Search Results for author:
Found 524 papers, 222 papers with code
HIT: Nested Named Entity Recognition via Head-Tail Pair and Token Interaction
Specifically, we design (1) Head-Tail Detector based on the multi-head self-attention mechanism and bi-affine classifier to detect boundary tokens, and (2) Token Interaction Tagger based on traditional sequence labeling approaches to characterize the internal token connection within the boundary.
NEURAL MALWARE CONTROL WITH DEEP REINFORCEMENT LEARNING
Antimalware products are a key component in detecting malware attacks, and their engines typically execute unknown programs in a sandbox prior to running them on the native operating system.
CNNSAT: Fast, Accurate Boolean Satisfiability using Convolutional Neural Networks
Boolean satisfiability (SAT) is one of the most well-known NP-complete problems and has been extensively studied.
Pseudo-Masked Language Models for Unified Language Model Pre-Training
We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM).
基于规则的双重否定识别——以“不v1不v2”为例(Double Negative Recognition Based on Rules——Taking “不v1不v2” as an Example)
“不v1不v2”是汉语中典型的双重否定结构形式之一, 它包括“不+助动词+不+v2”(不得不去)、“不+是+不v2”(不是不好)、述宾结构“不v1... 不v2”(不认为他不去)等多种双重否定结构, 情况复杂。本文以“不v1不v2”为例, 结合“元语否定”、“动词叙实性”、“否定焦点”等概念, 对“不v1不v2”进行了全面的考察, 制定了“不v1不v2”双重否定结构的识别策略。根据识别策略, 设计了双重否定自动识别程序, 并在此过程中补充了助动词表、非叙实动词表等词库。最终, 对28033句语料进行了识别, 识别正确率为97. 87%, 召回率约为93. 10%。
双重否定结构自动识别研究(The Research on Automatic Recognition of the Double Negation Structure)
“双重否定结构是一种“通过两次否定表示肯定意义”的特殊结构, 其存在会对自然语言处理中的语义判断与情感分类产生重要影响。本文以“eg eg P== extgreater P”为标准, 对现代汉语中所有的“否定词+否定词”结构进行了遍历研究, 将双重否定结构按照格式分为了3大类, 25小类, 常用双重否定结构或构式132个。结合动词的叙实性、否定焦点、语义否定与语用否定等相关理论, 本文归纳了双重否定结构的三大成立条件, 并据此设计实现了基于规则的双重否定结构自动识别程序。程序实验的精确率为98. 85%, 召回率为98. 90%, F1值为98. 85%。同时, 程序还从96281句语料中获得了8640句精确率约为99%的含有双重否定结构的句子, 为后续基于统计的深度学习模型提供了语料支持的可能。”
A New Concept of Knowledge based Question Answering (KBQA) System for Multi-hop Reasoning
Knowledge based question answering (KBQA) is a complex task for natural language understanding.
Hysteresis-Aware Neural Network Modeling and Whole-Body Reinforcement Learning Control of Soft Robots
In this study, we present a soft robotic system designed for surgical applications and propose a hysteresis-aware whole-body neural network model that accurately captures and predicts the soft robot's whole-body motion, including its hysteretic behavior.
Meta-Learning and Knowledge Discovery based Physics-Informed Neural Network for Remaining Useful Life Prediction
Predicting the remaining useful life (RUL) of rotating machinery is critical for industrial safety and maintenance, but existing methods struggle with scarce target-domain data and unclear degradation dynamics.
Chain-of-Thought Prompting for Out-of-Distribution Samples: A Latent-Variable Study
Chain-of-Thought (CoT) prompting has emerged as a powerful technique to improve in-context learning (ICL) in large language models (LLMs) by breaking complex reasoning into intermediate steps.
Sleep-time Compute: Beyond Inference Scaling at Test-time
Scaling test-time compute has emerged as a key ingredient for enabling large language models (LLMs) to solve difficult problems, but comes with high latency and inference cost.
NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images.
VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate
In this paper, we exploit the inherent temporal non-uniformity of real-world videos and observe that videos exhibit dynamic information density, with high-motion segments demanding greater detail preservation than static scenes.
DeepSelective: Feature Gating and Representation Matching for Interpretable Clinical Prediction
The rapid accumulation of Electronic Health Records (EHRs) has transformed healthcare by providing valuable data that enhance clinical predictions and diagnoses.
QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
In typical multimodal tasks, such as Visual Question Answering (VQA), adversarial attacks targeting a specific image and question can lead large vision-language models (LVLMs) to provide incorrect answers.
SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users
Social simulation is transforming traditional social science research by modeling human behavior through interactions between virtual individuals and their environments.
How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehension
Large language models are increasingly used in scientific domains, especially for molecular understanding and analysis.
Towards Distribution Matching between Collaborative and Language Spaces for Generative Recommendation
This work addresses this issue by proposing a model-agnostic generative recommendation framework called DMRec, which introduces a probabilistic meta-network to bridge the outputs of LMs with user interactions, thereby enabling an equivalent probabilistic modeling process.
VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation
Speech large language models (LLMs) have emerged as a prominent research focus in speech processing.
Benchmark of Segmentation Techniques for Pelvic Fracture in CT and X-ray: Summary of the PENGWIN 2024 Challenge
The segmentation of pelvic fracture fragments in CT and X-ray images is crucial for trauma diagnosis, surgical planning, and intraoperative guidance.
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image
To address these challenges, we propose a novel completion-based method, named DEPTHOR, featuring advances in both the training strategy and model architecture.
On Data Synthesis and Post-training for Visual Abstract Reasoning
This paper is a pioneering work attempting to address abstract visual reasoning (AVR) problems for large vision-language models (VLMs).
RARE: Retrieval-Augmented Reasoning Modeling
Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning capabilities under constrained parameter budgets.
LaViC: Adapting Large Vision-Language Models to Visually-Aware Conversational Recommendation
To address this challenge, we propose LaViC (Large Vision-Language Conversational Recommendation Framework), a novel approach that integrates compact image representations into dialogue-based recommendation systems.
DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers
Text-to-image generation models, especially Multimodal Diffusion Transformers (MMDiT), have shown remarkable progress in generating high-quality images.
Advancements in Natural Language Processing: Exploring Transformer-Based Architectures for Text Understanding
Natural Language Processing (NLP) has witnessed a transformative leap with the advent of transformer-based architectures, which have significantly enhanced the ability of machines to understand and generate human-like text.
AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models
Assessing the safety of autonomous driving policy is of great importance, and reinforcement learning (RL) has emerged as a powerful method for discovering critical vulnerabilities in driving policies.
FROG: Fair Removal on Graphs
As compliance with privacy regulations becomes increasingly critical, the growing demand for data privacy has highlighted the significance of machine unlearning in many real world applications, such as social network and recommender systems, many of which can be represented as graph-structured data.
Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds
Thus, the representation stability and capability of class distributions are enhanced, alleviating the potential class-wise confusion problem.
BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priors
We first empirically and theoretically explore the role of foregrounds and backgrounds in open set recognition and disclose that: 1) backgrounds that correlate with foregrounds would mislead the model and cause failures when encounters 'partially' known images; 2) Backgrounds unrelated to foregrounds can serve as auxiliary known outliers and provide regularization via global average pooling.
Probabilistic Prompt Distribution Learning for Animal Pose Estimation
To this end, we propose a novel probabilistic prompting approach to fully explore textual descriptions, which could alleviate the diversity issues caused by long-tail property and increase the adaptability of prompts on unseen category instance.
Empowering GraphRAG with Knowledge Filtering and Integration
GraphRAG-Integration employs a logits-based selection strategy to balance external knowledge from GraphRAG with the LLM's intrinsic reasoning, reducing over-reliance on retrievals.
MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification with Zoom-Free Remote Sensing Imagery
To address this limitation, we introduce the Million-scale finE-grained geospatial scEne classification dataseT (MEET), which contains over 1. 03 million zoom-free remote sensing scene samples, manually annotated into 80 fine-grained categories.
RankPO: Preference Optimization for Job-Talent Matching
By fine-tuning with RankPO, we achieve a balanced model that retains relatively good performance in the original tasks while significantly improving the alignment with AI preferences.
Partial differential equation system for binarization of degraded document images
In this system, the first equation is designed to estimate the background component, incorporating both diffusion and fidelity terms.
Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation
In tasks like summarization and open-book question answering (QA), Large Language Models (LLMs) often encounter "contextual hallucination", where they produce irrelevant or incorrect responses despite having access to accurate source information.
High-Precision Transformer-Based Visual Servoing for Humanoid Robots in Aligning Tiny Objects
High-precision tiny object alignment remains a common and critical challenge for humanoid robots in real-world.
DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models
The reliability of large language models remains a critical challenge, particularly due to their susceptibility to hallucinations and factual inaccuracies during text generation.
SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
However, due to the manufacturing constraints of compact devices and the inherent physical principles of imaging, dToF depth maps are sparse and noisy.
Hyperspectral Image Restoration and Super-resolution with Physics-Aware Deep Learning for Biomedical Applications
To overcome this limitation, we present a deep learning-based approach that restores and enhances pixel resolution post-acquisition without any a priori knowledge.
Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases
In the Planning stage, MoR generates textual planning graphs delineating the logic for answering queries.
AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms
The AgentSociety Challenge is the first competition in the Web Conference that aims to explore the potential of Large Language Model (LLM) agents in modeling user behavior and enhancing recommender systems on web platforms.
Strategic priorities for transformative progress in advancing biology with proteomics and artificial intelligence
Artificial intelligence (AI) is transforming scientific research, including proteomics.
