Search Results for author:
Found 64 papers, 23 papers with code
Enhancing Code LLM Training with Programmer Attention
Human attention provides valuable yet underexploited signals for code LLM training, offering a perspective beyond purely machine-driven attention.
Breaking the Stigma! Unobtrusively Probe Symptoms in Depression Disorder Diagnosis Dialogue
Stigma has emerged as one of the major obstacles to effectively diagnosing depression, as it prevents users from open conversations about their struggles.
Digital Twin Online Channel Modeling: Challenges,Principles, and Applications
Different from traditional offline channel modeling, digital twin online channel modeling can sense and accurately characterize dynamic wireless channels in real time, and can therefore greatly assist 6G network optimization.
How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyond
With the advancement of large language models (LLMs), intelligent models have evolved from mere tools to autonomous agents with their own goals and strategies for cooperating with humans.
Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts
Understanding the inner workings of Large Language Models (LLMs) is a critical research frontier.
Intuitive Axial Augmentation Using Polar-Sine-Based Piecewise Distortion for Medical Slice-Wise Segmentation
Most data-driven models for medical image analysis rely on universal augmentations to improve performance.
GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering
Despite considerable progress having been made in the LLM era, the reasoning processes of existing methods are often implicit, feeding the entire table into prompts, making it difficult to effectively filter out irrelevant information in the table.
Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP
Then we jointly train a prompt generator, optimized to produce a prompt embedding that stays close to the aggregated summary while minimizing task loss at the same time.
Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
Recent studies have attempted to incorporate camera control into the generation process, but their results are often limited to simple trajectories or lack the ability to generate consistent videos from multiple distinct camera paths for the same scene.
Text Clustering as Classification with LLMs
Second, after integrating similar labels generated by the LLM, we prompt the LLM to assign the most appropriate label to each sample in the dataset.
Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations
With the aid of large language models, current conversational recommender system (CRS) has gaining strong abilities to persuade users to accept recommended items.
On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
These findings highlight that DPORM has limited generalization ability and substantiates the integration of an explicit reward model in iterative DPO approaches.
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
A recent successful approach that falls under the JEPA framework is self-distillation, where an online encoder is trained to predict the output of the target encoder, sometimes using a lightweight predictor network.
CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation
Our in-depth category-level analysis reveals a lack of Chinese cultural knowledge in existing VLMs.
Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets
By leveraging this safety direction, Legend can then leverage the semantic distances of paired responses along this direction to annotate margins automatically.
CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models
To this end, we introduce CLAMBER, a benchmark for evaluating LLMs using a well-organized taxonomy.
ARAIDA: Analogical Reasoning-Augmented Interactive Data Annotation
To address this issue, interactive data annotation utilizes an annotation model to provide suggestions for humans to approve or correct.
STYLE: Improving Domain Transferability of Asking Clarification Questions in Large Language Model Powered Conversational Agents
However, they still struggle to deliver promising performance on unseen domains, struggling to achieve effective domain transferability.
Selective Annotation via Data Allocation: These Data Should Be Triaged to Experts for Annotation Rather Than the Model
As such, informative or hard data is assigned to the expert for annotation, while easy data is handled by the model.
Co-Matching: Towards Human-Machine Collaborative Legal Case Matching
However, successful legal case matching requires the tacit knowledge of legal practitioners, which is difficult to verbalize and encode into machines.
Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective
Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences.
Concept -- An Evaluation Protocol on Conversational Recommender Systems with System-centric and User-centric Factors
The conversational recommendation system (CRS) has been criticized regarding its user experience in real-world scenarios, despite recent significant progress achieved in academia.
Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation
We investigate non-collaborative dialogue agents, which are expected to engage in strategic conversations with diverse users, for securing a mutual agreement that leans favorably towards the system's objectives.
Arellano-Bond LASSO Estimator for Dynamic Linear Panel Models
We show that weak dependence along the panel's time series dimension naturally implies approximate sparsity of the most informative moment conditions, motivating the following approach to remove the bias: First, apply LASSO to the cross-section data at each time period to construct most informative (and cross-fitted) instruments, using lagged values of suitable covariates.
Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
Existing vision-language models exhibit strong generalization on a variety of visual domains and tasks.
Cross-Space Adaptive Filter: Integrating Graph Topology and Node Attributes for Alleviating the Over-smoothing Problem
To this end, various methods have been proposed to create an adaptive filter by incorporating an extra filter (e. g., a high-pass filter) extracted from the graph topology.
DREditor: An Time-efficient Approach for Building a Domain-specific Dense Retrieval Model
Motivated by this, we develop a time-efficient approach called DREditor to edit the matching rule of an off-the-shelf dense retrieval model to suit a specific domain.
Towards Equipping Transformer with the Ability of Systematic Compositionality
One of the key factors in language productivity and human cognition is the ability of systematic compositionality, which refers to understanding composed unseen examples of seen primitives.
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
In this paper, we introduce LiDAR (Linear Discriminant Analysis Rank), a metric designed to measure the quality of representations within JE architectures.
Adaptivity and Modularity for Efficient Generalization Over Task Complexity
We investigate how the use of a mechanism for adaptive and modular computation in transformers facilitates the learning of tasks that demand generalization over the number of sequential computation steps (i. e., the depth of the computation graph).
Cryo-Electron Ptychography: Applications and Potential in Biological Characterisation
There is a clear need for developments in characterisation techniques that provide detailed information about structure-function relationships in biology.
DUET: 2D Structured and Approximately Equivariant Representations
We propose 2D strUctured and EquivarianT representations (coined DUET), which are 2d representations organized in a matrix structure, and equivariant with respect to transformations acting on the input data.
