Search Results for author:
Found 34 papers, 14 papers with code
PromptHash: Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing Retrieval
Cross-modal hashing is a promising approach for efficient data retrieval and storage optimization.
Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning
Subsequently, we propose GGEUR, which leverages global geometric shapes to guide the generation of new samples, enabling a closer approximation to the ideal global distribution.
Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding
The performance of VLA models can be improved by integrating with action chunking, a critical technique for effective control.
Bridging the Creativity Understanding Gap: Small-Scale Human Alignment Enables Expert-Level Humor Ranking in LLMs
Large Language Models (LLMs) have shown significant limitations in understanding creative content, as demonstrated by Hessel et al. (2023)'s influential work on the New Yorker Cartoon Caption Contest (NYCCC).
Revealing Bias Formation in Deep Neural Networks Through the Geometric Mechanisms of Human Visual Decoupling
Deep neural networks (DNNs) often exhibit biases toward certain categories during object recognition, even under balanced training data conditions.
Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount
However, models still exhibit category bias even in datasets where instance counts are relatively balanced, clearly indicating that instance count alone cannot explain this phenomenon.
Channel Gain Map Construction based on Subregional Learning and Prediction
The construction of channel gain map (CGM) is essential for realizing environment-aware wireless communications expected in 6G, for which a fundamental problem is how to predict the channel gains at unknown locations effectively by a finite number of measurements.
First Token Probability Guided RAG for Telecom Question Answering
Large Language Models (LLMs) have garnered significant attention for their impressive general-purpose capabilities.
Multiple-choice
Multiple Choice Question Answering (MCQA)
+2
RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement
Existing large language models (LLMs) show exceptional problem-solving capabilities but might struggle with complex reasoning tasks.
Efficient Ternary Weight Embedding Model: Bridging Scalability and Performance
Embedding models have become essential tools in both natural language processing and computer vision, enabling efficient semantic search, recommendation, clustering, and more.
Exploring applications of topological data analysis in stock index movement prediction
Topological Data Analysis (TDA) has recently gained significant attention in the field of financial prediction.
DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes
Grasping in cluttered scenes remains highly challenging for dexterous hands due to the scarcity of data.
PersLLM: A Personified Training Approach for Large Language Models
Large language models exhibit aspects of human-level intelligence that catalyze their application as human-like agents in domains such as social simulations, human-machine interactions, and collaborative multi-agent systems.
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
We present a novel multimodal preference dataset for creative tasks, consisting of over 250 million human ratings on more than 2. 2 million captions, collected through crowdsourcing rating data for The New Yorker's weekly cartoon caption contest over the past eight years.
Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformation
Instead of completely relying on support images, we propose Self-Matching Transformation (SMT) to construct query-specific transformation matrices based on query images themselves to transform domain-specific query features into domain-agnostic ones.
MAML MOT: Multiple Object Tracking based on Meta-Learning
With the advancement of video analysis technology, the multi-object tracking (MOT) problem in complex scenes involving pedestrians is gaining increasing importance.
Accelerating Distributed Deep Learning using Lossless Homomorphic Compression
As deep neural networks (DNNs) grow in complexity and size, the resultant increase in communication overhead during distributed training has become a significant bottleneck, challenging the scalability of distributed training systems.
On a Foundation Model for Operating Systems
This paper lays down the research agenda for a domain-specific foundation model for operating systems (OSes).
Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts
Extensive experiments and analysis on five real multi-center medical image datasets demonstrate the superiority of FEAL over the state-of-the-art active learning methods in federated scenarios with domain shifts.
On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval
However, prior works for Few-shot VDER mainly address the problem at the document level with a predefined global entity space, which doesn't account for the entity-level few-shot scenario: target entity types are locally personalized by each task and entity occurrences vary significantly among documents.
MCRAGE: Synthetic Healthcare Data for Fairness
Machine learning models trained on class-imbalanced EHR datasets perform significantly worse in deployment for individuals of the minority classes compared to those from majority classes, which may lead to inequitable healthcare outcomes for minority groups.
DocumentNet: Bridging the Data Gap in Document Pre-Training
Document understanding tasks, in particular, Visually-rich Document Entity Retrieval (VDER), have gained significant attention in recent years thanks to their broad applications in enterprise AI.
PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations
Learning a generalizable object manipulation policy is vital for an embodied agent to work in complex real-world scenes.
UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
Trained on our synthesized large-scale dexterous grasp dataset, this model enables us to sample diverse and high-quality dexterous grasp poses for the object point cloud. For the second stage, we propose to replace the motion planning used in parallel gripper grasping with a goal-conditioned grasp policy, due to the complexity involved in dexterous grasping execution.
Self-Attentive Sequential Recommendation with Cheap Causal Convolutions
We evaluate the effectiveness of the proposed model in terms of both accurate and calibrated sequential recommendation.
Teaching Neural Module Networks to Do Arithmetic
Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning.
DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation
Robotic dexterous grasping is the first step to enable human-like dexterous object manipulation and thus a crucial robotic technology.
Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild
We for the first time propose a point cloud based hand joint tracking network, HandTrackNet, to estimate the inter-frame hand joint motion.
A Competitive Method for Dog Nose-print Re-identification
Vision-based pattern identification (such as face, fingerprint, iris etc.)
Long-Tail Session-based Recommendation from Calibration
Accurate predictions in session-based recommendations have progressed, but a few studies have focused on skewed recommendation lists caused by popularity bias.
Projective Manifold Gradient Layer for Deep Rotation Regression
Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem.
HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalities
To deal with task heterogeneity and promote fast within-task adaptions for each type of tasks, in this paper, we propose HetMAML, a task-heterogeneous model-agnostic meta-learning framework, which can capture both the type-specific and globally shared knowledge and can achieve the balance between knowledge customization and generalization.
Towards a Unified Evaluation of Explanation Methods without Ground Truth
This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges.
