Search Results for author:
Found 74 papers, 21 papers with code
基于循环交互注意力网络的问答立场分析(A Recurrent Interactive Attention Network for Answer Stance Analysis)
针对问答立场任务中, 现有方法难以提取问答文本间的依赖关系问题, 本文提出一种基于循环交互注意力(Recurrent Interactive Attention, RIA)网络的问答立场分析方法。该方法通过模仿人类阅读理解时的思维方式, 基于交互注意力机制和循环迭代方法, 有效地从问题和答案的相互联系中挖掘问答文本的立场信息。此外, 该方法将问题进行陈述化表示, 有效地解决疑问句表述下问题文本无法明确表达自身立场的问题。实验结果表明, 本文方法取得了比现有模型方法更好的效果, 同时证明该方法能有效拟合问答立场分析任务中的问答对依赖关系。
Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations
The emotion cause is a stimulus for human emotions.
Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems
To bridge this gap, we introduce RecInter, a novel agent-based simulation platform for recommender systems featuring a robust interaction mechanism.
Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario Games
We hope our approach can inspire future research on using reinforcement learning to improve the generalization of LLMs.
Trustless Autonomy: Understanding Motivations, Benefits and Governance Dilemma in Self-Sovereign Decentralized AI Agents
The recent trend of self-sovereign Decentralized AI Agents (DeAgents) combines Large Language Model (LLM)-based AI agents with decentralization technologies such as blockchain smart contracts and trusted execution environments (TEEs).
The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News
Concurrently, the InsightFlow Agents consist of two specialized sub-agents: the Synthesis Agent and the Analysis Agent.
How Does Monetary Policy Influence the U.S. Treasury Bond Yields, and What are the Implications for Portfolio Managers?
This paper investigates the impact of monetary policy surprises on U. S. Treasury bond yields and the implications for portfolio managers.
Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability
The diffusion models, in early stages focus on constructing basic image structures, while the refined details, including local features and textures, are generated in later stages.
Enhancing User Sequence Modeling through Barlow Twins-based Self-Supervised Learning
User sequence modeling is crucial for modern large-scale recommendation systems, as it enables the extraction of informative representations of users and items from their historical interactions.
CFIS-YOLO: A Lightweight Multi-Scale Fusion Network for Edge-Deployable Wood Defect Detection
Wood defect detection is critical for ensuring quality control in the wood processing industry.
NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains.
Cross-Domain Few-Shot
Cross-Domain Few-Shot Object Detection
+3
EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety
Experiments conducted in popular character-based chatbots show that emotionally engaging dialogues can lead to psychological deterioration in vulnerable users, with mental state deterioration in more than 34. 4% of the simulations.
EQ-Negotiator: An Emotion-Reasoning LLM Agent in Credit Dialogues
While large language model (LLM)-based chatbots have been applied for effective engagement in credit dialogues, their capacity for dynamic emotional expression remains limited.
The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation
Based on this phenomenon and interpretation, we further propose a method that includes two plug-and-play modules: one to flatten the loss landscapes for low-level features during source-domain training as a novel sharpness-aware minimization method, and the other to directly supplement target-domain information to the model during target-domain testing by low-level-based calibration.
Motion Blender Gaussian Splatting for Dynamic Scene Reconstruction
To address this, we propose Motion Blender Gaussian Splatting (MBGS), a novel framework that uses motion graphs as an explicit and sparse motion representation.
Alchemist: Towards the Design of Efficient Online Continual Learning System
Continual learning has become a promising solution to refine large language models incrementally by leveraging user feedback.
On Space-Filling Input Design for Nonlinear Dynamic Model Learning: A Gaussian Process Approach
While optimal input design for linear systems has been well-established, no systematic approach exists for nonlinear systems where robustness to extrapolation/interpolation errors is prioritized over minimizing estimated parameter variance.
Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Style
Great novels create immersive worlds with rich character arcs, well-structured plots, and nuanced writing styles.
Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey
Large Language Models (LLMs) have demonstrated remarkable success in various tasks such as natural language understanding, text summarization, and machine translation.
