Search Results for author:
Found 39 papers, 20 papers with code
Implicit Search via Discrete Diffusion: A Study on Chess
Furthermore, DiffuSearch demonstrates a notable 30% enhancement in puzzle-solving abilities compared to explicit search-based policies, along with a significant 540 Elo increase in game-playing strength assessment.
EmoAssist: Emotional Assistant for Visual Impairment Community
To address these gaps, this paper introduces the EmoAssist Benchmark, a comprehensive benchmark designed to evaluate the assistive performance of LMMs for the VI community.
Can Large Language Models Understand Preferences in Personalized Recommendation?
To address this, we introduce PerRecBench, disassociating the evaluation from these two factors and assessing recommendation techniques on capturing the personal preferences in a grouped ranking manner.
Contrastive Conditional Alignment based on Label Shift Calibration for Imbalanced Domain Adaptation
Thus, we propose contrastive conditional alignment based on label shift calibration (CCA-LSC) for IDA, to address both covariate shift and label shift.
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
To address these challenges, we propose OS-Genesis, a novel GUI data synthesis pipeline that reverses the conventional trajectory collection process.
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
Existing efforts in building GUI agents heavily rely on the availability of robust commercial Vision-Language Models (VLMs) such as GPT-4o and GeminiProVision.
Ranked #3 on
Natural Language Visual Grounding
on ScreenSpot
Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems.
SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
Existing zero-shot object navigation methods prompt LLM with the text of spatially closed objects, which lacks enough scene context for in-depth reasoning.
CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts
Taxonomies play a crucial role in various applications by providing a structural representation of knowledge.
Embodied Instruction Following in Unknown Environments
For the task planner, we generate the feasible step-by-step plans for human goal accomplishment according to the task completion process and the known visual clues.
Large Language Models Can Self-Correct with Key Condition Verification
The condition can be an entity in an open-domain question or a numeric value in a math question, which requires minimal effort (via prompting) to identify.
Instructing Large Language Models to Identify and Ignore Irrelevant Conditions
Lastly it instructs the LLMs with the verification on relevant and irrelevant conditions to avoid confusion and improve reasoning paths.
Decoupled Federated Learning on Long-Tailed and Non-IID data with Feature Statistics
In the second stage, DFL-FS employs federated feature regeneration based on global feature statistics and utilizes resampling and weighted covariance to calibrate the global classifier to enhance the model's adaptability to long-tailed data distributions.
TaE: Task-aware Expandable Representation for Long Tail Class Incremental Learning
Existing methods mainly focus on preserving representative samples from previous classes to combat catastrophic forgetting.
Colorectal Polyp Segmentation in the Deep Learning Era: A Comprehensive Survey
Colorectal polyp segmentation (CPS), an essential problem in medical image analysis, has garnered growing research attention.
TransLoc4D: Transformer-based 4D Radar Place Recognition
To validate TransLoc4D we construct two datasets and set up benchmarks for 4D radar place recognition.
Get an A in Math: Progressive Rectification Prompting
Given an initial answer from CoT, PRP iterates a verify-then-rectify process to progressively identify incorrect answers and rectify the reasoning paths.
Anyview: Generalizable Indoor 3D Object Detection with Variable Frames
Existing methods only consider fixed frames of input data for a single detector, such as monocular RGB-D images or point clouds reconstructed from dense multi-view RGB-D images.
SOAR: Scene-debiasing Open-set Action Recognition
The former prevents the decoder from reconstructing the video background given video features, and thus helps reduce the background information in feature learning.
NTU4DRadLM: 4D Radar-centric Multi-Modal Dataset for Localization and Mapping
5) Considered both middle- and large- scale outdoor environments, i. e., the 6 trajectories range from 246m to 6. 95km.
centroIDA: Cross-Domain Class Discrepancy Minimization Based on Accumulative Class-Centroids for Imbalanced Domain Adaptation
Unsupervised Domain Adaptation (UDA) approaches address the covariate shift problem by minimizing the distribution discrepancy between the source and target domains, assuming that the label distribution is invariant across domains.
Dual-Branch Temperature Scaling Calibration for Long-Tailed Recognition
Moreover, we noticed that the traditional calibration evaluation metric, Excepted Calibration Error (ECE), gives a higher weight to low-confidence samples in the minority classes, which leads to inaccurate evaluation of model calibration.
Embodied Task Planning with Large Language Models
Equipping embodied agents with commonsense is important for robots to successfully complete complex human instructions in general environments.
4DRadarSLAM: A 4D Imaging Radar SLAM System for Large-scale Environments based on Pose Graph Optimization
LiDAR-based SLAM may easily fail in adverse weathers (e. g., rain, snow, smoke, fog), while mmWave Radar remains unaffected.
Improvements on Recommender System based on Mathematical Principles
In this article, we will research the Recommender System's implementation about how it works and the algorithms used.
OpenICL: An Open-Source Framework for In-context Learning
However, the implementation of ICL is sophisticated due to the diverse retrieval and inference methods involved, as well as the varying pre-processing requirements for different models, datasets, and tasks.
Category-level Shape Estimation for Densely Cluttered Objects
Then we fuse the feature maps representing the visual information of multi-view RGB images and the pixel affinity learned from the clutter point cloud, where the acquired instance segmentation masks of multi-view RGB images are projected to partition the clutter point cloud.
Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection
This paper attempts to answer this unexplored question by proving a hypothesis: there is a point-labeled dataset where saliency models trained on it can achieve equivalent performance when trained on the densely annotated dataset.
Synthetic Data Supervised Salient Object Detection
In this paper, we propose a novel yet effective method for SOD, coined SODGAN, which can generate infinite high-quality image-mask pairs requiring only a few labeled data, and these synthesized pairs can replace the human-labeled DUTS-TR to train any off-the-shelf SOD model.
A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truth
The full dataset presented in this paper, including the ground truth object classification bounding boxes and haze density measurements, is provided for the community to evaluate their algorithms at: https://a2i2-archangel. vision.
E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles
Unmanned Aerial Vehicles (UAVs) based video text spotting has been extensively used in civil and military domains.
E^2TAD: An Energy-Efficient Tracking-based Action Detector
Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays.
Weakly-guided Self-supervised Pretraining for Temporal Activity Detection
However, such pretrained models are not ideal for downstream detection, due to the disparity between the pretraining and the downstream fine-tuning tasks.
Ranked #3 on
Action Detection
on Charades
Semantic Reinforced Attention Learning for Visual Place Recognition
(2) By exploiting the interpretability of the local weighting scheme, a semantic constrained initialization is proposed so that the local attention can be reinforced by semantic priors.
Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study
Existing diversity tests of samples from GANs are usually conducted qualitatively on a small scale, and/or depends on the access to original training data as well as the trained model parameters.
PCAL: A Privacy-preserving Intelligent Credit Risk Modeling Framework Based on Adversarial Learning
While machine learning is increasingly used in this field, the resulting large-scale collection of user private information has reinvigorated the privacy debate, considering dozens of data breach incidents every year caused by unauthorized hackers, and (potentially even more) information misuse/abuse by authorized parties.
MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis
Estimating the 3D hand pose from a monocular RGB image is important but challenging.
Is There Mode Collapse? A Case Study on Face Generation and Its Black-box Calibration
Generative adversarial networks (GANs) nowadays are capable of producing im-ages of incredible realism.
