Search Results for author:
Found 364 papers, 163 papers with code
TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering
High-quality novel view synthesis for large-scale scenes presents a challenging dilemma in 3D computer vision.
Denoising Programming Knowledge Tracing with a Code Graph-based Tuning Adaptor
However, current PKT studies primarily focus on the implicit relationship between code content and knowledge assessment, often overlooking two types of noise signals in long-term programming activities: unwanted signals from unrelated submissions and weak signals from minor modifications.
Are LLMs Reliable Translators of Logical Reasoning Across Lexically Diversified Contexts?
Building directly on the deficiencies identified through our benchmark, we propose a new method, MenTaL, to address this limitation.
CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective
Although large language models (LLMs) show promise in solving complex mathematical tasks, existing evaluation paradigms rely solely on a coarse measure of overall answer accuracy, which are insufficient for assessing their authentic capabilities.
Large Language Models Can Achieve Explainable and Training-Free One-shot HRRP ATR
This letter introduces a pioneering, training-free and explainable framework for High-Resolution Range Profile (HRRP) automatic target recognition (ATR) utilizing large-scale pre-trained Large Language Models (LLMs).
TestAgent: An Adaptive and Intelligent Expert for Human Assessment
It customizes assessments by selecting the fewest test questions .
MGS3: A Multi-Granularity Self-Supervised Code Search Framework
Subsequently, we introduce a novel Multi-Granularity Self-Supervised contrastive learning code Search framework (MGS$^{3}$}).
Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting
Time series forecasting (TSF) is a fundamental and widely studied task, spanning methods from classical statistical approaches to modern deep learning and multimodal language modeling.
Improving Time Series Forecasting via Instance-aware Post-hoc Revision
Time series forecasting plays a vital role in various real-world applications and has attracted significant attention in recent decades.
WDMIR: Wavelet-Driven Multimodal Intent Recognition
Multimodal intent recognition (MIR) seeks to accurately interpret user intentions by integrating verbal and non-verbal information across video, audio and text modalities.
Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering
Recently, large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, yet they remain prone to hallucinations when reasoning with insufficient internal knowledge.
Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models
Despite the remarkable reasoning performance, eliciting the long chain-of-thought (CoT) ability in large language models (LLMs) typically requires costly reinforcement learning or supervised fine-tuning on high-quality distilled data.
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables.
Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering
Recent advances in large language models (LLMs) have led to impressive progress in natural language generation, yet their tendency to produce hallucinated or unsubstantiated content remains a critical concern.
Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression
Despite substantial advancements in aligning large language models (LLMs) with human values, current safety mechanisms remain susceptible to jailbreak attacks.
WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?
However, prevailing benchmarks like DocVQA and ChartQA predominantly comprise \textit{scanned or digital} documents, inadequately reflecting the intricate challenges posed by diverse real-world scenarios, such as variable illumination and physical distortions.
Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering
Existing visual token pruning methods target prompt alignment and visual preservation with static strategies, overlooking the varying relative importance of these objectives across tasks, which leads to inconsistent performance.
SAEN-BGS: Energy-Efficient Spiking AutoEncoder Network for Background Subtraction
Background subtraction (BGS) is utilized to detect moving objects in a video and is commonly employed at the onset of object tracking and human recognition processes.
Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving
As a seemingly self-explanatory task, problem-solving has been a significant component of science and engineering.
am-ELO: A Stable Framework for Arena-based LLM Evaluation
Arena-based evaluation is a fundamental yet significant evaluation paradigm for modern AI models, especially large language models (LLMs).
GraphPrompter: Multi-stage Adaptive Prompt Optimization for Graph In-Context Learning
Graph In-Context Learning, with the ability to adapt pre-trained graph models to novel and diverse downstream graphs without updating any parameters, has gained much attention in the community.
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
Remarkably, our experiments demonstrate that DTD achieves an 82. 8% reduction in video tokens while maintaining 98% performance on StreamingBench, revealing that over 80% of visual content in streaming videos is naturally redundant without requiring language guidance.
PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
Current benchmarks for evaluating the reasoning capabilities of Large Language Models (LLMs) face significant limitations: task oversimplification, data contamination, and flawed evaluation items.
Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey
Recent advancements in Retrieval-Augmented Generation (RAG) have revolutionized natural language processing by integrating Large Language Models (LLMs) with external information retrieval, enabling accurate, up-to-date, and verifiable text generation across diverse applications.
Metamon-GS: Enhancing Representability with Variance-Guided Densification and Light Encoding
The introduction of 3D Gaussian Splatting (3DGS) has advanced novel view synthesis by utilizing Gaussians to represent scenes.
PSG-MAE: Robust Multitask Sleep Event Monitoring using Multichannel PSG Reconstruction and Inter-channel Contrastive Learning
When the encoder pre-trained through PSG-MAE is fine-tuned with downstream feature decomposition networks, it achieves an accuracy of 83. 7% for sleep staging and 90. 45% for detecting obstructive sleep apnea, which highlights the framework's robustness and broad applicability.
CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Framework
Event cameras have attracted increasing attention in recent years due to their advantages in high dynamic range, high temporal resolution, low power consumption, and low latency.
MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers
Then, we further design self-improvement strategy in target model to reduce the reliance on multiple shortcuts.
The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation
By referencing this external knowledge, RAG effectively reduces the generation of factually incorrect content and addresses hallucination issues within LLMs.
How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective
Recent studies have shown that large language models (LLMs) can assess relevance and support information retrieval (IR) tasks such as document ranking and relevance judgment generation.
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
We introduce Seed1. 5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks.
LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Reranking
Utilizing large language models (LLMs) for document reranking has been a popular and promising research direction in recent years, many studies are dedicated to improving the performance and efficiency of using LLMs for reranking.
Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving
The task of issue resolving is to modify a codebase to generate a patch that addresses a given issue.
HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation
However, human-object interaction (HOI) often cannot be precisely generated by current T2V models due to the lack of large-scale videos with accurate captions for HOI.
Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context
Knowledge Graph Completion (KGC) aims to infer missing information in Knowledge Graphs (KGs) to address their inherent incompleteness.
TEMPLE:Temporal Preference Learning of Video LLMs via Difficulty Scheduling and Pre-SFT Alignment
We further analyze the transferability of DPO data across architectures and the role of difficulty scheduling in optimization.
A Comprehensive Survey on Cross-Domain Recommendation: Taxonomy, Progress, and Prospects
Recommender systems (RS) have become crucial tools for information filtering in various real world scenarios.
Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion Estimation
Specifically, to enhance the robot's environmental perception, we introduce a new obstacle encoding method that evaluates the impact of obstacles on the robot's motion planning.
OpenVidVRD: Open-Vocabulary Video Visual Relation Detection via Prompt-Driven Semantic Space Alignment
The video visual relation detection (VidVRD) task is to identify objects and their relationships in videos, which is challenging due to the dynamic content, high annotation costs, and long-tailed distribution of relations.
A Survey on Knowledge-Oriented Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models.
Large Language Model Guided Progressive Feature Alignment for Multimodal UAV Object Detection
To address this problem, we propose a Large Language Model (LLM) guided Progressive feature Alignment Network called LPANet, which leverages the semantic features extracted from a large language model to guide the progressive semantic and spatial alignment between modalities for multimodal UAV object detection.
MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality
Knowledge editing is a technique for efficiently and accurately updating the knowledge of large language models (LLMs) to alleviate obsolescence and correct errors.
HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation
While Retrieval-Augmented Generation (RAG) has emerged as an effective approach for addressing the knowledge outdating problem in Large Language Models (LLMs), it faces a critical challenge: the prevalence of outdated information in knowledge bases.
PCE-GAN: A Generative Adversarial Network for Point Cloud Attribute Quality Enhancement based on Optimal Transport
Point cloud compression significantly reduces data volume but sacrifices reconstruction quality, highlighting the need for advanced quality enhancement techniques.
Entailment-Preserving First-order Logic Representations in Natural Language Entailment
To this extent, we propose a training method specialized for the task, iterative learning-to-rank, which directly optimizes the model's EPR score through a novel scoring function and a learning-to-rank objective.
Geometry-Aware 3D Salient Object Detection Network
In this paper, we propose a geometry-aware 3D salient object detection network that explicitly clusters points into superpoints to enhance the geometric boundaries of objects, thereby segmenting complete objects with clear boundaries.
SentiFormer: Metadata Enhanced Transformer for Image Sentiment Analysis
As more and more internet users post images online to express their daily emotions, image sentiment analysis has attracted increasing attention.
Chinese Spelling Correction: A Comprehensive Survey of Progress, Challenges, and Opportunities
Chinese Spelling Correction (CSC) is a critical task in natural language processing, aimed at detecting and correcting spelling errors in Chinese text.
Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment
In this paper, we introduce such a novel task, code reasoning, to provide a new perspective for the reasoning abilities of LLMs.
Fast Underwater Scene Reconstruction using Multi-View Stereo and Physical Imaging
To address these limitations, we propose a novel method that integrates Multi-View Stereo (MVS) with a physics-based underwater image formation model.
DASKT: A Dynamic Affect Simulation Method for Knowledge Tracing
Knowledge Tracing (KT) predicts future performance by modeling students' historical interactions, and understanding students' affective states can enhance the effectiveness of KT, thereby improving the quality of education.
Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems
Personalized learning represents a promising educational strategy within intelligent educational systems, aiming to enhance learners' practice efficiency.
VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models
Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored.
OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
Scoring the Optical Character Recognition (OCR) capabilities of Large Multimodal Models (LMMs) has witnessed growing interest recently.
Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner
Pre-trained foundation models have recently significantly progressed in structured table understanding and reasoning.
Navigating Data Corruption in Machine Learning: Balancing Quality, Quantity, and Imputation Strategies
Data corruption, including missing and noisy data, poses significant challenges in real-world machine learning.
TextMatch: Enhancing Image-Text Consistency Through Multimodal Optimization
Text-to-image generative models excel in creating images from text but struggle with ensuring alignment and consistency between outputs and prompts.
GIRAFFE: Design Choices for Extending the Context Length of Visual Language Models
Towards this goal, we make the best design choice through extensive experiment settings from data curation to context window extending and utilizing: (1) we analyze data sources and length distributions to construct ETVLM - a data recipe to balance the performance across scenarios; (2) we examine existing position extending methods, identify their limitations and propose M-RoPE++ as an enhanced approach; we also choose to solely instruction-tune the backbone with mixed-source data; (3) we discuss how to better utilize extended context windows and propose hybrid-resolution training.
Stepwise Reasoning Error Disruption Attack of LLMs
Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain underexplored.
Precision-Enhanced Human-Object Contact Detection via Depth-Aware Perspective Interaction and Object Texture Restoration
Human-object contact (HOT) is designed to accurately identify the areas where humans and objects come into contact.
Toy-GS: Assembling Local Gaussians for Precisely Rendering Large-Scale Free Camera Trajectories
Currently, 3D rendering for large-scale free camera trajectories, namely, arbitrary input camera trajectories, poses significant challenges: 1) The distribution and observation angles of the cameras are irregular, and various types of scenes are included in the free trajectories; 2) Processing the entire point cloud and all images at once for large-scale scenes requires a substantial amount of GPU memory.
Semi-IIN: Semi-supervised Intra-inter modal Interaction Learning Network for Multimodal Sentiment Analysis
Despite multimodal sentiment analysis being a fertile research ground that merits further investigation, current approaches take up high annotation cost and suffer from label ambiguity, non-amicable to high-quality labeled data acquisition.
Conformal Prediction on Quantifying Uncertainty of Dynamic Systems
Our motivation is to introduce conformal prediction into the uncertainty assessment of dynamical systems, providing a method supported by theoretical guarantees.
Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models
Exploratory data analysis (EDA), coupled with SQL, is essential for data analysts involved in data exploration and analysis.
PoTable: Towards Systematic Thinking via Stage-oriented Plan-then-Execute Reasoning on Tables
In recent years, table reasoning has garnered substantial research interest, particularly its integration with Large Language Models (LLMs) which revolutionize natural language applications.
FullStack Bench: Evaluating LLMs as Full Stack Coders
As the capabilities of code large language models (LLMs) continue to expand, their applications across diverse code intelligence domains are rapidly increasing.
VLRewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models
Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored.
TableTime: Reformulating Time Series Classification as Zero-Shot Table Understanding via Large Language Models
Despite their effectiveness, we reveal that these methods conceal three inherent bottlenecks: (1) they struggle to encode temporal and channel-specific information in a lossless manner, both of which are critical components of multivariate time series; (2) it is much difficult to align the learned representation space with the semantic space of the LLMs; (3) they require task-specific retraining, which is both computationally expensive and labor-intensive.
Optimizing Student Ability Assessment: A Hierarchy Constraint-Aware Cognitive Diagnosis Framework for Educational Contexts
To address this, we propose the Hierarchy Constraint-Aware Cognitive Diagnosis Framework (HCD), designed to more accurately represent student ability performance within real educational contexts.
MDHP-Net: Detecting an Emerging Time-exciting Threat in IVN
We systematically analyze the characteristics of the threat: dynamism, time-exciting impact, and low prior knowledge dependency.
3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration
Multi-instance point cloud registration aims to estimate the pose of all instances of a model point cloud in the whole scene.
Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling
Motivated by the success of collaborative modeling in various domains, such as recommender systems, we aim to investigate how collaborative signals among learners contribute to the diagnosis of human cognitive states (i. e., knowledge proficiency) in the context of intelligent education.
LE-PDE++: Mamba for accelerating PDEs Simulations
Partial Differential Equations are foundational in modeling science and natural systems such as fluid dynamics and weather forecasting.
DisenTS: Disentangled Channel Evolving Pattern Modeling for Multivariate Time Series Forecasting
To this end, we propose DisenTS, a tailored framework for modeling disentangled channel evolving patterns in general multivariate time series forecasting.
Leveraging LLMs for Hypothetical Deduction in Logical Inference: A Neuro-Symbolic Approach
Large Language Models (LLMs) have exhibited remarkable potential across a wide array of reasoning tasks, including logical reasoning.
RecFlow: An Industrial Full Flow Recommendation Dataset
Industrial recommendation systems (RS) rely on the multi-stage pipeline to balance effectiveness and efficiency when delivering items from a vast corpus to users.
Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models
3) Chain-of-thought prompting notably reduces shortcut reliance and outperforms other prompting strategies, while few-shot prompts generally underperform compared to zero-shot prompts.
Understanding the Role of LLMs in Multimodal Evaluation Benchmarks
The rapid advancement of Multimodal Large Language Models (MLLMs) has been accompanied by the development of various benchmarks to evaluate their capabilities.
DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking
Despite these advancements, current methods are often tailored for specific docking settings, and limitations such as the neglect of protein side-chain structures, difficulties in handling large binding pockets, and challenges in predicting physically valid structures exist.
The Epochal Sawtooth Effect: Unveiling Training Loss Oscillations in Adam and Other Optimizers
In this paper, we identify and analyze a recurring training loss pattern, which we term the \textit{Epochal Sawtooth Effect (ESE)}, commonly observed during training with adaptive gradient-based optimizers, particularly Adam optimizer.
VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment
As large vision-language models (LVLMs) evolve rapidly, the demand for high-quality and diverse data to align these models becomes increasingly crucial.
Ranked #62 on
Visual Question Answering
on MM-Vet
OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting
Entity Linking (EL) is the process of associating ambiguous textual mentions to specific entities in a knowledge base.
Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds
In addition, this work establishes a database named WPC6. 0, the first and largest PCQA database dedicated to Trisoup-Lifting encoding mode, encompassing 400 distorted point clouds with both 4 geometric multiplied by 5 texture distortion levels.
CursorCore: Assist Programming through Aligning Anything
In this work, we propose a new conversational framework that comprehensively integrates these information sources, collect data to train our models and evaluate their performance.
Learning Recommender Systems with Soft Target: A Decoupled Perspective
Learning recommender systems with multi-class optimization objective is a prevalent setting in recommendation.
Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series Forecasting
Self-supervised learning has become a popular and effective approach for enhancing time series forecasting, enabling models to learn universal representations from unlabeled data.
Temporal Reasoning Transfer from Text to Video
Video Large Language Models (Video LLMs) have shown promising capabilities in video comprehension, yet they struggle with tracking temporal changes and reasoning about temporal relationships.
DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Prediction
Multi-sensor fusion significantly enhances the accuracy and robustness of 3D semantic occupancy prediction, which is crucial for autonomous driving and robotics.
Ranked #1 on
Prediction Of Occupancy Grid Maps
on Occ3D-nuScenes
Generalized Protein Pocket Generation with Prior-Informed Flow Matching
One critical step in this process involves designing protein pockets, the protein interface binding with the ligand.
FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling
Structure-based drug design (SBDD), which aims to generate 3D ligand molecules binding to target proteins, is a fundamental task in drug discovery.
Long or Short or Both? An Exploration on Lookback Time Windows of Behavioral Features in Product Search Ranking
Customer shopping behavioral features are core to product search ranking models in eCommerce.
Towards More Relevant Product Search Ranking Via Large Language Models: An Empirical Study
Training Learning-to-Rank models for e-commerce product search ranking can be challenging due to the lack of a gold standard of ranking relevance.
Pre-trained Language Model and Knowledge Distillation for Lightweight Sequential Recommendation
The algorithm operates in two stages: in the first stage, we fine-tune the pre-trained language model on the recommendation dataset to transfer the pre-trained knowledge to the recommendation task; in the second stage, we distill the trained language model to transfer the learned knowledge to a lightweight model.
ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models
To this end, we propose \textbf{\textit{ChemEval}}, which provides a comprehensive assessment of the capabilities of LLMs across a wide range of chemical domain tasks.
CSS: Overcoming Pose and Scene Challenges in Crowd-Sourced 3D Gaussian Splatting
We introduce Crowd-Sourced Splatting (CSS), a novel 3D Gaussian Splatting (3DGS) pipeline designed to overcome the challenges of pose-free scene reconstruction using crowd-sourced imagery.
Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study
Retrieval-augmented generation (RAG) is increasingly recognized as an effective approach for mitigating the hallucination of large language models (LLMs) through the integration of external knowledge.
Efficient Transfer Learning Framework for Cross-Domain Click-Through Rate Prediction
The challenges include the inefficiencies arising from the management of extensive source data and the problem of 'catastrophic forgetting' that results from the CTR model's daily updating.
Multi-Agent Target Assignment and Path Finding for Intelligent Warehouse: A Cooperative Multi-Agent Deep Reinforcement Learning Perspective
Multi-agent target assignment and path planning (TAPF) are two key problems in intelligent warehouse.
SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning
Extensive experimental results on D4RL datasets demonstrate that SUMO can provide more accurate uncertainty estimation and boost the performance of base algorithms.
