autonomous Driving90
UniPAD is presented, a novel self-supervised learning paradigm applying 3D volumetric differentiable rendering that implicitly encodes 3D space, facilitating the reconstruction of continuous 3D shape structures and the intricate appear-ance characteristics of their 2D projections.
- PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer81
A novel Point-Voxel Transformer for single-stage 3D detection (PVT-SSD) that takes advantage of voxel-based sparse convolutions for efficient feature encoding and adaptively fuses long-range contextual and local geometric information around reference points into content queries.
- Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification41
A novel diffusion-based feature learning framework that explores multi-timestep multi-stage diffusion features for HSI classification for the first time, called MTMSD, which outperforms state-of-the-art methods for HSI classification, especially on the challenging Houston 2018 dataset.
- The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition33
A gradient-driven training mechanism to tackle the long-tail problem: re-balancing the positive/negative gradients dynamically according to current accumulative gradients, with a unified goal of achieving balance gradient ratios.
- 30
- 26
- 24
- 21
- 19
- 19
- 18
- 18
- 3D-QueryIS: A Query-based Framework for 3D Instance Segmentation17
This paper proposes to generate representative points in an implicit manner, and use them together with the initial queries to generate the informative instance queries, and concludes that the 3D-QueryIS is free from the accumulated errors caused by the inter-task dependencies.
- 14
- 14
- 14
- Compatible Transformer for Irregularly Sampled Multivariate Time Series14
The proposed CoFormer is a transformer-based encoder to achieve comprehensive temporal-interaction feature learning for each individual sample in irregular multivariate time series, and can analyze irregularly sampled multivariate time series for many downstream tasks, including classification and prediction.
- 13
- Holistic-Motion2D: Scalable Whole-body Human Motion Generation in 2D Space13
This paper presents Holistic-Motion2D, the first comprehensive and large-scale benchmark for 2D whole-body motion generation, which includes over 1M in-the-wild motion sequences, each paired with high-quality whole-body/partial pose annotations and textual descriptions.
- 12
- 12
- Factorized Visual Tokenization and Generation11
Factorized Quantization (FQ) is introduced, a novel approach that revitalizes VQ-based tokenizers by decomposing a large codebook into multiple independent sub-codebooks, enabling more efficient and scalable visual tokenization.
- 10
- 9
- 9
- 8
- 7
- 7
- 6
- Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning6
- 6
- 5
- 5
- 5
- 4
- 3
- 3
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.