Search Results for author:
Found 55 papers, 15 papers with code
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
Instruction-based image editing enables robust image modification via natural language prompts, yet current methods face a precision-efficiency tradeoff.
PathoHR: Breast Cancer Survival Prediction on High-Resolution Pathological Images
Breast cancer survival prediction in computational pathology presents a remarkable challenge due to tumor heterogeneity.
HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization
This paper introduces HarmonySet, a comprehensive dataset designed to advance video-music understanding.
Nexus-O: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision
For the third question, we design the speech data synthesis pipeline to obtain high-quality speech training datasets, covering various real-world scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
QUBE: Enhancing Automatic Heuristic Design via Quality-Uncertainty Balanced Evolution
Solving NP-hard problems traditionally relies on heuristics, yet manually designing effective heuristics for complex problems remains a significant challenge.
Energy-Efficient RIS-Aided Cell-Free Massive MIMO Systems: Application, Opportunities, and Challenges
Reconfigurable intelligent surfaces (RIS)-assisted cell-free massive multiple-input multiple-output (CF mMIMO) systems have emerged as a promising technology for sixth-generation communication systems.
Push the Limit of Multi-modal Emotion Recognition by Prompting LLMs with Receptive-Field-Aware Attention Weighting
In this paper, we present a framework, Lantern, that can improve the performance of a certain vanilla model by prompting large language models with receptive-field-aware attention weighting.
MME-Finance: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning
In recent years, multimodal benchmarks for general domains have guided the rapid development of multimodal models on general tasks.
Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas
Scientific innovation is pivotal for humanity, and harnessing large language models (LLMs) to generate research ideas could transform discovery.
LLMs + Persona-Plug = Personalized LLMs
By attaching this embedding to the task input, LLMs can better understand and capture user habits and preferences, thereby producing more personalized outputs without tuning their own parameters.
Sparse Signal Reconstruction for Overdispersed Low-photon Count Biomedical Imaging Using $\ell_p$ Total Variation
The negative binomial model, which generalizes the Poisson distribution model, can be found in applications involving low-photon signal recovery, including medical imaging.
Negative Binomial Matrix Completion
In our experiments, we demonstrate that the NB model outperforms Poisson matrix completion in various noise and missing data settings on real data.
Alternating Direction Method of Multipliers for Negative Binomial Model with The Weighted Difference of Anisotropic and Isotropic Total Variation
However, this model assumes that the mean and variance of the signal's noise distribution are equal.
GPT-based Textile Pilling Classification Using 3D Point Cloud Data
To the best of our knowledge, it is the first publicly available eight-categories 3D point cloud dataset in the field of textile pilling assessment.
DaRec: A Disentangled Alignment Framework for Large Language Model and Recommender System
In this work, we prove that directly aligning the representations of LLMs and collaborative models is sub-optimal for enhancing downstream recommendation tasks performance, based on the information theorem.
FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention
FreeLong blends the low-frequency components of global video features, which encapsulate the entire video sequence, with the high-frequency components of local video features that focus on shorter subsequences of frames.
Hyperbolic Knowledge Transfer in Cross-Domain Recommendation System
Cross-Domain Recommendation (CDR) seeks to utilize knowledge from different domains to alleviate the problem of data sparsity in the target recommendation domain, and it has been gaining more attention in recent years.
Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs
This decline can be attributed to the loss of key information during the compression process.
G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine Translation
Moreover, to enhance the diversity of the training data we maximize the variety of influences they have on the model by clustering on their gradients and resampling.
Automated Multi-level Preference for MLLMs
To verify our viewpoint, we present the Automated Multi-level Preference (AMP) framework for MLLMs.
Understanding the Therapeutic Relationship between Counselors and Clients in Online Text-based Counseling using LLMs
Through further LLM-based evaluations on additional conversations, our findings underscore the challenges counselors face in cultivating strong online relationships with clients.
Unveiling the Secrets of Engaging Conversations: Factors that Keep Users Hooked on Role-Playing Dialog Agents
With the growing humanlike nature of dialog agents, people are now engaging in extended conversations that can stretch from brief moments to substantial periods of time.
FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax
Text-to-video (T2V) generation is a rapidly growing research area that aims to translate the scenes, objects, and actions within complex video text into a sequence of coherent visual frames.
ActiveDC: Distribution Calibration for Active Finetuning
Firstly, we select samples for annotation by optimizing the distribution similarity between the subset to be selected and the entire unlabeled pool in continuous space.
Data-Driven Modeling of an Unsaturated Bentonite Buffer Model Test Under High Temperatures Using an Enhanced Axisymmetric Reproducing Kernel Particle Method
In deep geological repositories for high level nuclear waste with close canister spacings, bentonite buffers can experience temperatures higher than 100 {\deg}C. In this range of extreme temperatures, phenomenological constitutive laws face limitations in capturing the thermo-hydro-mechanical (THM) behavior of the bentonite, since the pre-defined functional constitutive laws often lack generality and flexibility to capture a wide range of complex coupling phenomena as well as the effects of stress state and path dependency.
NEOLAF, an LLM-powered neural-symbolic cognitive architecture
This paper presents the Never Ending Open Learning Adaptive Framework (NEOLAF), an integrated neural-symbolic cognitive architecture that models and constructs intelligent agents.
