Papers

New on arXiv

Mon 13 Jan 2025

224 papers

FlowDAS: A Stochastic Interpolant-based Framework for Data AssimilationDiffusion models → Flow matching, time series and science
Gaussian Universality for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Dataset Distillation as Pushforward Optimal QuantizationDiffusion models → Diffusion foundations and sampling
CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis TheorySynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
A Survey of Early Exit Deep Neural Networks in NLPEfficient LLM inference and serving → Early exit and edge inference
BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video RepresentationsDiffusion models → Video generation
WebWalker: Benchmarking LLMs in Web TraversalRetrieval-augmented generation → Agentic RAG, agents and memory
Imagine while Reasoning in Space: Multimodal Visualization-of-ThoughtLLM reasoning → Multimodal reasoning +1
Evaluating Agent-based Program Repair at GoogleLLM agents and tool use → Software engineering coding agents
Parallel Key-Value Cache Fusion for Position Invariant RAGRetrieval-augmented generation → Generation and context integration +1
PrecipDiff: Leveraging image diffusion models to enhance satellite-based precipitation observationsDiffusion models → Flow matching, time series and science
Introducing 3D Representation for Medical Image Volume-to-Volume Translation via Score FusionDiffusion models → Medical imaging and segmentation
Zero-Shot Scene Understanding for Automatic Target Recognition Using Large Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
Enhancing Retrieval-Augmented Generation: A Study of Best PracticesRetrieval-augmented generation → RAG pipeline design and evaluation
Bigger Isn't Always Better: Towards a General Prior for Medical Image ReconstructionDiffusion models → Medical imaging and segmentation
Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline DataOffline RL and imitation learning from data → Imitation learning methods
TempoGPT: Enhancing Time Series Reasoning via Quantizing EmbeddingLLM reasoning → Time series reasoning +1
The Lessons of Developing Process Reward Models in Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning +1
Lifelong Learning of Large Language Model based Agents: A RoadmapLLM agents and tool use → Agent memory systems
Skip Mamba Diffusion for Monocular 3D Semantic Scene CompletionDiffusion models → 3D, point cloud and scene generation +1
Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language ModelLLM reasoning → Audio-language model reasoning
Can Vision-Language Models Evaluate Handwritten Math?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Lessons From Red Teaming 100 Generative AI ProductsLLM safety and security → Prompt injection and agent security
MECD+: Unlocking Event-Level Causal Graph Discovery for Video ReasoningLLM reasoning → Multimodal reasoning
A4O: All Trigger for One sampleLLM safety and security → Backdoor and data poisoning attacks
BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific LiteratureMultimodal LLMs / vision-language models → Medical vision-language models
MSV-Mamba: A Multiscale Vision Mamba Network for Echocardiography SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
ListConRanker: A Contrastive Text Reranker with Listwise EncodingRetrieval-augmented generation → Generation and context integration
The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question AnsweringMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
How GPT learns layer by layerWorld models → World models for language agents
Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
D3MES: Diffusion Transformer with multihead equivariant self-attention for 3D molecule generationDiffusion models → Flow matching, time series and science
Enhancing Image Generation Fidelity via Progressive PromptsDiffusion models → Image generation, text-to-image and editing
Research on the Online Update Method for Retrieval-Augmented Generation (RAG) Model with Incremental LearningRetrieval-augmented generation → RAG pipeline design and evaluation
PoAct: Policy and Action Dual-Control Agent for Generalized ApplicationsLLM reasoning → Reasoning for agents, planning and code +1
Erasing Noise in Signal Detection with Diffusion Model: From Theory to ApplicationDiffusion models → Diffusion foundations and sampling
Neural Probabilistic Circuits: Enabling Compositional and Interpretable Predictions through Logical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving MapsDiffusion models → Diffusion foundations and sampling
Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