Semi-Supervised and Long-Tailed Object Detection with CascadeMatch
This paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature.
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors
We do so by Masked Augmentation Subspace Training (or MAST) to encode in the single feature space the priors from different data augmentations in a factorized way.
Unified Vision and Language Prompt Learning
Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models like CLIP.
Pre-Training Representations of Binary Code Using Contrastive Learning
We further analyze the impact of human-written and synthetic comments on binary code comprehension tasks, revealing a significant performance disparity.
A Weighted Random Forest Based PositioningAlgorithm for 6G Indoor Communications
Due to the indoor none-line-of-sight (NLoS) propagation and multi-access interference (MAI), it is a great challenge to achieve centimeter-level positioning accuracy in indoor scenarios.
Position Prediction as an Effective Pretraining Strategy
This pretraining strategy which has been used in BERT models in NLP, Wav2Vec models in Speech and, recently, in MAE models in Vision, forces the model to learn about relationships between the content in different parts of the input using autoencoding related objectives.
Efficient Representation Learning via Adaptive Context Pooling
Inspired by the success of ConvNets that are combined with pooling to capture long-range dependencies, we learn to pool neighboring features for each token before computing attention in a given attention layer.
An Empirical Study of Language Model Integration for Transducer based Speech Recognition
Based on the DR method, we propose a low-order density ratio method (LODR) by replacing the estimation with a low-order weak language model.
Open-Vocabulary DETR with Conditional Matching
To this end, we propose a novel open-vocabulary detector based on DETR -- hence the name OV-DETR -- which, once trained, can detect any object given its class name or an exemplar image.
Ranked #25 on
Open Vocabulary Object Detection
on MSCOCO
Artificial intelligence enabled radio propagation for communications-Part I: Channel characterization and antenna-channel optimization
To provide higher data rates, as well as better coverage, cost efficiency, security, adaptability, and scalability, the 5G and beyond 5G networks are developed with various artificial intelligence techniques.
Artificial intelligence enabled radio propagation for communications-Part II: Scenario identification and channel modeling
This two-part paper investigates the application of artificial intelligence (AI) and in particular machine learning (ML) to the study of wireless propagation channels.
A Geometry-Based Stochastic Model for Truck Communication Channels in Freeway Scenarios
We validate this model by contrasting the root-mean-square delay spread and the angular spreads of departure/arrival derived from the channel model with the outcomes directly derived from the measurements.
A Dot Product Attention Free Transformer
We introduce Dot Product Attention Free Transformer (DAFT), an efficient variant of Transformers \citep{transformer} that eliminates the query-key dot product in self attention.
Ranked #678 on
Image Classification
on ImageNet
An Attention Free Transformer
We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention.
Uniform Inference on High-dimensional Spatial Panel Networks
We propose employing a debiased-regularized, high-dimensional generalized method of moments (GMM) framework to perform inference on large-scale spatial panel networks.
MetricOpt: Learning to Optimize Black-Box Evaluation Metrics
This leads to consistent improvements since the value function provides effective metric supervision during finetuning, and helps to correct the potential bias of loss-only supervision.
FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation
We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data scarcity issue by augmenting the feature space especially for rare classes.
Neural-DINF: A Neural Network based Framework for Measuring Document Influence
Measuring the scholarly impact of a document without citations is an important and challenging problem.
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment
In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric.
Dense Intrinsic Appearance Flow for Human Pose Transfer
Unlike existing methods, we propose to estimate dense and intrinsic 3D appearance flow to better guide the transfer of pixels between poses.
Pose Guided Human Video Generation
Human pose, on the other hand, can represent motion patterns intrinsically and interpretably, and impose the geometric constraints regardless of appearance.
Deep Imbalanced Learning for Face Recognition and Attribute Prediction
Data for face analysis often exhibit highly-skewed class distribution, i. e., most data belong to a few majority classes, while the minority classes only contain a scarce amount of instances.
Mask-aware Photorealistic Face Attribute Manipulation
The task of face attribute manipulation has found increasing applications, but still remains challeng- ing with the requirement of editing the attributes of a face image while preserving its unique details.
CNNs are Globally Optimal Given Multi-Layer Support
Stochastic Gradient Descent (SGD) is the central workhorse for training modern CNNs.
Learning to Disambiguate by Asking Discriminative Questions
In particular, each tuple consists of a pair of images and 4. 6 discriminative questions (as positive samples) and 5. 9 non-discriminative questions (as negative samples) on average.
Learning Policies for Adaptive Tracking with Deep Feature Cascades
Our fundamental insight is to take an adaptive approach, where easy frames are processed with cheap features (such as pixel values), while challenging frames are processed with invariant but expensive deep features.
Need for Speed: A Benchmark for Higher Frame Rate Object Tracking
In this paper, we propose the first higher frame rate video dataset (called Need for Speed - NfS) and benchmark for visual object tracking.
Local Similarity-Aware Deep Feature Embedding
Existing deep embedding methods in vision tasks are capable of learning a compact Euclidean space from images, where Euclidean distances correspond to a similarity metric.
Ranked #27 on
Metric Learning
on CUB-200-2011
Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking
In this paper, we develop a new approach of spatially supervised recurrent convolutional neural networks for visual object tracking.
Unsupervised Learning of Discriminative Attributes and Visual Representations
Attributes offer useful mid-level features to interpret visual data.
Learning Deep Representation for Imbalanced Classification
We further demonstrate that more discriminative deep representation can be learned by enforcing a deep network to maintain both inter-cluster and inter-class margins.
Discriminative Sparse Neighbor Approximation for Imbalanced Learning
These methods further deteriorate on small, imbalanced data that has a large degree of class overlap.