AVD2: Accident Video Diffusion for Accident Video Description
Traffic accidents present complex challenges for autonomous driving, often featuring unpredictable scenarios that hinder accurate system interpretation and responses. Nonetheless, prevailing methodologies fall short in elucidating the causes of accidents and proposing preventive measures due to the paucity of training data specific to accident scenarios. In this work, we introduce AVD2 (Accident Video Diffusion for Accident Video Description), a novel framework that enhances accident scene understanding by generating accident videos that aligned with detailed natural language descriptions and reasoning, resulting in the contributed EMM-AU (Enhanced Multi-Modal Accident Video Understanding) dataset.
Megrez-Omni Technical Report
In this work, we present the Megrez models, comprising a language model (Megrez-3B-Instruct) and a multimodal model (Megrez-3B-Omni).
Policy-to-Language: Train LLMs to Explain Decisions with Flow-Matching Generated Rewards
As humans increasingly share environments with diverse agents powered by RL, LLMs, and beyond, the ability to explain their policies in natural language will be vital for reliable coexistence.
RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
For structured data, such as knowledge graphs, GraphRAG has been widely used to retrieve relevant information.
DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation
In this paper, we propose the Dynamic Latent Frame Rate VAE (DLFR-VAE), a training-free paradigm that can make use of adaptive temporal compression in latent space.
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
By explicitly disentangling the optimization of visual understanding from task-specific alignment, MDGD preserves pre-trained visual knowledge while enabling efficient task adaptation.
From Selection to Generation: A Survey of LLM-based Active Learning
Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training.
KPIs 2024 Challenge: Advancing Glomerular Segmentation from Patch- to Slide-Level
Chronic kidney disease (CKD) is a major global health issue, affecting over 10% of the population and causing significant mortality.
Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization
We propose Latent Space Policy Optimization (LSPO), an iterative framework that addresses these challenges by first mapping free-form text to a discrete latent space, where methods like CFR and RL can learn strategic policy more effectively.
Intent Representation Learning with Large Language Model for Recommendation
To tackle these challenges, we propose a model-agnostic framework, Intent Representation Learning with Large Language Model (IRLLRec), which leverages large language models (LLMs) to construct multimodal intents and enhance recommendations.
VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play
To bridge this gap, we present VolleyBots, a new MARL testbed where multiple drones cooperate and compete in the sport of volleyball under physical dynamics.
M+: Extending MemoryLLM with Scalable Long-Term Memory
Equipping large language models (LLMs) with latent-space memory has attracted increasing attention as they can extend the context window of existing language models.
Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network
First, ARSQ decomposes the continuous action space into discrete spaces in a coarse-to-fine hierarchy, enhancing sample efficiency for fine-grained continuous control tasks.
Reflections on "Can AI Understand Our Universe?"
This article briefly discusses the philosophical and technical aspects of AI.
360Brew: A Decoder-only Foundation Model for Personalized Ranking and Recommendation
In this report, we present our research to address these challenges by utilizing a large foundation model with a textual interface for ranking and recommendation tasks.
WanJuanSiLu: A High-Quality Open-Source Webtext Dataset for Low-Resource Languages
This paper introduces the open-source dataset WanJuanSiLu, designed to provide high-quality training corpora for low-resource languages, thereby advancing the research and development of multilingual models.
MedS$^3$: Towards Medical Small Language Models with Self-Evolved Slow Thinking
In this work, we present a deployable, small-scale medical language model, \mone, designed for long-chain reasoning in clinical tasks using a self-evolution paradigm.
PySpatial: A High-Speed Whole Slide Image Pathomics Toolkit
These results highlight PySpatial's potential to handle large-scale WSI analysis with enhanced efficiency and accuracy, paving the way for broader applications in digital pathology.
Holistic Semantic Representation for Navigational Trajectory Generation
Trajectory generation has garnered significant attention from researchers in the field of spatio-temporal analysis, as it can generate substantial synthesized human mobility trajectories that enhance user privacy and alleviate data scarcity.
Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications
Large language models (LLMs) hold promise for addressing healthcare challenges but often generate hallucinations due to limited integration of medical knowledge.
Personalized Graph-Based Retrieval for Large Language Models
As large language models (LLMs) evolve, their ability to deliver personalized and context-aware responses offers transformative potential for improving user experiences.
Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap
Cold-start problem is one of the long-standing challenges in recommender systems, focusing on accurately modeling new or interaction-limited users or items to provide better recommendations.
Retrieval-Augmented Generation with Graphs (GraphRAG)
However, unlike conventional RAG, where the retriever, generator, and external data sources can be uniformly designed in the neural-embedding space, the uniqueness of graph-structured data, such as diverse-formatted and domain-specific relational knowledge, poses unique and significant challenges when designing GraphRAG for different domains.
FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models
Leveraging the unique properties of similarity over importance, we introduce FrameFusion, a novel approach that combines similarity-based merging with importance-based pruning for better token reduction in LVLMs.
MBQ: Modality-Balanced Quantization for Large Vision-Language Models
Therefore, treating tokens from different modalities equally, as in existing PTQ methods, may over-emphasize the insensitive modalities, leading to significant accuracy loss.