DimeRec: A Unified Framework for Enhanced Sequential Recommendation via Generative Diffusion Models
Nevertheless, a straightforward combination of SR and DM leads to sub-optimal performance due to discrepancies in learning objectives (recommendation vs. noise reconstruction) and the respective learning spaces (non-stationary vs. stationary).
RePair: Automated Program Repair with Process-based Feedback
The gap between the trepidation of program reliability and the expense of repairs underscores the indispensability of Automated Program Repair (APR).
A Review of Human-Object Interaction Detection
Human-object interaction (HOI) detection plays a key role in high-level visual understanding, facilitating a deep comprehension of human activities.
Experimental evaluation of offline reinforcement learning for HVAC control in buildings
In summary, this paper presents our well-structured investigations and new findings when applying offline reinforcement learning to building HVAC systems.
An Efficient Continuous Control Perspective for Reinforcement-Learning-based Sequential Recommendation
However, previous studies mainly focus on discrete action and policy spaces, which might have difficulties in handling dramatically growing items efficiently.
Modeling Domain and Feedback Transitions for Cross-Domain Sequential Recommendation
In this paper, we propose $\text{Transition}^2$, a novel method to model transitions across both domains and types of user feedback.
Mamba Retriever: Utilizing Mamba for Effective and Efficient Dense Retrieval
Experimental results show that (1) on the MS MARCO passage ranking dataset and BEIR, the Mamba Retriever achieves comparable or better effectiveness compared to Transformer-based retrieval models, and the effectiveness grows with the size of the Mamba model; (2) on the long-text LoCoV0 dataset, the Mamba Retriever can extend to longer text length than its pre-trained length after fine-tuning on retrieval task, and it has comparable or better effectiveness compared to other long-text retrieval models; (3) the Mamba Retriever has superior inference speed for long-text retrieval.
Towards Few-shot Self-explaining Graph Neural Networks
Subsequently, the predictor mimics the decision-making process, which makes predictions based on the generated explanation.
KnowPC: Knowledge-Driven Programmatic Reinforcement Learning for Zero-shot Coordination
Zero-shot coordination (ZSC) remains a major challenge in the cooperative AI field, which aims to learn an agent to cooperate with an unseen partner in training environments or even novel environments.
Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling
Recent image generation models excel at creating high-quality images from brief captions.
Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization
The rapid increase in multimedia data has spurred advancements in Multimodal Summarization with Multimodal Output (MSMO), which aims to produce a multimodal summary that integrates both text and relevant images.
Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models
Recent advancements in machine learning, particularly in Natural Language Processing (NLP), have led to the development of sophisticated models trained on extensive datasets, yet raising concerns about the potential leakage of sensitive information.
Empowering Few-Shot Relation Extraction with The Integration of Traditional RE Methods and Large Language Models
Specifically, DSARE innovatively injects the prior knowledge of LLMs into traditional RE models, and conversely enhances LLMs' task-specific aptitude for RE through relation extraction augmentation.
Detect, Investigate, Judge and Determine: A Novel LLM-based Framework for Few-shot Fake News Detection
To address these shortcomings, we propose a Dual-perspective Augmented Fake News Detection (DAFND) model, designed to enhance LLMs from both inside and outside perspectives.
Dynamic neural network with memristive CIM and CAM for 2D and 3D vision
In contrast, AI models are static, unable to associate inputs with past experiences, and run on digital computers with physically separated memory and processing.
A Survey of Models for Cognitive Diagnosis: New Developments and Future Directions
Cognitive diagnosis has been developed for decades as an effective measurement tool to evaluate human cognitive status such as ability level and knowledge mastery.
A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding
However, existing methods that integrate spatial layouts with text have limitations, such as producing overly long text sequences or failing to fully leverage the autoregressive traits of LLMs.
Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models
To address these issues, in this paper, we propose PE-Rank, leveraging the single passage embedding as a good context compression for efficient listwise passage reranking.
Jailbreaking as a Reward Misspecification Problem
In this paper, we propose a novel perspective that attributes this vulnerability to reward misspecification during the alignment process.
TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy
However, several significant challenges still persist in LLMs for ranking: (1) LLMs are constrained by limited input length, precluding them from processing a large number of documents simultaneously; (2) The output document sequence is influenced by the input order of documents, resulting in inconsistent ranking outcomes; (3) Achieving a balance between cost and ranking performance is quite challenging.
InstructRL4Pix: Training Diffusion for Image Editing by Reinforcement Learning
Instruction-based image editing has made a great process in using natural human language to manipulate the visual content of images.
Continuous-Time Digital Twin with Analogue Memristive Neural Ordinary Differential Equation Solver
We experimentally validate our approach by developing a digital twin of the HP memristor, which accurately extrapolates its nonlinear dynamics, achieving a 4. 2-fold projected speedup and a 41. 4-fold projected decrease in energy consumption compared to state-of-the-art digital hardware, while maintaining an acceptable error margin.
