Search Results for author:
Found 44 papers, 17 papers with code
LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models
Inspired by the application of reinforcement learning in mathematical problem-solving to encourage step-by-step reasoning in LLMs, we propose LearNAT (Learning NL2SQL with AST-guided Task Decomposition), a novel framework that improves the performance of open-source LLMs on complex NL2SQL tasks through task decomposition and reinforcement learning.
HyperGraphRAG: Retrieval-Augmented Generation with Hypergraph-Structured Knowledge Representation
To retrieve and generate over hypergraphs, we introduce a complete pipeline with a hypergraph construction method, a hypergraph retrieval strategy, and a hypergraph-guided generation mechanism.
TRACE: Real-Time Multimodal Common Ground Tracking in Situated Collaborative Dialogues
We present TRACE, a novel system for live *common ground* tracking in situated collaborative tasks.
Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability
Classic uniform generalization bounds, which rely on VC-dimension or Rademacher complexity, fail to explain the significant attribute that over-parameterized models in deep learning exhibit nice generalizability.
Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
Wasserstein distributionally robust optimization (WDRO) optimizes against worst-case distributional shifts within a specified uncertainty set, leading to enhanced generalization on unseen adversarial examples, compared to standard adversarial training which focuses on pointwise adversarial perturbations.
A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models
In order to streamline the fine-tuning of foundation models, Low-Rank Adapters (LoRAs) have been substantially adopted across various fields, including instruction tuning and domain adaptation.
SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL
To address these issues, we propose SQL-o1, a Self-Reward-based heuristic search method designed to enhance the reasoning ability of LLMs in SQL query generation.
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs
While Key-Value (KV) caching effectively trades memory for computation to enhance inference efficiency, the growing memory footprint from extensive KV caches significantly reduces throughput and restricts prolonged deployment on memory-constrained GPU devices.
PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning
Federated learning (FL) has gained widespread attention for its privacy-preserving and collaborative learning capabilities.
KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
Moreover, it employs MCTS, a heuristic search method driven by policy and reward models, to balance agentic exploration's performance and search space.
TSVC:Tripartite Learning with Semantic Variation Consistency for Robust Image-Text Retrieval
In order to resolve this problem, we introduce a Tripartite learning with Semantic Variation Consistency (TSVC) for robust image-text retrieval.
PowerMLP: An Efficient Version of KAN
The Kolmogorov-Arnold Network (KAN) is a new network architecture known for its high accuracy in several tasks such as function fitting and PDE solving.
Speech Is Not Enough: Interpreting Nonverbal Indicators of Common Knowledge and Engagement
Our goal is to develop an AI Partner that can provide support for group problem solving and social dynamics.
One-Shot Real-to-Sim via End-to-End Differentiable Simulation and Rendering
Identifying predictive world models for robots in novel environments from sparse online observations is essential for robot task planning and execution in novel environments.
Bridging Large Language Models and Graph Structure Learning Models for Robust Representation Learning
In this paper, we introduce LangGSL, a robust framework that integrates the complementary strengths of pre-trained language models and GSLMs to jointly enhance both node feature and graph structure learning.
Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey
The rapid development of artificial intelligence has constantly reshaped the field of intelligent healthcare and medicine.
Few-shot Scooping Under Domain Shift via Simulated Maximal Deployment Gaps
Our Deep Kernel Calibration with Maximal Deployment Gaps (kCMD) strategy explicitly trains a deep kernel model to adapt to large domain shifts by creating simulated maximal deployment gaps from an offline training dataset and training models to overcome these deployment gaps during training.
RevGNN: Negative Sampling Enhanced Contrastive Graph Learning for Academic Reviewer Recommendation
Therefore, investigating how to better comprehend the negative labeling of unobserved interactions in academic reviewer recommendations is a significant challenge.
CP-Prompt: Composition-Based Cross-modal Prompting for Domain-Incremental Continual Learning
The key challenge of cross-modal domain-incremental learning (DIL) is to enable the learning model to continuously learn from novel data with different feature distributions under the same task without forgetting old ones.
T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
The recent development of Sora leads to a new era in text-to-video (T2V) generation.
Common Ground Tracking in Multimodal Dialogue
Within Dialogue Modeling research in AI and NLP, considerable attention has been spent on ``dialogue state tracking'' (DST), which is the ability to update the representations of the speaker's needs at each turn in the dialogue by taking into account the past dialogue moves and history.
OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining
We envisage that OAG-Bench can serve as a common ground for the community to evaluate and compare algorithms in academic graph mining, thereby accelerating algorithm development and advancement in this field.
Semantic Object-level Modeling for Robust Visual Camera Relocalization
Due to the improvement of CNN-based object detection algorithm, the robustness of visual relocalization is greatly enhanced especially in viewpoints where classical methods fail.
Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
Availability attacks can prevent the unauthorized use of private data and commercial datasets by generating imperceptible noise and making unlearnable examples before release.
Detection and Defense of Unlearnable Examples
Detectability of unlearnable examples with simple networks motivates us to design a novel defense method.
Adapting to climate change: Long-term impact of wind resource changes on China's power system resilience
Modern society's reliance on power systems is at risk from the escalating effects of wind-related climate change.
Scalable CP Decomposition for Tensor Learning using GPU Tensor Cores
However, the application of tensor decomposition is largely hindered by the exponential increment of the computational complexity and storage consumption with the size of tensors.
ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models
Knowledge Base Question Answering (KBQA) aims to answer natural language questions over large-scale knowledge bases (KBs), which can be summarized into two crucial steps: knowledge retrieval and semantic parsing.
Ranked #1 on
Knowledge Base Question Answering
on WebQuestionsSP
Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction
However, the construction of NKGs remains at a coarse-grained level, which is always in a single schema, ignoring the order and variable arity of entities.
Event-based N-ary Relaiton Extraction
Hypergraph-based N-ary Relaiton Extraction
+3
Human-Inspired Facial Sketch Synthesis with Dynamic Adaptation
Besides, different artists may use diverse drawing techniques and create multiple styles of sketches; but the style is globally consistent in a sketch.
Continual Learning as Computationally Constrained Reinforcement Learning
The design of such agents, which remains a long-standing challenge of artificial intelligence, is addressed by the subject of continual learning.
Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections
To remedy this issue, we present a novel surface reconstruction framework, NeuS-HSR, based on implicit neural rendering.
Consistent Depth Prediction for Transparent Object Reconstruction from RGB-D Camera
We compare the metrics on our dataset and SLAM reconstruction results in both synthetic scenes and real scenes with the previous methods.
Is Stochastic Gradient Descent Near Optimal?
However, existing computational theory suggests that, even for single-hidden-layer teacher networks, to attain small error for all such teacher networks, the computation required to achieve this sample complexity is intractable.
Deep Learning Assisted Optimization for 3D Reconstruction from Single 2D Line Drawings
In this paper, we revisit the long-standing problem of automatic reconstruction of 3D objects from single line drawings.
AMinerGNN: Heterogeneous Graph Neural Network for Paper Click-through Rate Prediction with Fusion Query
Paper recommendation with user-generated keyword is to suggest papers that simultaneously meet user's interests and are relevant to the input keyword.
An Information-Theoretic Framework for Supervised Learning
For a particular prior distribution on weights, we establish sample complexity bounds that are simultaneously width independent and linear in depth.
Over-the-Air Aggregation for Federated Learning: Waveform Superposition and Prototype Validation
In this paper, we develop an orthogonal-frequency-division-multiplexing (OFDM)-based over-the-air (OTA) aggregation solution for wireless federated learning (FL).
Fully Three-dimensional Radial Visualization
We develop methodology for three-dimensional (3D) radial visualization (RadViz) of multidimensional datasets.
Heterogeneous Graph-Based Multimodal Brain Network Learning
Other experiments also indicate that our proposed model with a pretraining strategy alleviates the problem of limited labelled data and yields a significant improvement in accuracy.
Systematic design and experimental demonstration of transmission-type multiplexed acoustic meta-holograms
Acoustic holograms have promising applications in sound-field reconstruction, particle manipulation, ultrasonic haptics and therapy.
Applied Physics
Transfusion: A Novel SLAM Method Focused on Transparent Objects
In this paper, we propose a novel SLAM approach called transfusion that allows transparent object existence and recovery in the video input.
A Deep Learning Method for Complex Human Activity Recognition Using Virtual Wearable Sensors
The experimental results show that the proposed method can surprisingly converge in a few iterations and achieve an accuracy of 91. 15% on a real IMU dataset, demonstrating the efficiency and effectiveness of the proposed method.
Visualization of Labeled Mixed-featured Datasets
We develop methodology for visualization of labeled mixed-featured datasets.
