Search Results for author:
Found 88 papers, 29 papers with code
Disentangled Knowledge Tracing for Alleviating Cognitive Bias
In the realm of Intelligent Tutoring System (ITS), the accurate assessment of students' knowledge states through Knowledge Tracing (KT) is crucial for personalized learning.
AEIA-MN: Evaluating the Robustness of Multimodal LLM-Powered Mobile Agents Against Active Environmental Injection Attacks
As researchers continuously optimize AI agents to perform tasks more effectively within operating systems, they often neglect to address the critical need for enabling these agents to identify "impostors" within the system.
InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning
Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have made significant advancements in reasoning capabilities.
Optimize Incompatible Parameters through Compatibility-aware Knowledge Integration
The integrated model can be used directly for inference or for further fine-tuning.
Cascaded Self-Evaluation Augmented Training for Efficient Multimodal Large Language Models
SEAT uses more powerful EMLLMs for CoT reasoning, data selection, and evaluation generation, then trains EMLLMs with the synthesized data.
Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation
During training, LLM generates candidate lists to enhance the ranking ability of SRM in collaborative scenarios and enables SRM to update adaptively to capture real-time user interests.
InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
Graphical User Interface (GUI) Agents, powered by multimodal large language models (MLLMs), have shown great potential for task automation on computing devices such as computers and mobile phones.
InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion
Large Language Models (LLMs) have demonstrated strong performance across various reasoning tasks, yet building a single model that consistently excels across all domains remains challenging.
Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendation
To mitigate this, Forward-OFA is designed to establish a structure-guided mapping of real-time behaviors to the parameters of assembled networks.
FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning
Thus, we propose FedCFA, a novel FL framework employing counterfactual learning to generate counterfactual samples by replacing local data critical factors with global average data, aligning local data distributions with the global and mitigating Simpson's Paradox effects.
Reinforcement Learning Enhanced LLMs: A Survey
This paper surveys research in the rapidly growing field of enhancing large language models (LLMs) with reinforcement learning (RL), a technique that enables LLMs to improve their performance by receiving feedback in the form of rewards based on the quality of their outputs, allowing them to generate more accurate, coherent, and contextually appropriate responses.
Preliminary Evaluation of the Test-Time Training Layers in Recommendation System (Student Abstract)
This paper explores the application and effectiveness of Test-Time Training (TTT) layers in improving the performance of recommendation systems.
ProGraph: Temporally-alignable Probability Guided Graph Topological Modeling for 3D Human Reconstruction
To estimate realistic 3D human mesh sequences based on incomplete features, we propose Temporally-alignable Probability Guided Graph Topological Modeling for 3D Human Reconstruction (ProGraph).
Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation
Drawing inspiration from pedagogical theories like Guided Discovery Learning, we propose a novel framework, FiGRet (Fine-grained Guidance for Retrievers), which leverages the language capabilities of LLMs to construct examples from a more granular, information-centric perspective to guide the learning of retrievers.
Unconstrained Model Merging for Enhanced LLM Reasoning
In this work, we propose an unconstrained model merging framework that accommodates both homogeneous and heterogeneous model architectures with a focus on reasoning tasks.
AutoGeo: Automating Geometric Image Dataset Creation for Enhanced Geometry Understanding
With the rapid advancement of large language models, there has been a growing interest in their capabilities in mathematical reasoning.
Semantic Codebook Learning for Dynamic Recommendation Models
Dynamic sequential recommendation (DSR) can generate model parameters based on user behavior to improve the personalization of sequential recommendation under various user preferences.
DIET: Customized Slimming for Incompatible Networks in Sequential Recommendation
In response to these challenges, we propose a customizeD slImming framework for incompatiblE neTworks(DIET).
Causal Distillation for Alleviating Performance Heterogeneity in Recommender Systems
The emerging causal recommendation methods achieve this by modeling the causal effect between user behaviors, however potentially neglect unobserved confounders (\eg, friend suggestions) that are hard to measure in practice.
RemoCap: Disentangled Representation Learning for Motion Capture
Reconstructing 3D human bodies from realistic motion sequences remains a challenge due to pervasive and complex occlusions.
Ranked #25 on
3D Human Pose Estimation
on 3DPW
NieR: Normal-Based Lighting Scene Rendering
In real-world road scenes, diverse material properties lead to complex light reflection phenomena, making accurate color reproduction crucial for enhancing the realism and safety of simulated driving environments.
Gaussian Control with Hierarchical Semantic Graphs in 3D Human Recovery
Although 3D Gaussian Splatting (3DGS) has recently made progress in 3D human reconstruction, it primarily relies on 2D pixel-level supervision, overlooking the geometric complexity and topological relationships of different body parts.