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
As the first work to demonstrate the possibility of one-step generation for image AR models, DD challenges the prevailing notion that AR models are inherently slow, and opens up new opportunities for efficient AR generation.
Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
Contrastive learning is a prevalent technique in self-supervised vision representation learning, typically generating positive pairs by applying two data augmentations to the same image.
GUI Agents: A Survey
Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction.
E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling
Our approach not only enhances computational efficiency but also aligns naturally with image generation principles by operating in continuous token space and following a hierarchical generation process from coarse to fine details.
What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Study
The policy derived by SimpleFlight consistently excels across both smooth polynominal trajectories and challenging infeasible zigzag trajectories on small thrust-to-weight quadrotors.
Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal
Multimodal large language models (MLLMs) excel at multimodal perception and understanding, yet their tendency to generate hallucinated or inaccurate responses undermines their trustworthiness.
A4-Unet: Deformable Multi-Scale Attention Network for Brain Tumor Segmentation
Brain tumor segmentation models have aided diagnosis in recent years.
GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
To avoid hallucination of a single MLLM agent, we decompose this stage to four sequentially-executed MLLM-based agents: verification agent, suggestion agent, correction agent, and output structuring agent.
ASIGN: An Anatomy-aware Spatial Imputation Graphic Network for 3D Spatial Transcriptomics
Expanding ST to three-dimensional (3D) volumes is challenging due to the prohibitive costs; a 2D ST acquisition already costs over 50 times more than whole slide imaging (WSI), and a full 3D volume with 10 sections can be an order of magnitude more expensive.
Personalized Multimodal Large Language Models: A Survey
We propose an intuitive taxonomy for categorizing the techniques used to personalize MLLMs to individual users, and discuss the techniques accordingly.
Jailbreak Large Vision-Language Models Through Multi-Modal Linkage
With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly.
DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
Large vision-language models (LVLMs) have demonstrated exceptional performance on complex multimodal tasks.
LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization
Visual Autoregressive (VAR) has emerged as a promising approach in image generation, offering competitive potential and performance comparable to diffusion-based models.
ΩSFormer: Dual-Modal Ω-like Super-Resolution Transformer Network for Cross-scale and High-accuracy Terraced Field Vectorization Extraction
Terraced field is a significant engineering practice for soil and water conservation (SWC).
Glo-In-One-v2: Holistic Identification of Glomerular Cells, Tissues, and Lesions in Human and Mouse Histopathology
In this study, we leverage the Glo-In-One toolkit to version 2 with fine-grained segmentation capabilities, curating 14 distinct labels for tissue regions, cells, and lesions across a dataset of 23, 529 annotated glomeruli across human and mouse histopathology data.
Continual SFT Matches Multimodal RLHF with Negative Supervision
Our nSFT disentangles this negative supervision in RLHF paradigm, and continually aligns VLMs with a simple SFT loss.
Neural Internal Model Control: Learning a Robust Control Policy via Predictive Error Feedback
In this paper, we propose a novel framework, Neural Internal Model Control, which integrates model-based control with RL-based control to enhance robustness.
Towards Accurate and Efficient Sub-8-Bit Integer Training
Our integer training framework includes two components: ShiftQuant to realize accurate gradient estimation, and L1 normalization to smoothen the loss landscape.
WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery Benchmarking
While deep learning has revolutionized computer-aided drug discovery, the AI community has predominantly focused on model innovation and placed less emphasis on establishing best benchmarking practices.
Selecting Between BERT and GPT for Text Classification in Political Science Research
Political scientists often grapple with data scarcity in text classification.
DynaSaur: Large Language Agents Beyond Predefined Actions
Existing LLM agent systems typically select actions from a fixed and predefined set at every step.
GRS-QA -- Graph Reasoning-Structured Question Answering Dataset
Large Language Models (LLMs) have excelled in multi-hop question-answering (M-QA) due to their advanced reasoning abilities.
How Good Are We? Evaluating Cell AI Foundation Models in Kidney Pathology with Human-in-the-Loop Enrichment
This study establishes a benchmark for the development and deployment of cell vision foundation models tailored for real-world data applications.
Personalization of Large Language Models: A Survey
Personalization of Large Language Models (LLMs) has recently become increasingly important with a wide range of applications.
Efficient and Effective Retrieval of Dense-Sparse Hybrid Vectors using Graph-based Approximate Nearest Neighbor Search
To address these issues, we propose a graph-based ANNS algorithm for dense-sparse hybrid vectors.
A Survey of Small Language Models
We propose a novel taxonomy for categorizing the methods used to optimize SLMs, including model compression, pruning, and quantization techniques.
Guide for Defense (G4D): Dynamic Guidance for Robust and Balanced Defense in Large Language Models
With the extensive deployment of Large Language Models (LLMs), ensuring their safety has become increasingly critical.
ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agents
Large Language Models (LLMs) have shown promising potential in the medical domain, assisting with tasks like clinical note generation and patient communication.
PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting
In this paper, we propose a new method called PLGS that enables 3DGS to generate consistent panoptic segmentation masks from noisy 2D segmentation masks while maintaining superior efficiency compared to NeRF-based methods.
Error estimates between SGD with momentum and underdamped Langevin diffusion
Stochastic gradient descent with momentum is a popular variant of stochastic gradient descent, which has recently been reported to have a close relationship with the underdamped Langevin diffusion.
Large Language Models are In-context Preference Learners
Preference-based reinforcement learning is an effective way to handle tasks where rewards are hard to specify but can be exceedingly inefficient as preference learning is often tabula rasa.
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
Finally, our method can identify an optimal SubNet through few-step gradient optimization and a simple post-processing procedure.
Large Language Model-based Augmentation for Imbalanced Node Classification on Text-Attributed Graphs
Node classification on graphs often suffers from class imbalance, leading to biased predictions and significant risks in real-world applications.
Disentangling Likes and Dislikes in Personalized Generative Explainable Recommendation
Specifically, we construct the datasets by explicitly extracting users' positive and negative opinions from their post-purchase reviews using an LLM, and propose to evaluate systems based on whether the generated explanations 1) align well with the users' sentiments, and 2) accurately identify both positive and negative opinions of users on the target items.
Towards Trustworthy Knowledge Graph Reasoning: An Uncertainty Aware Perspective
We design an uncertainty-aware multi-step reasoning framework that leverages conformal prediction to provide a theoretical guarantee on the prediction set.
Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across multimodal tasks such as visual perception and reasoning, leading to good performance on various multimodal evaluation benchmarks.
Reconstruction of Particle Flow Energy Distribution Using Deep Learning Algorithms
In high-energy particle physics, extracting information from complex detector signals is crucial for energy reconstruction.
Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
We compare the performance of the same optimization methods across different hardware platforms, the performance across different hardware platforms, and the performance of different methods on the same hardware platform.
Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
In this paper, we propose a training-free probabilistic parallel decoding algorithm, Speculative Jacobi Decoding (SJD), to accelerate auto-regressive text-to-image generation.
Self-Updatable Large Language Models with Parameter Integration
Despite significant advancements in large language models (LLMs), the rapid and frequent integration of small-scale experiences, such as interactions with surrounding objects, remains a substantial challenge.
Towards the Mitigation of Confirmation Bias in Semi-supervised Learning: a Debiased Training Perspective
TaMatch employs a scaling ratio derived from both a prior target distribution and the model's learning status to estimate and correct bias at each training step.
Multi-Designated Detector Watermarking for Language Models
In this paper, we initiate the study of \emph{multi-designated detector watermarking (MDDW)} for large language models (LLMs).
Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learning
Multi-UAV pursuit-evasion, where pursuers aim to capture evaders, poses a key challenge for UAV swarm intelligence.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
Anisotropic Diffusion Probabilistic Model for Imbalanced Image Classification
We utilize the data distribution to control the diffusion speed of different class samples during the forward process, effectively improving the classification accuracy of the denoiser in the reverse process.
Towards LifeSpan Cognitive Systems
In this paper we focus on the domain of Large Language Models (LLMs), where we identify two major challenges: (1) Abstraction and Experience Merging, and (2) Long-term Retention with Accurate Recall.
Reward-Robust RLHF in LLMs
As Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence, Reinforcement Learning from Human Feedback (RLHF) is increasingly seen as a key pathway toward achieving Artificial General Intelligence (AGI).
CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios
Therefore, we introduce CSKV, a training-efficient Channel Shrinking technique for KV cache compression: (1) We first analyze the singular value distribution of the KV cache, revealing significant redundancy and compression potential along the channel dimension.
PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions
We propose an unconventional method named PIP, which utilizes the attention patterns of one randomly selected irrelevant probe question (e. g., "Is there a clock?")
Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation
The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs).
A Fashion Item Recommendation Model in Hyperbolic Space
In this work, we propose a fashion item recommendation model that incorporates hyperbolic geometry into user and item representations.
A Comprehensive Review of 3D Object Detection in Autonomous Driving: Technological Advances and Future Directions
By providing a holistic view of the current state and future developments in 3D object perception, we aim to offer a more comprehensive understanding of perception tasks for autonomous driving.
Revisiting the Phenomenon of Syntactic Complexity Convergence on German Dialogue Data
We revisit the phenomenon of syntactic complexity convergence in conversational interaction, originally found for English dialogue, which has theoretical implication for dialogical concepts such as mutual understanding.
Cross-Species Data Integration for Enhanced Layer Segmentation in Kidney Pathology
Cross-species homologous data, such as mouse kidney data, which exhibits high structural and feature similarity to human kidneys, has the potential to enhance model performance on human datasets.