Genomics-guided Representation Learning for Pathologic Pan-cancer Tumor Microenvironment Subtype Prediction
The characterization of Tumor MicroEnvironment (TME) is challenging due to its complexity and heterogeneity.
QAGCF: Graph Collaborative Filtering for Q&A Recommendation
Traditional recommendation methods treat the question-answer pair as a whole or only consider the answer as a single item, which overlooks the two challenges and cannot effectively model user interests.
EduNLP: Towards a Unified and Modularized Library for Educational Resources
We also provide a configurable pipeline to unify the data usage and model usage in standard ways, where users can customize their own needs.
TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy
In this mechanism, all the involved diverse visual table understanding (VTU) tasks and multi-source visual embeddings are abstracted as concepts.
PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations
Our toolkit further includes a suite of \textbf{response consistency analyses} that compare performance on raw vs. perturbed test sets to precisely assess LLMs' genuine knowledge capacity.
Cognitive Evolutionary Learning to Select Feature Interactions for Recommender Systems
We show that CELL can adaptively evolve into different models for different tasks and data, which enables practitioners to access off-the-shelf models.
TerDiT: Ternary Diffusion Models with Transformers
Recent developments in large-scale pre-trained text-to-image diffusion models have significantly improved the generation of high-fidelity images, particularly with the emergence of diffusion models based on transformer architecture (DiTs).
MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering
Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de facto gold proxy to evaluate AI models in the domain of text-centric scene understanding.
CELA: Cost-Efficient Language Model Alignment for CTR Prediction
This model-agnostic framework can be equipped with plug-and-play textual features, with item-level alignment enhancing the utilization of external information while maintaining training and inference efficiency.
Evaluation of Retrieval-Augmented Generation: A Survey
Retrieval-Augmented Generation (RAG) has recently gained traction in natural language processing.
Aerial-NeRF: Adaptive Spatial Partitioning and Sampling for Large-Scale Aerial Rendering
To that end, we propose Aerial-NeRF with three innovative modifications for jointly adapting NeRF in large-scale aerial rendering: (1) Designing an adaptive spatial partitioning and selection method based on drones' poses to adapt different flight trajectories; (2) Using similarity of poses instead of (expert) network for rendering speedup to determine which region a new viewpoint belongs to; (3) Developing an adaptive sampling approach for rendering performance improvement to cover the entire buildings at different heights.
Tree-based Ensemble Learning for Out-of-distribution Detection
In this paper, we propose TOOD detection, a simple yet effective tree-based out-of-distribution (TOOD) detection mechanism to determine if a set of unseen samples will have similar distribution as of the training samples.
Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language models
We introduce Vibe-Eval: a new open benchmark and framework for evaluating multimodal chat models.
TextSquare: Scaling up Text-Centric Visual Instruction Tuning
Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of leading models like GPT4V and Gemini, partly due to a lack of extensive, high-quality instruction tuning data.
AG-NeRF: Attention-guided Neural Radiance Fields for Multi-height Large-scale Outdoor Scene Rendering
Existing neural radiance fields (NeRF)-based novel view synthesis methods for large-scale outdoor scenes are mainly built on a single altitude.
Efficient and accurate neural field reconstruction using resistive memory
The GE harnesses the intrinsic stochasticity of resistive memory for efficient input encoding, while the PE achieves precise weight mapping through a Hardware-Aware Quantization (HAQ) circuit.
Event Grounded Criminal Court View Generation with Cooperative (Large) Language Models
Then, we incorporate the extracted events into court view generation by merging case facts and events.
Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model
Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64. 8 and 156. 5, respectively.
Survey of Computerized Adaptive Testing: A Machine Learning Perspective
Computerized Adaptive Testing (CAT) provides an efficient and tailored method for assessing the proficiency of examinees, by dynamically adjusting test questions based on their performance.
Unleashing the Potential of Large Language Models for Predictive Tabular Tasks in Data Science
Despite their proficiency in comprehending natural language, LLMs fall short in dealing with structured tabular data.
An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models
Based on these findings, we then propose several simple document pruning methods to reduce the storage overhead and compare the effectiveness of different pruning methods on different late-interaction models.
Advancing Time Series Classification with Multimodal Language Modeling
In this work, we propose InstructTime, a novel attempt to reshape time series classification as a learning-to-generate paradigm.
Cross-Domain Pre-training with Language Models for Transferable Time Series Representations
To address this challenge, we propose CrossTimeNet, a novel cross-domain SSL learning framework to learn transferable knowledge from various domains to largely benefit the target downstream task.
Spatiotemporal Diffusion Model with Paired Sampling for Accelerated Cardiac Cine MRI
Current deep learning reconstruction for accelerated cardiac cine MRI suffers from spatial and temporal blurring.
Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform
Through this gateway, users have the opportunity to submit their questions, testing the models on a personalized and potentially broader range of capabilities.