NOVA-3D: Non-overlapped Views for 3D Anime Character Reconstruction
However, there is currently a lack of automated approaches for generating anime characters directly from these 2D designs.
MOSS: Motion-based 3D Clothed Human Synthesis from Monocular Video
To overcome these limitations, we introduce an innovative framework, Motion-Based 3D Clo}thed Humans Synthesis (MOSS), which employs kinematic information to achieve motion-aware Gaussian split on the human surface.
GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting
In this paper, we propose GaussianTalker, a novel method for audio-driven talking head synthesis based on 3D Gaussian Splatting.
MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities
The core mechanism of MergeNet lies in the parameter adapter, which operates by querying the source model's low-rank parameters and adeptly learning to identify and map parameters into the target model.
AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
However, simply adopting models derived from DFKD for real-world applications suffers significant performance degradation, due to the discrepancy between teachers' training data and real-world scenarios (student domain).
ModelGPT: Unleashing LLM's Capabilities for Tailored Model Generation
The rapid advancement of Large Language Models (LLMs) has revolutionized various sectors by automating routine tasks, marking a step toward the realization of Artificial General Intelligence (AGI).
MPOD123: One Image to 3D Content Generation Using Mask-enhanced Progressive Outline-to-Detail Optimization
Specifically in the first stage MPOD123 utilizes the pretrained view-conditioned diffusion model to guide the outline shape optimization of the 3D content.
Sim-GPT: Text Similarity via GPT Annotated Data
Due to the lack of a large collection of high-quality labeled sentence pairs with textual similarity scores, existing approaches for Semantic Textual Similarity (STS) mostly rely on unsupervised techniques or training signals that are only partially correlated with textual similarity, e. g., NLI-based datasets.
Sentiment Analysis through LLM Negotiations
A standard paradigm for sentiment analysis is to rely on a singular LLM and makes the decision in a single round under the framework of in-context learning.
Instruction Tuning for Large Language Models: A Survey
Instruction tuning refers to the process of further training LLMs on a dataset consisting of \textsc{(instruction, output)} pairs in a supervised fashion, which bridges the gap between the next-word prediction objective of LLMs and the users' objective of having LLMs adhere to human instructions.
DisCover: Disentangled Music Representation Learning for Cover Song Identification
We analyze the CSI task in a disentanglement view with the causal graph technique, and identify the intra-version and inter-version effects biasing the invariant learning.
Multi-task Bioassay Pre-training for Protein-ligand Binding Affinity Prediction
By introducing multi-task pre-training to treat the prediction of different affinity labels as different tasks and classifying relative rankings between samples from the same bioassay, MBP learns robust and transferrable structural knowledge from our new ChEMBL-Dock dataset with varied and noisy labels.
Denoising Multi-modal Sequential Recommenders with Contrastive Learning
In contrast, modalities that do not cause users' behaviors are potential noises and might mislead the learning of a recommendation model.
Quantum approximate optimization via learning-based adaptive optimization
Quantum approximate optimization algorithm (QAOA), one of the most representative quantum-classical hybrid algorithms, is designed to solve combinatorial optimization problems by transforming the discrete optimization problem into a classical optimization problem over continuous circuit parameters.
Intelligent Model Update Strategy for Sequential Recommendation
There is an evolving paradigm in this research field that recommendation network learning occurs both on the cloud and on edges with knowledge transfer in between (i. e., edge-cloud collaboration).
Multi-Constraint Molecular Generation using Sparsely Labelled Training Data for Localized High-Concentration Electrolyte Diluent Screening
Recently, machine learning methods have been used to propose molecules with desired properties, which is especially useful for exploring large chemical spaces efficiently.
Protein-Ligand Complex Generator & Drug Screening via Tiered Tensor Transform
The generation of small molecule candidate (ligand) binding poses in its target protein pocket is important for computer-aided drug discovery.
Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning
Moreover, we treat the uncertainty score of frames in a video as a whole, and estimate the difficulty of each video, which can further relieve the burden of video selection.
WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding
WINNER first builds the language decomposition tree in a bottom-up manner, upon which the structural attention mechanism and top-down feature backtracking jointly build a multi-modal decomposition tree, permitting a hierarchical understanding of unstructured videos.
DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization
DUET is deployed on a powerful cloud server that only requires the low cost of forwarding propagation and low time delay of data transmission between the device and the cloud.
Personalizing Intervened Network for Long-tailed Sequential User Behavior Modeling
In this paper, we propose a novel approach that significantly improves the recommendation performance of the tail users while achieving at least comparable performance for the head users over the base model.