Rethinking the Mixture of Vision Encoders Paradigm for Enhanced Visual Understanding in Multimodal LLMsLLM reasoning → Multimodal reasoning +1
Enhancing Team Diversity with Generative AI: A Novel Project Management Framework
Subject Representation Learning from EEG using Graph Convolutional Variational Autoencoders
Median of Means Sampling for the Keister Function
Synthetic Data and Health Privacy
A Preliminary Survey of Semantic Descriptive Model for Images
Evaluating Human Perception of Novel View Synthesis: Subjective Quality Assessment of Gaussian Splatting and NeRF in Dynamic Scenes
Performance Optimization of Ratings-Based Reinforcement Learning
Universal Training of Neural Networks to Achieve Bayes Optimal Classification Accuracy
Rethinking AI Cultural Alignment
Boosting Sclera Segmentation through Semi-supervised Learning with Fewer Labels
Scaling Up ESM2 Architectures for Long Protein Sequences Analysis: Long and Quantized Approaches
A Heterogeneous Multimodal Graph Learning Framework for Recognizing User Emotions in Social Networks
RePoseD: Efficient Relative Pose Estimation With Known Depth Information
Advancing Student Writing Through Automated Syntax Feedback
Multi-megabase scale genome interpretation with genetic language models
HyperQuery: Beyond Binary Link Prediction
Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
Autoencoded UMAP-Enhanced Clustering for Unsupervised Learning
Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks
Exploring the encoding of linguistic representations in the Fully-Connected Layer of generative CNNs for Speech
ESURF: Simple and Effective EDU Segmentation
ML-assisted Randomization Tests for Detecting Treatment Effects in A/B Experiments
LLMic: Romanian Foundation Language Model
Entailed Between the Lines: Incorporating Implication into NLI
Benchmarking Abstractive Summarisation: A Dataset of Human-authored Summaries of Norwegian News Articles
Testing Human-Hand Segmentation on In-Distribution and Out-of-Distribution Data in Human-Robot Interactions Using a Deep Ensemble Model
Pedestrian Trajectory Prediction Based on Social Interactions Learning With Random Weights
Adaptive Collocation Point Strategies For Physics Informed Neural Networks via the QR Discrete Empirical Interpolation Method
C2PD: Continuity-Constrained Pixelwise Deformation for Guided Depth Super-Resolution
Fast sampling and model selection for Bayesian mixture models
Enhancing Talent Employment Insights Through Feature Extraction with LLM Finetuning
Large Language Models for Interpretable Mental Health Diagnosis
Finite Sample Identification of Partially Observed Bilinear Dynamical Systems
A Step Toward Interpretability: Smearing the Likelihood
GPT as a Monte Carlo Language Tree: A Probabilistic Perspective
PowerGraph-LLM: Novel Power Grid Graph Embedding and Optimization with Large Language Models
Dataset Distillation via Committee Voting
UnCommon Objects in 3D
E2ESlack: An End-to-End Graph-Based Framework for Pre-Routing Slack Prediction
Training-Free Motion-Guided Video Generation with Enhanced Temporal Consistency Using Motion Consistency Loss
MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training
Dynamic Prototype Rehearsal for Continual ECG Arrhythmia Detection
SST-EM: Advanced Metrics for Evaluating Semantic, Spatial and Temporal Aspects in Video Editing
disco: Distributional Synthetic Controls
ML Mule: Mobile-Driven Context-Aware Collaborative Learning
Investigating Map-Based Path Loss Models: A Study of Feature Representations in Convolutional Neural Networks
Confident Pseudo-labeled Diffusion Augmentation for Canine Cardiomegaly Detection
Investigating Large Language Models in Inferring Personality Traits from User Conversations
IP-FaceDiff: Identity-Preserving Facial Video Editing with Diffusion
Communication-Efficient, 2D Parallel Stochastic Gradient Descent for Distributed-Memory Optimization
RadAlign: Advancing Radiology Report Generation with Vision-Language Concept Alignment
The Paradox of Success in Evolutionary and Bioinspired Optimization: Revisiting Critical Issues, Key Studies, and Methodological Pathways
Improving DeFi Accessibility through Efficient Liquidity Provisioning with Deep Reinforcement Learning
Inductive Learning of Robot Task Knowledge from Raw Data and Online Expert Feedback
Human-Inspired Multi-Level Reinforcement Learning
Three-view Focal Length Recovery From Homographies
Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Method
Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
Data and System Perspectives of Sustainable Artificial Intelligence
Smart Learning in the 21st Century: Advancing Constructionism Across Three Digital Epochs

All 224