Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks82 from public data
- Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks1,364
This work introduces Grounded SAM, which uses Grounding DINO as an open-set object detector to combine with the segment anything model (SAM), which enables the detection and segmentation of any regions based on arbitrary text inputs and opens a door to connecting various vision models.
- LISA: Reasoning Segmentation via Large Language Model1,078
This work proposes a new segmentation task - reasoning segmentation and presents LISA: large Language Instructed Segmentation Assistant, which inherits the language generation capabilities of multimodal Large Language Models (LLMs) while also possessing the ability to produce segmentation masks.
- VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking524
This paper shows that a fully sparse voxel-based representation works decently for LIDAR 3D object detection and tracking, and proposes VoxelNext, an elegant and efficient framework with no need for sparse-to-dense conversion or NMS post-processing.
- VisionZip: Longer is Better but Not Necessary in Vision Language Models362
The proposed VisionZip is a simple yet effective method that selects a set of informative tokens for input to the language model, reducing visual token redundancy and improving efficiency while maintaining model performance.
- Focal Sparse Convolutional Networks for 3D Object Detection326
This paper introduces two new modules to enhance the capability of Sparse CNNs, both are based on making feature sparsity learnable with position-wise importance prediction and shows that spatially learnable sparsity in sparse convolution is essential for sophisticated 3D object detection.
- LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models297
LongLoRA is presented, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost, and is compatible with most existing techniques, like Flash-Attention2.
- Spherical Transformer for LiDAR-Based 3D Recognition270
This work study the varying-sparsity distribution of LiDAR points and present SphereFormer to directly aggregate information from dense close points to the sparse distant ones, and design radial window self-attention that partitions the space into multiple non-overlapping narrow and long windows.
- NVILA: Efficient Frontier Visual Language Models260
NVILA, a family of open VLMs designed to optimize both efficiency and accuracy, is introduced by improving its model architecture by first scaling up the spatial and temporal resolutions, and then compressing visual tokens, which enables NVILA to efficiently process high-resolution images and long videos.
- Learning Dynamic Routing for Semantic Segmentation190
A conceptually new method to alleviate the scale variance in semantic representation, named dynamic routing, which generates data-dependent routes, adapting to the scale distribution of each image, and compares with several static architectures, which can be modeled as special cases in the routing space.
- LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs174
This work proposes the spatial-wise partition convolution and its large-kernel module, which avoids the optimization and efficiency issues of naive 3D large kernels and shows that large kernels are feasible and essential for 3D visual tasks.
- 154
- FocalFormer3D : Focusing on Hard Instance for 3D Object Detection133
This work proposes Hard Instance Probing (HIP), a general pipeline that identifies FN in a multi-stage manner and guides the models to focus on excavating difficult instances, and instantiates this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall.
- 133
- Voxel Field Fusion for 3D Object Detection122
This work presents a conceptually simple yet effective framework for cross-modality 3D object detection, named voxel field fusion, and develops mixed augmentor to align feature-variant transformations, which bridges the modality gap in data augmentation.
- OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation103
The creation of Omni-Adaptive 3D CNNs (OA-CNNs), a family of networks that integrates a lightweight module to greatly enhance the adaptivity of sparse CNNs at minimal computational cost, is proposed.
- DetNAS: Neural Architecture Search on Object Detection.94
This paper proposes DetNAS to automatically search neural architectures for the backbones of object detectors, formulated into a supernet and the search method relies on evolution algorithm (EA).
- SEED-Story: Multimodal Long Story Generation with Large Language Model86
This work introduces SEED-Story, a novel approach that extends Multi-modal Large Language Models (MLLMs) to generate coherent, extended narratives composed of both interleaved text and images, and introduces a multimodal attention sink mechanism to overcome the train-short test-long challenge.
- IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation81
A simple prior-free implicit space transformation network, namely IST-Net, is introduced to transform camera-space features to world-space counterparts and build correspondences between them in an implicit manner without relying on 3D priors, with state-of-the-art performance based on prior-free design.
- Stitcher: Feedback-driven Data Provider for Object Detection76
Stitcher is presented, a feedback-driven data provider, which aims to train object detectors in a balanced way, and steadily improves performance by a large margin in all settings, especially for small objects, with nearly no additional computation in both training and testing stages.
- Multi-Scale Aligned Distillation for Low-Resolution Detection74
The idea of spatially aligning feature maps between models of varying input resolutions by shifting feature pyramid position is explored and crossed feature-level fusion is proposed to dynamically fuse teacher’s multi-resolution features to guide the student better.