Rate-Aware Learned Speech Compression
However, this architecture exhibits insufficient RD performance due to two main drawbacks: (1) the inadequate performance of the quantizer, challenging training processes, and issues such as codebook collapse; (2) the limited representational capacity of the encoder and decoder, making it difficult to meet feature representation requirements across various bitrates.
More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives
Recognizing the lack of multi-task datasets with diverse many-shot distributions, we develop the Many-Shot ICL Benchmark (ICL-50)-a large-scale benchmark of 50 tasks that cover shot numbers from 1 to 350 within sequences of up to 8, 000 tokens-for fine-tuning purposes.
Event-Equalized Dense Video Captioning
Models trained on these datasets will pay less attention to out-of-distribution events.
Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinement
To further minimize test-time computation overhead, we introduce preference-driven optimization with Reinforced Self-Training (ReST), which uses exploration trajectories from ThinkCoder to guide LLM's evolution.
DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving
Large Language Models (LLMs) are increasingly employed in complex workflows, where different LLMs and fine-tuned variants collaboratively address complex tasks.
The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents
With the growing spread of misinformation online, understanding how true news evolves into fake news has become crucial for early detection and prevention.
Autoregressive Action Sequence Learning for Robotic Manipulation
Based on CCT, we propose the Autoregressive Policy (ARP) architecture, which solves manipulation tasks by generating hybrid action sequences.
Ranked #3 on
Robot Manipulation
on RLBench
Dr. GPT in Campus Counseling: Understanding Higher Education Students' Opinions on LLM-assisted Mental Health Services
In response to the increasing mental health challenges faced by college students, we sought to understand their perspectives on how AI applications, particularly Large Language Models (LLMs), can be leveraged to enhance their mental well-being.
Object Modeling from Underwater Forward-Scan Sonar Imagery with Sea-Surface Multipath
We propose an optimization technique for 3-D underwater object modeling from 2-D forward-scan sonar images at known poses.
DAP: Diffusion-based Affordance Prediction for Multi-modality Storage
We present a novel Diffusion-based Affordance Prediction (DAP) pipeline for the multi-modal object storage problem.
Unleash the Power of Ellipsis: Accuracy-enhanced Sparse Vector Technique with Exponential Noise
To provide a rigorous DP guarantee for SVT, prior works in the literature adopt a conservative privacy analysis by assuming the direct disclosure of noisy query results as in typical private query releases.
Semantic-aware Representation Learning for Homography Estimation
In our work, we seek another way to use the semantic information, that is semantic-aware feature representation learning framework. Based on this, we propose SRMatcher, a new detector-free feature matching method, which encourages the network to learn integrated semantic feature representation. Specifically, to capture precise and rich semantics, we leverage the capabilities of recently popularized vision foundation models (VFMs) trained on extensive datasets.
Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration
Modular Pluralism is uniquely compatible with black-box LLMs and offers the modular control of adding new community LMs for previously underrepresented communities.
Scaling Manipulation Learning with Visual Kinematic Chain Prediction
Learning general-purpose models from diverse datasets has achieved great success in machine learning.
DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning
Third, the model is updated with the gradient reconstructed from recycled common knowledge and noisy incremental information.
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
To speed up the prefill of the long LLM inputs, one can pre-compute the KV cache of a text and re-use the KV cache when the context is reused as the prefix of another LLM input.
Physics-Guided State-Space Model Augmentation Using Weighted Regularized Neural Networks
A new weighted regularization term is added to the cost function to penalize the difference between the state and output function of the baseline physics-based and final identified model.
TS3IM: Unveiling Structural Similarity in Time Series through Image Similarity Assessment Insights
This paper introduces the Structured Similarity Index Measure for Time Series (TS3IM), a novel approach inspired by the success of the Structural Similarity Index Measure (SSIM) in image analysis, tailored to address these limitations by assessing structural similarity in time series.
Event-based Video Frame Interpolation with Edge Guided Motion Refinement
Moreover, given that event data can provide accurate visual references at scene edges between consecutive frames, we introduce a learned visibility map derived from event data to adaptively mitigate the occlusion problem in the warping refinement process.