Med-PMC: Medical Personalized Multi-modal Consultation with a Proactive Ask-First-Observe-Next Paradigm
The application of the Multi-modal Large Language Models (MLLMs) in medical clinical scenarios remains underexplored.
Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives
This paper introduces the Re-TASK framework, a novel theoretical model that revisits LLM tasks from the perspectives of capability, skill, and knowledge, drawing on the principles of Bloom's Taxonomy and Knowledge Space Theory.
Assessment of Cell Nuclei AI Foundation Models in Kidney Pathology
Among the evaluated models, CellViT demonstrated superior performance in segmenting nuclei in kidney pathology.
A Survey on Self-play Methods in Reinforcement Learning
Self-play, characterized by agents' interactions with copies or past versions of themselves, has recently gained prominence in reinforcement learning (RL).
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Decoding Linguistic Representations of Human Brain
Language, as an information medium created by advanced organisms, has always been a concern of neuroscience regarding how it is represented in the brain.
CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models
Instruction tuning in multimodal large language models (MLLMs) aims to smoothly integrate a backbone LLM with a pre-trained feature encoder for downstream tasks.
GLAM: Glomeruli Segmentation for Human Pathological Lesions using Adapted Mouse Model
To answer this question, we introduced GLAM, a deep learning study for fine-grained segmentation of human kidney lesions using a mouse model, addressing mouse-to-human transfer learning, by evaluating different learning strategies for segmenting human pathological lesions using zero-shot transfer learning and hybrid learning by leveraging mouse samples.
Intent-guided Heterogeneous Graph Contrastive Learning for Recommendation
Contrastive Learning (CL)-based recommender systems have gained prominence in the context of Heterogeneous Graph (HG) due to their capacity to enhance the consistency of representations across different views.
Reconstruct the Pruned Model without Any Retraining
Structured pruning is a promising hardware-friendly compression technique for large language models (LLMs), which is expected to be retraining-free to avoid the enormous retraining cost.
Facial Affect Recognition based on Multi Architecture Encoder and Feature Fusion for the ABAW7 Challenge
In this paper, we present our approach to addressing the challenges of the 7th ABAW competition.
LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction
Existing methods enhance open-vocabulary object detection by leveraging the robust open-vocabulary recognition capabilities of Vision-Language Models (VLMs), such as CLIP. However, two main challenges emerge:(1) A deficiency in concept representation, where the category names in CLIP's text space lack textual and visual knowledge.
Ranked #1 on
Open Vocabulary Object Detection
on LVIS v1.0
OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer
Open-vocabulary object detection focusing on detecting novel categories guided by natural language.
ISWSST: Index-space-wave State Superposition Transformers for Multispectral Remotely Sensed Imagery Semantic Segmentation
Currently the semantic segmentation task of multispectral remotely sensed imagery (MSRSI) faces the following problems: 1) Usually, only single domain feature (i. e., space domain or frequency domain) is considered; 2) downsampling operation in encoder generally leads to the accuracy loss of edge extraction; 3) multichannel features of MSRSI are not fully considered; and 4) prior knowledge of remote sensing is not fully utilized.
LaMoD: Latent Motion Diffusion Model For Myocardial Strain Generation
More specifically, our method first employs an encoder from a pre-trained registration network that learns latent motion features (also considered as deformation-based shape features) from image sequences.
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
For example, we demonstrate that pruning up to 75% of experts in Mixtral $8\times7$B-Instruct results in a substantial reduction in parameters with minimal performance loss.
HATs: Hierarchical Adaptive Taxonomy Segmentation for Panoramic Pathology Image Analysis
Panoramic image segmentation in computational pathology presents a remarkable challenge due to the morphologically complex and variably scaled anatomy.
Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihood
Human and model-generated texts can be distinguished by examining the magnitude of likelihood in language.
CAPM: Fast and Robust Verification on Maxpool-based CNN via Dual Network
This study uses CAPM (Convex Adversarial Polytope for Maxpool-based CNN) to improve the verified bound for general purpose maxpool-based convolutional neural networks (CNNs) under bounded norm adversarial perturbations.
ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Models
Analog circuit design requires substantial human expertise and involvement, which is a significant roadblock to design productivity.
MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation
Based on this two-stage paradigm, we proposed a Medical LLM through decoupling Clinical Alignment and Knowledge Aggregation (MedCare), which is designed to achieve state-of-the-art (SOTA) performance on over 20 medical tasks, as well as SOTA results on specific medical alignment tasks.
Intensity Confusion Matters: An Intensity-Distance Guided Loss for Bronchus Segmentation
We regard a voxel as a hard sample if it is in: (1) the background and has an intensity value close to the bronchus region; (2) the bronchus region and is of higher intensity than most voxels inside the bronchus; (3) the background region and at a short distance from the bronchus.
MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression
Existing methods typically employ a uniform sparse attention mask, applying the same sparse pattern across different attention heads and input lengths.
