Search Results for author:
Found 27 papers, 20 papers with code
STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1.
AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
This paper studies the vulnerabilities of transformer-based Large Language Models (LLMs) to jailbreaking attacks, focusing specifically on the optimization-based Greedy Coordinate Gradient (GCG) strategy.
From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation
Local aggregation is employed to form superpixels, leveraging the inherent redundancy of the image data to produce segments closely aligned with specific parts of the object, guided by object-level supervision.
What If We Recaption Billions of Web Images with LLaMA-3?
For discriminative models like CLIP, we observe enhanced zero-shot performance in cross-modal retrieval tasks.
Ranked #127 on
Visual Question Answering
on MM-Vet
Autoregressive Pretraining with Mamba in Vision
The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks.
Medical Vision Generalist: Unifying Medical Imaging Tasks in Context
This study presents Medical Vision Generalist (MVG), the first foundation model capable of handling various medical imaging tasks -- such as cross-modal synthesis, image segmentation, denoising, and inpainting -- within a unified image-to-image generation framework.
Mamba-R: Vision Mamba ALSO Needs Registers
Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba.
3D-TransUNet for Brain Metastases Segmentation in the BraTS2023 Challenge
We identify that the Decoder-only 3D-TransUNet model should offer enhanced efficacy in the segmentation of brain metastases, as indicated by our 5-fold cross-validation on the training set.
SPFormer: Enhancing Vision Transformer with Superpixel Representation
In this work, we introduce SPFormer, a novel Vision Transformer enhanced by superpixel representation.
A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties
Instead of relying solely on category-specific annotations, ProLab uses descriptive properties grounded in common sense knowledge for supervising segmentation models.
Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning
This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs).
SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference
Specifically, we replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module and reuse its pretrained projection matrices of query, key, and value, leading to a training-free adaptation approach for CLIP's zero-shot semantic segmentation.
3D TransUNet: Advancing Medical Image Segmentation through Vision Transformers
In this paper, we extend the 2D TransUNet architecture to a 3D network by building upon the state-of-the-art nnU-Net architecture, and fully exploring Transformers' potential in both the encoder and decoder design.
FedConv: Enhancing Convolutional Neural Networks for Handling Data Heterogeneity in Federated Learning
Federated learning (FL) is an emerging paradigm in machine learning, where a shared model is collaboratively learned using data from multiple devices to mitigate the risk of data leakage.
Superpixel Transformers for Efficient Semantic Segmentation
Finally, we directly project the superpixel class predictions back into the pixel space using the associations between the superpixels and the image pixel features.
3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation
Motivated by the recent success of generative models in rigid object pose estimation, we propose 3D-aware Neural Body Fitting (3DNBF) - an approximate analysis-by-synthesis approach to 3D human pose estimation with SOTA performance and occlusion robustness.
SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
To address this limitation, we present Masked Multi-view with Swin Transformers (SwinMM), a novel multi-view pipeline for enabling accurate and data-efficient self-supervised medical image analysis.
Waymo Open Dataset: Panoramic Video Panoptic Segmentation
We therefore present the Waymo Open Dataset: Panoramic Video Panoptic Segmentation Dataset, a large-scale dataset that offers high-quality panoptic segmentation labels for autonomous driving.
In Defense of Image Pre-Training for Spatiotemporal Recognition
Inspired by this observation, we hypothesize that the key to effectively leveraging image pre-training lies in the decomposition of learning spatial and temporal features, and revisiting image pre-training as the appearance prior to initializing 3D kernels.
Fast AdvProp
Specifically, our modifications in Fast AdvProp are guided by the hypothesis that disentangled learning with adversarial examples is the key for performance improvements, while other training recipes (e. g., paired clean and adversarial training samples, multi-step adversarial attackers) could be largely simplified.
Are Transformers More Robust Than CNNs?
Transformer emerges as a powerful tool for visual recognition.
Ranked #1 on
Adversarial Robustness
on Stylized ImageNet
Batch Normalization with Enhanced Linear Transformation
Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data distributions.
Shape-Texture Debiased Neural Network Training
To prevent models from exclusively attending on a single cue in representation learning, we augment training data with images with conflicting shape and texture information (eg, an image of chimpanzee shape but with lemon texture) and, most importantly, provide the corresponding supervisions from shape and texture simultaneously.
Ranked #1 on
Image Classification
on ImageNet
(Hardware Burden metric)
Neural Architecture Search for Lightweight Non-Local Networks
However, it has been rarely explored to embed the NL blocks in mobile neural networks, mainly due to the following challenges: 1) NL blocks generally have heavy computation cost which makes it difficult to be applied in applications where computational resources are limited, and 2) it is an open problem to discover an optimal configuration to embed NL blocks into mobile neural networks.
Ranked #60 on
Neural Architecture Search
on ImageNet
CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks
3D Convolution Neural Networks (CNNs) have been widely applied to 3D scene understanding, such as video analysis and volumetric image recognition.
AtomNAS: Fine-Grained End-to-End Neural Architecture Search
We propose a fine-grained search space comprised of atomic blocks, a minimal search unit that is much smaller than the ones used in recent NAS algorithms.
Ranked #61 on
Neural Architecture Search
on ImageNet
Online Dictionary Learning for Approximate Archetypal Analysis
The archetypes generally correspond to the extremal points in the dataset and are learned by requiring them to be convex combinations of the training data.