Clinically Feasible Diffusion Reconstruction for Highly-Accelerated Cardiac Cine MRI
The currently limited quality of accelerated cardiac cine reconstruction may potentially be improved by the emerging diffusion models, but the clinically unacceptable long processing time poses a challenge.
Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery
Since existing methods still suffer from adopting the shortcuts in data to compose rationales and limited large-scale annotated rationales by human, in this paper, we propose a Shortcuts-fused Selective Rationalization (SSR) method, which boosts the rationalization by discovering and exploiting potential shortcuts.
Empowering Sequential Recommendation from Collaborative Signals and Semantic Relatedness
It is also significant to model the \textit{semantic relatedness} reflected in content features, e. g., images and text.
Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration
Human-object interaction (HOI) detection aims to locate human-object pairs and identify their interaction categories in images.
A Dataset for the Validation of Truth Inference Algorithms Suitable for Online Deployment
In this paper, we introduce a substantial crowdsourcing annotation dataset collected from a real-world crowdsourcing platform.
Cooperative Classification and Rationalization for Graph Generalization
To address these challenges, in this paper, we propose a Cooperative Classification and Rationalization (C2R) method, consisting of the classification and the rationalization module.
Unified Uncertainty Estimation for Cognitive Diagnosis Models
Specifically, based on the idea of estimating the posterior distributions of cognitive diagnosis model parameters, we first provide a unified objective function for mini-batch based optimization that can be more efficiently applied to a wide range of models and large datasets.
ImgTrojan: Jailbreaking Vision-Language Models with ONE Image
In this paper, we propose a novel jailbreaking attack against VLMs, aiming to bypass their safety barrier when a user inputs harmful instructions.
FreeA: Human-object Interaction Detection using Free Annotation Labels
Recent human-object interaction (HOI) detection methods depend on extensively annotated image datasets, which require a significant amount of manpower.
PointCore: Efficient Unsupervised Point Cloud Anomaly Detector Using Local-Global Features
Three-dimensional point cloud anomaly detection that aims to detect anomaly data points from a training set serves as the foundation for a variety of applications, including industrial inspection and autonomous driving.
ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis
Designing effective models for learning time series representations is foundational for time series analysis.
Ranked #9 on
Time Series Forecasting
on ETTh1 (336) Multivariate
Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models
To fill this gap, we introduce Multimodal ArXiv, consisting of ArXivCap and ArXivQA, for enhancing LVLMs scientific comprehension.
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language.
Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
Specifically, we propose, for the first time to our best knowledge, post-training approaches for task-agnostic and task-specific expert pruning and skipping of MoE LLMs, tailored to improve deployment efficiency while maintaining model performance across a wide range of tasks.
SISSA: Real-time Monitoring of Hardware Functional Safety and Cybersecurity with In-vehicle SOME/IP Ethernet Traffic
Scalable service-Oriented Middleware over IP (SOME/IP) is an Ethernet communication standard protocol in the Automotive Open System Architecture (AUTOSAR), promoting ECU-to-ECU communication over the IP stack.
ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning
Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged continuously.
ViTree: Single-path Neural Tree for Step-wise Interpretable Fine-grained Visual Categorization
As computer vision continues to advance and finds widespread applications across various domains, the need for interpretability in deep learning models becomes paramount.
FedGT: Federated Node Classification with Scalable Graph Transformer
However, existing methods have the following limitations: (1) The links between local subgraphs are missing in subgraph federated learning.
TED-Net: Dispersal Attention for Perceiving Interaction Region in Indirectly-Contact HOI Detection
Human-Object Interaction (HOI) detection is a fertile research ground that merits further investigation in computer vision, and plays an important role in image high-level semantic information understanding.
Red Teaming Visual Language Models
Additionally, we simply apply red teaming alignment to LLaVA-v1. 5 with Supervised Fine-tuning (SFT) using RTVLM, and this bolsters the models' performance with 10% in RTVLM test set, 13% in MM-Hal, and without noticeable decline in MM-Bench, overpassing other LLaVA-based models with regular alignment data.
Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native
In this paper, we investigate the intersection of large generative AI models and cloud-native computing architectures.
Nucleus subtype classification using inter-modality learning
In this paper, we propose to use inter-modality learning to label previously un-labelable cell types on virtual H&E.
A locally statistical active contour model for SAR image segmentation can be solved by denoising algorithms
In this paper, we propose a novel locally statistical variational active contour model based on I-divergence-TV denoising model, which hybrides geodesic active contour (GAC) model with active contours without edges (ACWE) model, and can be used to segment images corrupted by multiplicative gamma noise.
LMaaS: Exploring Pricing Strategy of Large Model as a Service for Communication
In the first step, we optimize the seller's pricing decision and propose an Iterative Model Pricing (IMP) algorithm that optimizes the prices of large models iteratively by reasoning customers' future rental decisions, which is able to achieve a near-optimal pricing solution.