Privacy Preserved Blood Glucose Level Cross-Prediction: An Asynchronous Decentralized Federated Learning Approach
Newly diagnosed Type 1 Diabetes (T1D) patients often struggle to obtain effective Blood Glucose (BG) prediction models due to the lack of sufficient BG data from Continuous Glucose Monitoring (CGM), presenting a significant "cold start" problem in patient care.
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
We reveal some findings: (1) Teaching materials that make it easier for students to learn have clearer and more accurate logic when using in-context learning as the student's "learning" method; (2) Weak-to-strong generalization: LbT might help improve strong models by teaching weak models; (3) Diversity in students might help: teaching multiple students could be better than teaching one student or the teacher itself.
Towards an End-to-End Framework for Invasive Brain Signal Decoding with Large Language Models
In this paper, we introduce a groundbreaking end-to-end (E2E) framework for decoding invasive brain signals, marking a significant advancement in the field of speech neuroprosthesis.
Edge Classification on Graphs: New Directions in Topological Imbalance
Our empirical studies confirm that TE effectively measures local class distribution variance, and indicate that prioritizing edges with high TE values can help address the issue of topological imbalance.
DiTFastAttn: Attention Compression for Diffusion Transformer Models
Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to the quadratic complexity of self-attention operators.
Large Generative Graph Models
To remedy this crucial gap, we propose a new class of graph generative model called Large Graph Generative Model (LGGM) that is trained on a large corpus of graphs (over 5000 graphs) from 13 different domains.
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Diffusion transformers (DiTs) have exhibited remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions.
CityLight: A Universal Model for Coordinated Traffic Signal Control in City-scale Heterogeneous Intersections
Our method, CityLight, features a universal representation module that not only aligns the state representations of intersections by reindexing their phases based on their semantics and designing heterogeneity-preserving observations, but also encodes the narrowed relative traffic relation types to project the neighborhood intersections onto a uniform relative traffic impact space.
Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation
We note that there is a disparity between the generation priors of these two diffusion models, leading to their different appearance outputs.
Cross-Training with Multi-View Knowledge Fusion for Heterogenous Federated Learning
Federated learning benefits from cross-training strategies, which enables models to train on data from distinct sources to improve the generalization capability.
TAIA: Large Language Models are Out-of-Distribution Data Learners
However, in certain specialized domains, such as healthcare or harmless content generation, it is nearly impossible to obtain a large volume of high-quality data that matches the downstream distribution.
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Finally, we develop an integer-programming-based method to conduct bit-width allocation.
Large Scale Knowledge Washing
To this end, we propose LAW (Large Scale Washing) to update the MLP layers in decoder-only large language models to perform knowledge washing, as inspired by model editing methods and based on the hypothesis that knowledge and reasoning are disentanglable.
Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character
With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), ensuring their safety has become increasingly critical.
HETHUB: A Distributed Training System with Heterogeneous Cluster for Large-Scale Models
We train the Llama-140B model on a heterogeneous cluster with 768 GPU-accelerators(128 AMD and 640 GPU-accelerator A).
DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis
In addition, to further improve training efficiency for high-resolution image generation with DiM, we investigate "weak-to-strong" training strategy that pretrains DiM on low-resolution images ($256\times 256$) and then finetune it on high-resolution images ($512 \times 512$).
SubGDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning
We propose a novel diffusion model termed SubGDiff for involving the molecular subgraph information in diffusion.
Learning Discriminative Spatio-temporal Representations for Semi-supervised Action Recognition
Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data.
CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective
Note that constraints on intra-sample similarities and inter-sample dissimilarities can be efficiently and effectively reformulated into a contrastive learning framework with newly designed positive and negative pairs.
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.
Ranked #5 on
MMR total
on MRR-Benchmark
(using extra training data)
A Survey on Efficient Inference for Large Language Models
This paper presents a comprehensive survey of the existing literature on efficient LLM inference.
A competitive game optimization algorithm for Unmanned Aerial Vehicle path planning
To solve the Unmanned Aerial Vehicle (UAV) path planning problem, a meta-heuristic optimization algorithm called competitive game optimizer (CGO) is proposed.
Can AI Understand Our Universe? Test of Fine-Tuning GPT by Astrophysical Data
With the ever-growing volume of multidisciplinary data and the advancement of AI technology, we look forward to the emergence of a more fundamental and comprehensive understanding of our universe.
MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts
Large language models like ChatGPT have shown substantial progress in natural language understanding and generation, proving valuable across various disciplines, including the medical field.
On the Uniqueness of Solution for the Bellman Equation of LTL Objectives
In a widely-adopted surrogate reward approach, two discount factors are used to ensure that the expected return approximates the satisfaction probability of the LTL objective.
Generative-Enhanced Heterogeneous Graph Contrastive Learning
3) A hierarchical contrastive learning strategy for capturing local and global information.
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
For example, LCSC achieves better performance using 1 number of function evaluation (NFE) than the base model with 2 NFE on consistency distillation, and decreases the NFE of DM from 15 to 9 while maintaining the generation quality on CIFAR-10.