AUGUST: an Automatic Generation Understudy for Synthesizing Conversational Recommendation Datasets
High-quality data is essential for conversational recommendation systems and serves as the cornerstone of the network architecture development and training strategy design.
Pretrained Language Model based Web Search Ranking: From Relevance to Satisfaction
In this work, we focus on ranking user satisfaction rather than relevance in web search, and propose a PLM-based framework, namely SAT-Ranker, which comprehensively models different dimensions of user satisfaction in a unified manner.
Rediscovery of Numerical Lüscher's Formula from the Neural Network
We present that by predicting the spectrum in discrete space from the phase shift in continuous space, the neural network can remarkably reproduce the numerical L\"uscher's formula to a high precision.
Personalizing or Not: Dynamically Personalized Federated Learning with Incentives
This dynamically personalized FL technique incentivizes clients to participate in personalizing local models while allowing the adoption of the global model when it performs better.
A Simple yet Effective Framework for Active Learning to Rank
To handle the diverse query requests from users at web-scale, Baidu has done tremendous efforts in understanding users' queries, retrieve relevant contents from a pool of trillions of webpages, and rank the most relevant webpages on the top of results.
Interpretable Fault Diagnosis of Rolling Element Bearings with Temporal Logic Neural Network
Machine learning-based methods have achieved successful applications in machinery fault diagnosis.
Learning Confidence for Transformer-based Neural Machine Translation
Confidence estimation aims to quantify the confidence of the model prediction, providing an expectation of success.
Federated Two-stage Learning with Sign-based Voting
In this paper, we design a federated two-stage learning framework that augments prototypical federated learning with a cut layer on devices and uses sign-based stochastic gradient descent with the majority vote method on model updates.
CRIS: CLIP-Driven Referring Image Segmentation
In addition, we present text-to-pixel contrastive learning to explicitly enforce the text feature similar to the related pixel-level features and dissimilar to the irrelevances.
Interpreting Deep Knowledge Tracing Model on EdNet Dataset
With more deep learning techniques being introduced into the knowledge tracing domain, the interpretability issue of the knowledge tracing models has aroused researchers' attention.
Attention Calibration for Transformer in Neural Machine Translation
Attention mechanisms have achieved substantial improvements in neural machine translation by dynamically selecting relevant inputs for different predictions.
Towards Heterogeneous Clients with Elastic Federated Learning
Training in heterogeneous and potentially massive networks introduces bias into the system, which is originated from the non-IID data and the low participation rate in reality.
Efficient Speech Emotion Recognition Using Multi-Scale CNN and Attention
Emotion recognition from speech is a challenging task.
RevCore: Review-augmented Conversational Recommendation
Existing conversational recommendation (CR) systems usually suffer from insufficient item information when conducted on short dialogue history and unfamiliar items.
RoFormer: Enhanced Transformer with Rotary Position Embedding
Then, we propose a novel method named Rotary Position Embedding(RoPE) to effectively leverage the positional information.
Ranked #1 on
Semantic Text Matching
on CAIL2019-SCM - test
GINet: Graph Interaction Network for Scene Parsing
GI unit is further improved by the SC-loss to enhance the semantic representations over the exemplar-based semantic graph.
CASIA's System for IWSLT 2020 Open Domain Translation
This paper describes the CASIA{'}s system for the IWSLT 2020 open domain translation task.
Towards Interpretable Deep Learning Models for Knowledge Tracing
We thus propose to adopt the post-hoc method to tackle the interpretability issue for deep learning based knowledge tracing (DLKT) models.
Object Instance Mining for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) using only image-level annotations has attracted growing attention over the past few years.
Ranked #16 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
C-DLinkNet: considering multi-level semantic features for human parsing
Human parsing is an essential branch of semantic segmentation, which is a fine-grained semantic segmentation task to identify the constituent parts of human.
Learning Efficient Video Representation with Video Shuffle Networks
To this end, we propose the video shuffle, a parameter-free plug-in component that efficiently reallocates the inputs of 2D convolution so that its receptive field can be extended to the temporal dimension.
Structured Pruning for Efficient ConvNets via Incremental Regularization
Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance degrade.
Provably Optimal Algorithms for Generalized Linear Contextual Bandits
Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search.
Statistical and Computational Guarantees of Lloyd's Algorithm and its Variants
Lloyd's algorithm, proposed in 1957, is still possibly the most widely used clustering algorithm in practice due to its simplicity and empirical performance.
Exact Exponent in Optimal Rates for Crowdsourcing
In many machine learning applications, crowdsourcing has become the primary means for label collection.
Optimal Estimation and Completion of Matrices with Biclustering Structures
Biclustering structures in data matrices were first formalized in a seminal paper by John Hartigan (1972) where one seeks to cluster cases and variables simultaneously.
Multi-Linear Interactive Matrix Factorization
Recommender systems, which can significantly help users find their interested items from the information era, has attracted an increasing attention from both the scientific and application society.
Linearly Supporting Feature Extraction For Automated Estimation Of Stellar Atmospheric Parameters
On real spectra, we extracted 23 features to estimate $T_{eff}$, 62 features for log$~g$, and 68 features for [Fe/H].
Individualized Rank Aggregation using Nuclear Norm Regularization
In recent years rank aggregation has received significant attention from the machine learning community.