Improving Depth Completion via Depth Feature Upsampling
In this paper we visualize the internal feature maps to analyze how the network densifies the input sparse depth.
Unlocking the Potential of Large Language Models for Explainable Recommendations
In this study, we propose LLMXRec, a simple yet effective two-stage explainable recommendation framework aimed at further boosting the explanation quality by employing LLMs.
Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives
Consequently, we refine the cognitive states of cold-start students as diagnostic outcomes via virtual data, aligning with the diagnosis-oriented goal.
Active contours driven by local and global intensity fitting energy with application to SAR image segmentation and its fast solvers
In this paper, we propose a novel variational active contour model based on Aubert-Aujol (AA) denoising model, which hybrides geodesic active contour (GAC) model with active contours without edges (ACWE) model and can be used to segment images corrupted by multiplicative gamma noise.
A Survey of Reasoning with Foundation Models
Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation.
Random resistive memory-based deep extreme point learning machine for unified visual processing
Our random resistive memory-based deep extreme point learning machine may pave the way for energy-efficient and training-friendly edge AI across various data modalities and tasks.
AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction
Most existing methods focus on the network architecture design of the CTR model for better accuracy and suffer from the data sparsity problem.
A global optimization SAR image segmentation model can be easily transformed to a general ROF denoising model
The second model is: we use a different splitting approach than one model to transform the global optimization model into a differentiable term and a general ROF model term, which can be solved by the same technique as the first model.
Multi-scale Iterative Refinement towards Robust and Versatile Molecular Docking
This model is then paired with GPU-accelerated sampling algorithms.
SigFormer: Sparse Signal-Guided Transformer for Multi-Modal Human Action Segmentation
Nowadays, the majority of approaches concentrate on the fusion of dense signals (i. e., RGB, optical flow, and depth maps).
DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding
This work presents DocPedia, a novel large multimodal model (LMM) for versatile OCR-free document understanding, capable of parsing images up to 2, 560$\times$2, 560 resolution.
Deep Group Interest Modeling of Full Lifelong User Behaviors for CTR Prediction
The insights from this subset reveal the user's decision-making process related to the candidate item, improving prediction accuracy.
Pruning random resistive memory for optimizing analogue AI
Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning to optimize the topology of a randomly weighted analogue resistive memory neural network.
Sparse Attention-Based Neural Networks for Code Classification
We introduce an approach named the Sparse Attention-based neural network for Code Classification (SACC) in this paper.
AutoSAM: Towards Automatic Sampling of User Behaviors for Sequential Recommender Systems
Sequential recommender systems (SRS) have gained widespread popularity in recommendation due to their ability to effectively capture dynamic user preferences.
SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations
Large language models (LLMs) have been widely applied in various fields due to their excellent capability for memorizing knowledge and chain of thought (CoT).
On the Opportunities of Green Computing: A Survey
To tackle the challenges of computing resources and environmental impact of AI, Green Computing has become a hot research topic.
BianQue: Balancing the Questioning and Suggestion Ability of Health LLMs with Multi-turn Health Conversations Polished by ChatGPT
Large language models (LLMs) have performed well in providing general and extensive health suggestions in single-turn conversations, exemplified by systems such as ChatGPT, ChatGLM, ChatDoctor, DoctorGLM, and etc.
AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking
Specifically, we adopt a multiple pairwise ranking loss which trains the user model to capture the similarity orders between the implicitly augmented view, the explicitly augmented view, and views from other users.
LRRU: Long-short Range Recurrent Updating Networks for Depth Completion
Existing deep learning-based depth completion methods generally employ massive stacked layers to predict the dense depth map from sparse input data.
Full-Atom Protein Pocket Design via Iterative Refinement
In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions.
Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models
The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples.
Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition
Current speaker recognition systems primarily rely on supervised approaches, constrained by the scale of labeled datasets.
Reformulating Sequential Recommendation: Learning Dynamic User Interest with Content-enriched Language Modeling
Recommender systems are indispensable in the realm of online applications, and sequential recommendation has enjoyed considerable prevalence due to its capacity to encapsulate the dynamic shifts in user interests.
FedJudge: Federated Legal Large Language Model
To this end, in this paper, we propose the first Federated Legal Large Language Model (FedJudge) framework, which fine-tunes Legal LLMs efficiently and effectively.
Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation
Existing LLM evaluation methods are mainly supervised signal-based which depends on static datasets and cannot evaluate the ability of LLMs in dynamic real-world scenarios where deep interaction widely exists.
Decomposed Guided Dynamic Filters for Efficient RGB-Guided Depth Completion
The decomposed filters not only maintain the favorable properties of guided dynamic filters as being content-dependent and spatially-variant, but also reduce model parameters and hardware costs, as the learned adaptors are decoupled with the number of feature channels.