ParCo: Part-Coordinating Text-to-Motion Synthesis
However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts.
Ranked #16 on
Motion Synthesis
on HumanML3D
Leveraging Large Language Models for Fuzzy String Matching in Political Science
Fuzzy string matching remains a key issue when political scientists combine data from different sources.
FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
In recent years, there has been significant progress in the development of text-to-image generative models.
Simple Graph Condensation
The burdensome training costs on large-scale graphs have aroused significant interest in graph condensation, which involves tuning Graph Neural Networks (GNNs) on a small condensed graph for use on the large-scale original graph.
M$^3$AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset
Although multiple academic video datasets have been constructed and released, few of them support both multimodal content recognition and understanding tasks, which is partially due to the lack of high-quality human annotations.
Tokensome: Towards a Genetic Vision-Language GPT for Explainable and Cognitive Karyotyping
Automatic karyotype analysis is often defined as a visual perception task focused solely on chromosomal object-level modeling.
AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting
However, with the integration of additional modalities, MLLMs are exposed to new vulnerabilities, rendering them prone to structured-based jailbreak attacks, where semantic content (e. g., "harmful text") has been injected into the images to mislead MLLMs.
Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator
Large Language Models (LLMs) have demonstrated remarkable proficiency in human interactions, yet their application within the medical field remains insufficiently explored.
Position: Towards Implicit Prompt For Text-To-Image Models
We call for increased attention to the potential and risks of implicit prompts in the T2I community and further investigation into the capabilities and impacts of implicit prompts, advocating for a balanced approach that harnesses their benefits while mitigating their risks.
COLA: Cross-city Mobility Transformer for Human Trajectory Simulation
To address these challenges, we have tailored a Cross-city mObiLity trAnsformer (COLA) with a dedicated model-agnostic transfer framework by effectively transferring cross-city knowledge for human trajectory simulation.
A Tutorial on the Pretrain-Finetune Paradigm for Natural Language Processing
In this tutorial, we introduce the pretrain-finetune paradigm.
Post-decoder Biasing for End-to-End Speech Recognition of Multi-turn Medical Interview
End-to-end (E2E) approach is gradually replacing hybrid models for automatic speech recognition (ASR) tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
LLMs in Political Science: Heralding a New Era of Visual Analysis
We find that Gemini is highly accurate in performing object detection, which is arguably the most common and fundamental task in image analysis for political scientists.
Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding
The vast applications of deep generative models are anchored in three core capabilities -- generating new instances, reconstructing inputs, and learning compact representations -- across various data types, such as discrete text/protein sequences and continuous images.
PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation
Understanding the anatomy of renal pathology is crucial for advancing disease diagnostics, treatment evaluation, and clinical research.
Leveraging Diverse Modeling Contexts with Collaborating Learning for Neural Machine Translation
Autoregressive (AR) and Non-autoregressive (NAR) models are two types of generative models for Neural Machine Translation (NMT).
Evaluating Quantized Large Language Models
Specifically, PTQ can effectively mitigate memory consumption and reduce computational overhead in LLMs.
Intelligent Director: An Automatic Framework for Dynamic Visual Composition using ChatGPT
We propose an Intelligent Director framework, utilizing LENS to generate descriptions for images and video frames and combining ChatGPT to generate coherent captions while recommending appropriate music names.
Representation Learning for Frequent Subgraph Mining
SPMiner combines graph neural networks, order embedding space, and an efficient search strategy to identify network subgraph patterns that appear most frequently in the target graph.
LVCHAT: Facilitating Long Video Comprehension
To address this issue, we propose Long Video Chat (LVChat), where Frame-Scalable Encoding (FSE) is introduced to dynamically adjust the number of embeddings in alignment with the duration of the video to ensure long videos are not overly compressed into a few embeddings.
Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability
In this paper, we extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
Leveraging Opposite Gender Interaction Ratio as a Path towards Fairness in Online Dating Recommendations Based on User Sexual Orientation
While recommender systems have been designed to improve the user experience in dating platforms by providing personalized recommendations, increasing concerns about fairness have encouraged the development of fairness-aware recommender systems from various perspectives (e. g., gender and race).
M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation
Video-grounded dialogue generation (VDG) requires the system to generate a fluent and accurate answer based on multimodal knowledge.
DictLLM: Harnessing Key-Value Data Structures with Large Language Models for Enhanced Medical Diagnostics
Structured data offers a sophisticated mechanism for the organization of information.
Knowledge Graph-based Session Recommendation with Adaptive Propagation
Then, we adaptively aggregate items' neighbor information considering user intention within the learned session.
Rec-GPT4V: Multimodal Recommendation with Large Vision-Language Models
We utilize user history as in-context user preferences to address the first challenge.
MEMORYLLM: Towards Self-Updatable Large Language Models
We aim to build models containing a considerable portion of self-updatable parameters, enabling the model to integrate new knowledge effectively and efficiently.
