Search Results for author:
Found 71 papers, 36 papers with code
Figure it Out: Analyzing-based Jailbreak Attack on Large Language Models
In this paper, we further explore the boundary of jailbreak attacks on LLMs and propose Analyzing-based Jailbreak (ABJ).
Developing a Reliable, General-Purpose Hallucination Detection and Mitigation Service: Insights and Lessons Learned
Hallucination, a phenomenon where large language models (LLMs) produce output that is factually incorrect or unrelated to the input, is a major challenge for LLM applications that require accuracy and dependability.
Multi-threshold Deep Metric Learning for Facial Expression Recognition
Each embedding slice corresponds to a sample threshold and is learned by enforcing the corresponding triplet loss, yielding a set of distinct expression features, one for each embedding slice.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement
Large language model agents have exhibited exceptional performance across a range of complex interactive tasks.
DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models
In this paper, we introduce DP-MemArc, a novel training framework aimed at reducing the memory costs of large language models while emphasizing the protection of user data privacy.
Tool-Planner: Dynamic Solution Tree Planning for Large Language Model with Tool Clustering
Tool-Planner groups tools based on the API functions with the same function into a toolkit and allows LLMs to implement planning across the various toolkits.
xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
This paper introduces xRAG, an innovative context compression method tailored for retrieval-augmented generation.
Leveraging 2D Information for Long-term Time Series Forecasting with Vanilla Transformers
A vertical slicing of this grid combines the variates at each time step into a \textit{time token}, while a horizontal slicing embeds the individual series across all time steps into a \textit{variate token}.
Ranked #30 on
Time Series Forecasting
on ETTh1 (336) Multivariate
Representation Alignment Contrastive Regularization for Multi-Object Tracking
Achieving high-performance in multi-object tracking algorithms heavily relies on modeling spatio-temporal relationships during the data association stage.
LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models
This paper presents a comprehensive survey of the current status and opportunities for Large Language Models (LLMs) in strategic reasoning, a sophisticated form of reasoning that necessitates understanding and predicting adversary actions in multi-agent settings while adjusting strategies accordingly.
Structurally Prune Anything: Any Architecture, Any Framework, Any Time
However, the diverse patterns for coupling parameters, such as residual connections and group convolutions, the diverse deep learning frameworks, and the various time stages at which pruning can be performed make existing pruning methods less adaptable to different architectures, frameworks, and pruning criteria.
Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models
We introduce Generalized Instruction Tuning (called GLAN), a general and scalable method for instruction tuning of Large Language Models (LLMs).
Reliable long timescale decision-directed channel estimation for OFDM system
Decision-directed channel estimation (DDCE) is one kind of blind channel estimation method that tracks the channel blindly by an iterative algorithm without relying on the pilots, which can increase the utilization of wireless resource.
K-Level Reasoning with Large Language Models
While Large Language Models (LLMs) have demonstrated their proficiency in complex reasoning tasks, their performance in dynamic, interactive, and competitive scenarios - such as business strategy and stock market analysis - remains underexplored.
Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification
To this end we propose a Continual Compatible Representation (C2R) method which facilitates the query feature calculated by the continuously updated model to effectively retrieve the gallery feature calculated by the old model in a compatible manner.
Two Directions for Clinical Data Generation with Large Language Models: Data-to-Label and Label-to-Data
We train a system to detect AD-related signs and symptoms from EHRs, using three datasets: (1) a gold dataset annotated by human experts on longitudinal EHRs of AD patients; (2) a silver dataset created by the data-to-label method; and (3) a bronze dataset created by the label-to-data method.
Gene-MOE: A sparsely gated prognosis and classification framework exploiting pan-cancer genomic information
According to the survival analysis results on 14 cancer types, Gene-MOE outperformed state-of-the-art models on 12 cancer types.
Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding
In this manner, our framework is able to learn the unified representations of uni-modal or multi-modal skeleton input, which is flexible to different kinds of modality input for robust action understanding in practical cases.
ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents
This paper introduces Alympics (Olympics for Agents), a systematic simulation framework utilizing Large Language Model (LLM) agents for game theory research.
NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes
We introduce NoteChat, a novel cooperative multi-agent framework leveraging Large Language Models (LLMs) to generate patient-physician dialogues.
Robust Visual Imitation Learning with Inverse Dynamics Representations
Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems.
SCALE: Synergized Collaboration of Asymmetric Language Translation Engines
In this paper, we introduce SCALE, a collaborative framework that connects compact Specialized Translation Models (STMs) and general-purpose Large Language Models (LLMs) as one unified translation engine.
Dual-view Curricular Optimal Transport for Cross-lingual Cross-modal Retrieval
Therefore, we propose Dual-view Curricular Optimal Transport (DCOT) to learn with noisy correspondence in CCR.
Early Prediction of Alzheimers Disease Leveraging Symptom Occurrences from Longitudinal Electronic Health Records of US Military Veterans
We used a panel of AD-related keywords and their occurrences over time in a patient's longitudinal EHRs as predictors for AD prediction with four machine learning models.
In-context Autoencoder for Context Compression in a Large Language Model
These promising results imply a novel perspective on the connection between working memory in cognitive science and representation learning in LLMs, revealing ICAE's significant implications in addressing the long context problem and suggesting further research in LLM context management.
ODD: A Benchmark Dataset for the Natural Language Processing based Opioid Related Aberrant Behavior Detection
Experimental results show that the prompt-tuning models outperformed the fine-tuning models in most categories and the gains were especially higher among uncommon categories (Suggested Aberrant Behavior, Confirmed Aberrant Behaviors, Diagnosed Opioid Dependence, and Medication Change).
Interactive Editing for Text Summarization
Summarizing lengthy documents is a common and essential task in our daily lives.
Smart Word Suggestions for Writing Assistance
The training dataset comprises over 3. 7 million sentences and 12. 7 million suggestions generated through rules.
An Evaluation on Large Language Model Outputs: Discourse and Memorization
We present an empirical evaluation of various outputs generated by nine of the most widely-available large language models (LLMs).
Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters
The goal of Few-Shot Continual Learning (FSCL) is to incrementally learn novel tasks with limited labeled samples and preserve previous capabilities simultaneously, while current FSCL methods are all for the class-incremental purpose.
Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video Retrieval
During the knowledge distillation, an inheritance student branch is devised to absorb the knowledge from the teacher model.
Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite
We introduce \textsc{PoliteRewrite} -- a dataset for polite language rewrite which is a novel sentence rewrite task.
Momentum Calibration for Text Generation
The input and output of most text generation tasks can be transformed to two sequences of tokens and they can be modeled using sequence-to-sequence learning modeling tools such as Transformers.
Ranked #2 on
Text Summarization
on SAMSum
Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning
This paper targets unsupervised skeleton-based action representation learning and proposes a new Hierarchical Contrast (HiCo) framework.
Extensible Prompts for Language Models on Zero-shot Language Style Customization
We propose eXtensible Prompt (X-Prompt) for prompting a large language model (LLM) beyond natural language (NL).
Latent Prompt Tuning for Text Summarization
In this paper, we propose Lotus (shorthand for Latent Prompt Tuning for Summarization), which is a single model that can be applied in both controlled and uncontrolled (without control signals) modes.
Hypothesis Test Procedures for Detecting Leakage Signals in Water Pipeline Channels
We design statistical hypothesis tests for performing leak detection in water pipeline channels.
Partially Relevant Video Retrieval
To fill the gap, we propose in this paper a novel T2VR subtask termed Partially Relevant Video Retrieval (PRVR).
Ranked #1 on
Partially Relevant Video Retrieval
on TVR
Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning
In this paper, we propose a noise-robust cross-lingual cross-modal retrieval method for low-resource languages.
Modality-Balanced Embedding for Video Retrieval
This modality imbalanceresults from a) modality gap: the relevance between a query and a video text is much easier to learn as the query is also a piece of text, with the same modality as the video text; b) data bias: most training samples can be solved solely by text matching.
Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval
In this work, we concentrate on video representation learning, an essential component for text-to-video retrieval.