CCL4Rec: Contrast over Contrastive Learning for Micro-video Recommendation
Micro-video recommender systems suffer from the ubiquitous noises in users' behaviors, which might render the learned user representation indiscriminating, and lead to trivial recommendations (e. g., popular items) or even weird ones that are far beyond users' interests.
Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendation
Specifically, Re4 encapsulates three backward flows, i. e., 1) Re-contrast, which drives each interest embedding to be distinct from other interests using contrastive learning; 2) Re-attend, which ensures the interest-item correlation estimation in the forward flow to be consistent with the criterion used in final recommendation; and 3) Re-construct, which ensures that each interest embedding can semantically reflect the information of representative items that relate to the corresponding interest.
Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos
In this paper, we introduce a new task, named Temporal Emotion Localization in videos~(TEL), which aims to detect human emotions and localize their corresponding temporal boundaries in untrimmed videos with aligned subtitles.
BOSS: Bottom-up Cross-modal Semantic Composition with Hybrid Counterfactual Training for Robust Content-based Image Retrieval
In this scenario, the input image serves as an intuitive context and background for the search, while the corresponding language expressly requests new traits on how specific characteristics of the query image should be modified in order to get the intended target image.
Intelligent Request Strategy Design in Recommender System
RSs typically put a large number of items into one page to reduce excessive resource consumption from numerous paging requests, which, however, would diminish the RSs' ability to timely renew the recommendations according to users' real-time interest and lead to a poor user experience.
An adaptive graph learning method for automated molecular interactions and properties predictions
In fact, the pursuit of high prediction performance on a limited number of datasets has crystallized their architectures and hyperparameters, making them lose advantage in repurposing to new data generated in drug discovery.
Ranked #1 on
Drug Discovery
on ToxCast (Toxicity Forecaster)
ODBO: Bayesian Optimization with Search Space Prescreening for Directed Protein Evolution
Directed evolution is a versatile technique in protein engineering that mimics the process of natural selection by iteratively alternating between mutagenesis and screening in order to search for sequences that optimize a given property of interest, such as catalytic activity and binding affinity to a specified target.
Contrastive Learning with Positive-Negative Frame Mask for Music Representation
We devise a novel contrastive learning objective to accommodate both self-augmented positives/negatives sampled from the same music.
End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding
To achieve effective grounding under a limited annotation budget, we investigate one-shot video grounding, and learn to ground natural language in all video frames with solely one frame labeled, in an end-to-end manner.
BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation
In this paper, we propose a novel semi-supervised learning (SSL) framework named BoostMIS that combines adaptive pseudo labeling and informative active annotation to unleash the potential of medical image SSL models: (1) BoostMIS can adaptively leverage the cluster assumption and consistency regularization of the unlabeled data according to the current learning status.
A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation
A common problem in both pruning and distillation is to determine compressed architecture, i. e., the exact number of filters per layer and layer configuration, in order to preserve most of the original model capacity.
Retroformer: Pushing the Limits of Interpretable End-to-end Retrosynthesis Transformer
In this paper, we propose Retroformer, a novel Transformer-based architecture for retrosynthesis prediction without relying on any cheminformatics tools for molecule editing.
MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning
We propose the Multimodal relAtional Graph adversarIal inferenCe (MAGIC) framework for diverse and unpaired TextCap.
Learning Large-scale Network Embedding from Representative Subgraph
Then, NES computes the network embedding from this representative subgraph, efficiently.
SPLDExtraTrees: Robust machine learning approach for predicting kinase inhibitor resistance
Drug resistance is a major threat to the global health and a significant concern throughout the clinical treatment of diseases and drug development.
Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI
However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed.
MIC: Model-agnostic Integrated Cross-channel Recommenders
However, existing work are primarily built upon pre-defined retrieval channels, including User-CF (U2U), Item-CF (I2I), and Embedding-based Retrieval (U2I), thus access to the limited correlation between users and items which solely entail from partial information of latent interactions.
Stable Prediction on Graphs with Agnostic Distribution Shift
The results demonstrate that our method outperforms various SOTA GNNs for stable prediction on graphs with agnostic distribution shift, including shift caused by node labels and attributes.
Multi-trends Enhanced Dynamic Micro-video Recommendation
In this paper, we propose the DMR framework to explicitly model dynamic multi-trends of users' current preference and make predictions based on both the history and future potential trends.
Why Do We Click: Visual Impression-aware News Recommendation
In this work, inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news, we propose to capture such visual impression information with visual-semantic modeling for news recommendation.