- Mask-Attention-Free Transformer for 3D Instance Segmentation67
This work abandons the mask attention design and resorts to an auxiliary center regression task instead, which effectively overcome the low-recall issue and perform cross-attention by imposing positional prior.
- 66
- Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision65
A conceptually simple, strong, and efficient framework for fully- and weakly-supervised panoptic segmentation, called Panoptic FCN, which encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly.
- 63
- Identification of hepatocellular carcinoma related genes with k -th shortest paths in a protein–protein interaction network53
A computational method is developed to identify hepatocellular carcinoma related genes based on k-th shortest paths in the protein-protein interaction (PPI) network and it is found that 33 genes whose p-values were less than 0.05 have been reported to be involved in HCC tumorigenesis and development.
- 47
- 40
- 39
- PointINS: Point-Based Instance Segmentation34
This paper proposes an instance-aware convolution that decomposes this mask representation learning task into two tractable modules as instance- aware weights and instance-agnostic features, improving mask learning efficiency by avoiding employing several independent convolutions.
- 3D Aware Region Prompted Vision Language Model32
Spatial Region 3D is presented, a aware vision-language model that connects single-view 2D images and multi-view 3D data through a shared visual token space and achieves state-of-the-art performance, underscoring its effectiveness for unifying 2D and 3D representation space on scene understanding.
- ICM-3D: Instantiated Category Modeling for 3D Instance Segmentation29
This paper proposes ICM-3D, a single-step method to segment 3D instances via instantiated categorization and shows that it obtains inspiring performance across multiple frameworks, backbones and benchmarks.
- LYRA: An Efficient and Speech-Centric Framework for Omni-Cognition28
Lyra is introduced, an efficient MLLM that enhances multimodal abilities, including advanced long speech comprehension, sound understanding, cross-modality efficiency, and seamless speech interaction, while also using fewer computational resources and less training data.
- 27
- 27
- 27
- 27
- EAT-NAS: elastic architecture transfer for accelerating large-scale neural architecture search25
Not only a NAS method but also a mechanism for architecture-level transfer learning is proposed, which takes only fewer than 5 days using 8 TITAN X GPUs, which is significantly less than the computational consumption of the state-of-the-art large-scale NAS methods.
- 25
- Ultrasensitive one-pot detection of monkeypox virus with RPA and CRISPR in a sucrose-aided multiphase aqueous system20
A novel one-pot recombinase polymerase amplification-Clustered Regularly Interspaced Short Palindromic Repeats (RPA-CRISPR) assay for monkeypox virus with an ultra-high sensitivity is established, which provides an effective tool for the early diagnosis of monkeypox, which is useful for the prevention of an epidemic.
- 19
- SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference17
This work introduces SparseVILA, a novel method of query-aware token retrieval to dynamically accelerate the underlying LLM, by pruning tokens in the context stage while attending to a sparse subset of visual tokens during the generation phase.
- 17
- 16
- A multi-task learning model with reinforcement optimization for ASD comorbidity discrimination14
Experimental results based on resting-state EEG that collected from 150 ASD, ASD+ADHD or TD children with the RO- MLT method against the state-of-the-art counterparts indicate that RO-MLT is far superior in terms of all performance indicators (e.g., accuracy).
- 13
- Single-DARTS: Towards Stable Architecture Search12
This paper is the first to point out that the phenomenon of frequent performance collapse is attributed to bi-level optimization, and proposes Single-DARTS which merely uses single- level optimization, updating network weights and architecture parameters simultaneously with the same data batch.
- In‐Sensor Reservoir Computing Using Ferroelectric Optoelectronic Synapse for Near‐Infrared Face Recognition11
This work envisions ferroelectric optoelectronic synapse as potential building blocks for in‐sensor RC system, paving the way for achieving high‐accuracy recognition system in extended spectral range.
- 11
- Multi-modal recommendation algorithm fusing visual and textual features10
This paper designs a user history visual preference extraction module based on the Query-Key-Value attention to model users’ historical interests by using of visual features and proposes the FVTF (Fusing Visual and Textual Features) algorithm, which achieves the best performance compared with the benchmark recommendation algorithms.
- 9
- When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search9
A new NAS method called TNAS (NAS with trees), which improves search efficiency by exploring only a small number of architectures while also achieving a higher search accuracy, is proposed.
- 7
- 6
- 4
- 3
- 3
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. 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.