From Skepticism to Acceptance: Simulating the Attitude Dynamics Toward Fake News
Our simulation results uncover patterns in fake news propagation related to topic relevance, and individual traits, aligning with real-world observations.
MMoE: Robust Spoiler Detection with Multi-modal Information and Domain-aware Mixture-of-Experts
For instance, the metadata and the corresponding user's information of a review could be helpful.
Eloquent: A More Robust Transmission Scheme for LLM Token Streaming
To render each generated token in real-time for users, the Large Language Model (LLM) server generates tokens one by one and streams each token (or group of a few tokens) through the network to the user right after generation, which we refer to as LLM token streaming.
Video Frame Interpolation via Direct Synthesis with the Event-based Reference
Video Frame Interpolation (VFI) has witnessed a surge in popularity due to its abundant downstream applications.
P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models
In this work, we take a first step towards designing summarization systems that are faithful to the author's intent, not only the semantic content of the article.
Attitude Takeover Control for Noncooperative Space Targets Based on Gaussian Processes with Online Model Learning
One major challenge for autonomous attitude takeover control for on-orbit servicing of spacecraft is that an accurate dynamic motion model of the combined vehicles is highly nonlinear, complex and often costly to identify online, which makes traditional model-based control impractical for this task.
CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving
Compared to the recent systems that reuse the KV cache, CacheGen reduces the KV cache size by 3. 5-4. 3x and the total delay in fetching and processing contexts by 3. 2-3. 7x with negligible impact on the LLM response quality.
Automatic and Efficient Customization of Neural Networks for ML Applications
ML APIs have greatly relieved application developers of the burden to design and train their own neural network models -- classifying objects in an image can now be as simple as one line of Python code to call an API.
OneAdapt: Fast Configuration Adaptation for Video Analytics Applications via Backpropagation
While the high demand for network bandwidth and GPU resources could be substantially reduced by optimally adapting the configuration knobs, such as video resolution and frame rate, current adaptation techniques fail to meet three requirements simultaneously: adapt configurations (i) with minimum extra GPU or bandwidth overhead; (ii) to reach near-optimal decisions based on how the data affects the final DNN's accuracy, and (iii) do so for a range of configuration knobs.
Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models
The novel setting of geometric knowledge reasoning necessitates new LM abilities beyond existing atomic/linear multi-hop QA, such as backtracking, verifying facts and constraints, reasoning with uncertainty, and more.
Detect Everything with Few Examples
We evaluate DE-ViT on few-shot, and one-shot object detection benchmarks with Pascal VOC, COCO, and LVIS.
Ranked #2 on
Few-Shot Object Detection
on MS-COCO (10-shot)
Binary Classification
Cross-Domain Few-Shot Object Detection
+4
GRACE: Loss-Resilient Real-Time Video through Neural Codecs
In real-time video communication, retransmitting lost packets over high-latency networks is not viable due to strict latency requirements.
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models
We focus on hate speech and misinformation detection, aiming to empirically quantify the effects of political (social, economic) biases in pretraining data on the fairness of high-stakes social-oriented tasks.
Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Model
In this work, a general framework (APES) is built up to strengthen model privacy under personalized local privacy by leveraging the privacy amplification effect of the shuffle model.
Agent-based Simulation for Online Mental Health Matching
Online mental health communities (OMHCs) are an effective and accessible channel to give and receive social support for individuals with mental and emotional issues.
Learning For Predictive Control: A Dual Gaussian Process Approach
Gaussian process (GP) based estimation of system models is an effective tool to learn unknown dynamics directly from input/output data.
Discrete Distribution Estimation under User-level Local Differential Privacy
Perhaps surprisingly, we show that in suitable parameter regimes, having $m$ samples per user is equivalent to having $m$ times more users, each with only one sample.
Learning Continuous Control Policies for Information-Theoretic Active Perception
This paper proposes a method for learning continuous control policies for active landmark localization and exploration using an information-theoretic cost.