Fast Extraction of Word Embedding from Q-contexts
In this work, we show that with merely a small fraction of contexts (Q-contexts)which are typical in the whole corpus (and their mutual information with words), one can construct high-quality word embedding with negligible errors.
CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation
In this paper, we propose to learn accurate and robust user representations, which are required to be less sensitive to (attack on) noisy behaviors and trust more on the indispensable ones, by modeling counterfactual data distribution.
Modeling High-order Interactions across Multi-interests for Micro-video Recommendation
Personalized recommendation system has become pervasive in various video platform.
Neural Predictor based Quantum Architecture Search
For instance, a key component of VQAs is the design of task-dependent parameterized quantum circuits (PQCs) as in the case of designing a good neural architecture in deep learning.
Neural Architecture Search
Quantum Physics
TrimNet: learning molecular representation from triplet messages for biomedicine
These advantages have established TrimNet as a powerful and useful computational tool in solving the challenging problem of molecular representation learning.
Ranked #1 on
Drug Discovery
on MUV
Future-Aware Diverse Trends Framework for Recommendation
By diverse trends, supposing the future preferences can be diversified, we propose the diverse trends extractor and the time-aware mechanism to represent the possible trends of preferences for a given user with multiple vectors.
Differentiable Quantum Architecture Search
Hereby, we propose a general framework of differentiable quantum architecture search (DQAS), which enables automated designs of quantum circuits in an end-to-end differentiable fashion.
Quantum Physics
MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination
In this paper, we investigate the problem of text-to-pedestrian synthesis, which has many potential applications in art, design, and video surveillance.
DeVLBert: Learning Deconfounded Visio-Linguistic Representations
In this paper, we propose to investigate the problem of out-of-domain visio-linguistic pretraining, where the pretraining data distribution differs from that of downstream data on which the pretrained model will be fine-tuned.
Poet: Product-oriented Video Captioner for E-commerce
Then, based on the aspects of the video-associated product, we perform knowledge-enhanced spatial-temporal inference on those graphs for capturing the dynamic change of fine-grained product-part characteristics.
Comprehensive Information Integration Modeling Framework for Video Titling
In e-commerce, consumer-generated videos, which in general deliver consumers' individual preferences for the different aspects of certain products, are massive in volume.
Adaptive Double-Exploration Tradeoff for Outlier Detection
We study a variant of the thresholding bandit problem (TBP) in the context of outlier detection, where the objective is to identify the outliers whose rewards are above a threshold.
Grounded and Controllable Image Completion by Incorporating Lexical Semantics
Existing image completion procedure is highly subjective by considering only visual context, which may trigger unpredictable results which are plausible but not faithful to a grounded knowledge.
Contextual Combinatorial Conservative Bandits
The problem of multi-armed bandits (MAB) asks to make sequential decisions while balancing between exploitation and exploration, and have been successfully applied to a wide range of practical scenarios.
DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow
We then directly reconstruct the phase angles from the generations and loads by using the power flow equations.
Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
We introduce a new molecular dataset, named Alchemy, for developing machine learning models useful in chemistry and material science.
Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
The IGNN model is based on an elegant and fundamental idea in information theory as explained in the main text, and it could be easily generalized beyond the contexts of molecular graphs considered in this work.
A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR
Most recent efforts have been devoted to defending noisy labels by discarding noisy samples from the training set or assigning weights to training samples, where the weight associated with a noisy sample is expected to be small.
Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks
Our work is based on an excellent idea that whitening the inputs of neural networks can achieve a fast convergence speed.
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) as DNNs usually have the high capacity to memorize the noisy labels.
Ranked #39 on
Image Classification
on mini WebVision 1.0
Quantum algorithms for feedforward neural networks
The running times of our algorithms can be quadratically faster in the size of the network than their standard classical counterparts since they depend linearly on the number of neurons in the network, as opposed to the number of connections between neurons as in the classical case.
Log Hyperbolic Cosine Loss Improves Variational Auto-Encoder
In Variational Auto-Encoder (VAE), the default choice of reconstruction loss function between the decoded sample and the input is the squared $L_2$.
Learning to Aggregate Ordinal Labels by Maximizing Separating Width
While crowdsourcing has been a cost and time efficient method to label massive samples, one critical issue is quality control, for which the key challenge is to infer the ground truth from noisy or even adversarial data by various users.
Networked Fairness in Cake Cutting
We introduce a graphical framework for fair division in cake cutting, where comparisons between agents are limited by an underlying network structure.
On the Complexity of Trial and Error
On one hand, despite the seemingly very little information provided by the verification oracle, efficient algorithms do exist for a number of important problems.
