Search Results for author:
Found 35 papers, 14 papers with code
Defense against Prompt Injection Attacks via Mixture of Encodings
Large Language Models (LLMs) have emerged as a dominant approach for a wide range of NLP tasks, with their access to external information further enhancing their capabilities.
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
Based on our new StepEval-Audio-360 evaluation benchmark, Step-Audio achieves state-of-the-art performance in human evaluations, especially in terms of instruction following.
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length.
Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment
While diffusion models are powerful in generating high-quality, diverse synthetic data for object-centric tasks, existing methods struggle with scene-aware tasks such as Visual Question Answering (VQA) and Human-Object Interaction (HOI) Reasoning, where it is critical to preserve scene attributes in generated images consistent with a multimodal context, i. e. a reference image with accompanying text guidance query.
PediaBench: A Comprehensive Chinese Pediatric Dataset for Benchmarking Large Language Models
Through an in-depth analysis of experimental results, we offer insights into the ability of LLMs to answer pediatric questions in the Chinese context, highlighting their limitations for further improvements.
SplatFlow: Self-Supervised Dynamic Gaussian Splatting in Neural Motion Flow Field for Autonomous Driving
SplatFlow designs a unified framework to seamlessly integrate time-dependent 4D Gaussian representation within NMFF, where NMFF is a set of implicit functions to model temporal motions of both LiDAR points and Gaussians as continuous motion flow fields.
Cell as Point: One-Stage Framework for Efficient Cell Tracking
To solve these challenges, CAP introduces two key innovations: (1) adaptive event-guided (AEG) sampling, which prioritizes cell division events to mitigate the occurrence imbalance of cell events, and (2) the rolling-as-window (RAW) inference strategy, which ensures continuous and stable tracking of newly emerging cells over extended sequences.
Phenome-wide causal proteomics enhance systemic lupus erythematosus flare prediction: A study in Asian populations
The identification of key proteins and their causal relationships with flare-related clinical markers provides valuable insights for proactive SLE management and personalized therapeutic approaches.
Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View
Cellular nuclei recognition serves as a fundamental and essential step in the workflow of digital pathology.
LoSA: Long-Short-range Adapter for Scaling End-to-End Temporal Action Localization
Temporal Action Localization (TAL) involves localizing and classifying action snippets in an untrimmed video.
Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling
Machine learning holds tremendous promise for transforming the fundamental practice of scientific discovery by virtue of its data-driven nature.
Shifting to Machine Supervision: Annotation-Efficient Semi and Self-Supervised Learning for Automatic Medical Image Segmentation and Classification
Our study benchmarks these techniques on three distinct medical imaging datasets to evaluate their effectiveness in classification and segmentation tasks.
A Framework for Automated Measurement of Responsible AI Harms in Generative AI Applications
We present a framework for the automated measurement of responsible AI (RAI) metrics for large language models (LLMs) and associated products and services.
Enhancing Medical Image Segmentation: Optimizing Cross-Entropy Weights and Post-Processing with Autoencoders
In this paper, we present a deep-learning approach tailored for Medical image segmentation.
Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation
The success of automated medical image analysis depends on large-scale and expert-annotated training sets.
Rule By Example: Harnessing Logical Rules for Explainable Hate Speech Detection
In this paper, we present Rule By Example (RBE): a novel exemplar-based contrastive learning approach for learning from logical rules for the task of textual content moderation.
Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modality
There is a rapidly growing need for multimodal content moderation (CM) as more and more content on social media is multimodal in nature.
PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization
To address this, we present PivoTAL, Prior-driven Supervision for Weakly-supervised Temporal Action Localization, to approach WTAL from a localization-by-localization perspective by learning to localize the action snippets directly.
Weakly Supervised Action Localization
Weakly Supervised Temporal Action Localization
ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding
We present ProTeGe as the first method to perform VTG-based untrimmed pretraining to bridge the gap between trimmed pretrained backbones and downstream VTG tasks.
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
It captures object motion in the video via a novel optical flow calibration module that fuses the segmentation mask with optical flow estimation to improve within-object optical flow smoothness and reduce noise at object boundaries.
Ranked #1 on
Video Object Segmentation
on DAVIS 2017 (test-dev)
(using extra training data)
GateHUB: Gated History Unit with Background Suppression for Online Action Detection
We present GateHUB, Gated History Unit with Background Suppression, that comprises a novel position-guided gated cross-attention mechanism to enhance or suppress parts of the history as per how informative they are for current frame prediction.
Ranked #1 on
Online Action Detection
on TVSeries
MUSE: Feature Self-Distillation with Mutual Information and Self-Information
Importantly, we argue and empirically demonstrate that MUSE, compared to other feature discrepancy functions, is a more functional proxy to introduce dependency and effectively improve the expressivity of all features in the knowledge distillation framework.
Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation
We present MetaUVFS as the first Unsupervised Meta-learning algorithm for Video Few-Shot action recognition.
DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis
With image-level labels only, patch-wise classification would be sub-optimal due to inconsistency between the patch appearance and image-level label.
Seismic Inverse Modeling Method based on Generative Adversarial Network
Seismic inverse modeling is a common method in reservoir prediction and it plays a vital role in the exploration and development of oil and gas.
Revisiting Dynamic Convolution via Matrix Decomposition
It has two limitations: (a) it increases the number of convolutional weights by K-times, and (b) the joint optimization of dynamic attention and static convolution kernels is challenging.
Stronger NAS with Weaker Predictors
We propose a paradigm shift from fitting the whole architecture space using one strong predictor, to progressively fitting a search path towards the high-performance sub-space through a set of weaker predictors.
Weak NAS Predictor Is All You Need
Rather than expecting a single strong predictor to model the whole space, we seek a progressive line of weak predictors that can connect a path to the best architecture, thus greatly simplifying the learning task of each predictor.
BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images
Unfortunately, this imbalance enables a visual recognition system to perform well on head classes but poorly on tail classes.
Ranked #57 on
Long-tail Learning
on ImageNet-LT
PDAM: A Panoptic-Level Feature Alignment Framework for Unsupervised Domain Adaptive Instance Segmentation in Microscopy Images
In this work, we present an unsupervised domain adaptation (UDA) method, named Panoptic Domain Adaptive Mask R-CNN (PDAM), for unsupervised instance segmentation in microscopy images.
RasterNet: Modeling Free-Flow Speed using LiDAR and Overhead Imagery
Roadway free-flow speed captures the typical vehicle speed in low traffic conditions.
HyperSTAR: Task-Aware Hyperparameters for Deep Networks
To reduce HPO time, we present HyperSTAR (System for Task Aware Hyperparameter Recommendation), a task-aware method to warm-start HPO for deep neural networks.
Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting
More specifically, we first propose a nuclei inpainting mechanism to remove the auxiliary generated objects in the synthesized images.
Region and Object based Panoptic Image Synthesis through Conditional GANs
Our contribution consists of the proposal of a significant task worth investigating and a naive baseline of solving it.
FARSA: Fully Automated Roadway Safety Assessment
An emerging approach for conducting such assessments in the United States is through the US Road Assessment Program (usRAP), which rates roads from highest risk (1 star) to lowest (5 stars).