Exploiting full Resolution Feature Context for Liver Tumor and Vessel Segmentation via Integrate Framework: Application to Liver Tumor and Vessel 3D Reconstruction under embedded microprocessor
Segmentation and labeling of liver tumors and blood vessels in CT images can provide convenience for doctors in liver tumor diagnosis and surgical intervention.
Consistency Regularization for Deep Face Anti-Spoofing
Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems.
Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework
Model smoothing is of central importance for obtaining a reliable teacher model in the student-teacher framework, where the teacher generates surrogate supervision signals to train the student.
Learning to Persuade
Then we update the sender model to obtain an approximately optimal scheme using the receiver model.
Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability Detection
Then, we propose a novel temporal message propagation network to extract the graph feature from the normalized graph, and combine the graph feature with designed expert patterns to yield a final detection system.
Multi-scale super-resolution generation of low-resolution scanned pathological images
We design a strategy to scan slides with low resolution (5X) and a super-resolution method is proposed to restore the image details when in diagnosis.
Rethinking Deep Contrastive Learning with Embedding Memory
Pair-wise loss functions have been extensively studied and shown to continuously improve the performance of deep metric learning (DML).
Deep Dual Consecutive Network for Human Pose Estimation
Multi-frame human pose estimation in complicated situations is challenging.
Ranked #1 on
Multi-Person Pose Estimation
on PoseTrack2017
(using extra training data)
Progressive Localization Networks for Language-based Moment Localization
The language-based setting of this task allows for an open set of target activities, resulting in a large variation of the temporal lengths of video moments.
Automatic Detection of Cardiac Chambers Using an Attention-based YOLOv4 Framework from Four-chamber View of Fetal Echocardiography
The first step to automatically analyze fetal FC views is locating the fetal four crucial chambers of heart in a US image.
Dual Encoding for Video Retrieval by Text
In this paper we achieve this by proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own.
Ranked #3 on
Ad-hoc video search
on TRECVID-AVS16 (IACC.3)
(using extra training data)
Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval
To facilitate video retrieval with complex queries, we propose a Tree-augmented Cross-modal Encoding method by jointly learning the linguistic structure of queries and the temporal representation of videos.
Anisotropy links cell shapes to tissue flow during convergent extension
Within developing embryos, tissues flow and reorganize dramatically on timescales as short as minutes.
Feature Re-Learning with Data Augmentation for Video Relevance Prediction
Predicting the relevance between two given videos with respect to their visual content is a key component for content-based video recommendation and retrieval.
Channel Interaction Networks for Fine-Grained Image Categorization
Fine-grained image categorization is challenging due to the subtle inter-class differences. We posit that exploiting the rich relationships between channels can help capture such differences since different channels correspond to different semantics.
Ranked #24 on
Fine-Grained Image Classification
on FGVC Aircraft
Cross-Batch Memory for Embedding Learning
This suggests that the features of instances computed at preceding iterations can be used to considerably approximate their features extracted by the current model.
Ranked #2 on
Image Retrieval
on In-Shop
MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translation
Manipulating training data leads to robust neural models for MT.
HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs
The hubness problem widely exists in high-dimensional embedding space and is a fundamental source of error for cross-modal matching tasks.
Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning
A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning.
Ranked #4 on
Image Retrieval
on In-Shop
Dual Encoding for Zero-Example Video Retrieval
This paper attacks the challenging problem of zero-example video retrieval.
Reading Comprehension using Entity-based Memory Network
This paper introduces a novel neural network model for question answering, the \emph{entity-based memory network}.
Exploring Text Links for Coherent Multi-Document Summarization
Existing methods focus on the extraction of key information, but often neglect coherence.
Modeling Word Relatedness in Latent Dirichlet Allocation
Standard LDA model suffers the problem that the topic assignment of each word is independent and word correlation hence is neglected.
What a Nasty day: Exploring Mood-Weather Relationship from Twitter
While it has long been believed in psychology that weather somehow influences human's mood, the debates have been going on for decades about how they are correlated.
Time-dependent Hierarchical Dirichlet Model for Timeline Generation
Existing approaches neglect such hierarchical topic structure involved in the news corpus in timeline generation.