TwiBot-22: Towards Graph-Based Twitter Bot Detection
Twitter bot detection has become an increasingly important task to combat misinformation, facilitate social media moderation, and preserve the integrity of the online discourse.
Algorithms for bounding contribution for histogram estimation under user-level privacy
In this scenario, the amount of noise injected into the histogram to obtain differential privacy is proportional to the maximum user contribution, which can be amplified by few outliers.
Human Behavior Recognition Method Based on CEEMD-ES Radar Selection
First, this method decomposes and reconstructs the radar signal according to the difference in the reflected echo frequency between the limbs and the trunk of the human body.
Empathetic Response Generation with State Management
The emotion-aware dialogue management contains two parts: (1) Emotion state tracking maintains the current emotion state of the user and (2) Empathetic dialogue policy selection predicts a target emotion and a user's intent based on the results of the emotion state tracking.
Learning Based Model Predictive Control for Quadcopters with Dual Gaussian Process
In this paper, we present a novel Dual Gaussian Process (DGP) based model predictive control strategy that improves the performance of a quadcopter during trajectory tracking.
Distributed Estimation with Multiple Samples per User: Sharp Rates and Phase Transition
We obtain tight minimax rates for the problem of distributed estimation of discrete distributions under communication constraints, where $n$ users observing $m $ samples each can broadcast only $\ell$ bits.
Performance, Successes and Limitations of Deep Learning Semantic Segmentation of Multiple Defects in Transmission Electron Micrographs
In this work, we perform semantic segmentation of multiple defect types in electron microscopy images of irradiated FeCrAl alloys using a deep learning Mask Regional Convolutional Neural Network (Mask R-CNN) model.
Multi defect detection and analysis of electron microscopy images with deep learning
Electron microscopy is widely used to explore defects in crystal structures, but human detecting of defects is often time-consuming, error-prone, and unreliable, and is not scalable to large numbers of images or real-time analysis.
OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets
Finally, we demonstrate that our framework may also be integrated with physics engines, to create virtual robotics environments with unique ground truth such as friction coefficients and correspondence to real scenes.
Textual Analysis of Communications in COVID-19 Infected Community on Social Media
During the COVID-19 pandemic, people started to discuss about pandemic-related topics on social media.
AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning
With the rapid adoption of machine learning (ML), a number of domains now use the approach of fine tuning models which were pre-trained on a large corpus of data.
Accelerating Deep Learning Inference via Learned Caches
We present the design of GATI, an end-to-end prediction serving system that incorporates learned caches for low-latency DNN inference.
Estimating Sparse Discrete Distributions Under Local Privacy and Communication Constraints
We consider the problem of estimating sparse discrete distributions under local differential privacy (LDP) and communication constraints.
Auto-calibration Method Using Stop Signs for Urban Autonomous Driving Applications
Calibration of sensors is fundamental to robust performance for intelligent vehicles.
Learning discrete distributions: user vs item-level privacy
If each user has $m$ samples, we show that straightforward applications of Laplace or Gaussian mechanisms require the number of users to be $\mathcal{O}(k/(m\alpha^2) + k/\epsilon\alpha)$ to achieve an $\ell_1$ distance of $\alpha$ between the true and estimated distributions, with the privacy-induced penalty $k/\epsilon\alpha$ independent of the number of samples per user $m$.
OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets
Finally, we demonstrate that our framework may also be integrated with physics engines, to create virtual robotics environments with unique ground truth such as friction coefficients and correspondence to real scenes.
Tidal surface states as fingerprints of non-Hermitian nodal knot metals
Non-Hermitian nodal knot metals (NKMs) contains intricate complex-valued energy bands gives rise to knotted exceptional loops and new topological surface states.
Mesoscale and Nanoscale Physics Materials Science Other Condensed Matter Mathematical Physics Mathematical Physics Quantum Physics
Entanglement-guided architectures of machine learning by quantum tensor network
In this work, we implement simple numerical experiments, related to pattern/images classification, in which we represent the classifiers by many-qubit quantum states written in the matrix product states (MPS).
