Papers

New on arXiv

Sat 23 Nov 2024

148 papers

FollowGen: A Scaled Noise Conditional Diffusion Model for Car-Following Trajectory PredictionDiffusion models → Diffusion and flow policies for robotics
Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ DocumentsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Classifier-Free Guidance inside the Attraction Basin May Cause MemorizationDiffusion models → Diffusion foundations and sampling
ChemSafetyBench: Benchmarking LLM Safety on Chemistry DomainLLM safety and security → Safety alignment, refusal and guardrails
Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challengeRetrieval-augmented generation → Legal and financial RAG
"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal AttacksLLM safety and security → Jailbreaking
DiM-Gestor: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2State-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video DiffusionDiffusion models → Audio, speech and music
textitRevelio: Interpreting and leveraging semantic information in diffusion modelsDiffusion models → Diffusion foundations and sampling +1
Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention LensMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Two Heads Are Better Than One: Collaborative LLM Embodied Agents for Human-Robot InteractionLLM agents and tool use → General LLM agent frameworks and benchmarks
Active Prompt Learning with Vision-Language Model PriorsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against JailbreaksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
Importance-Based Token Merging for Efficient Image and Video GenerationDiffusion models → Diffusion foundations and sampling +1
Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge AlignmentMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
MC-NEST: Enhancing Mathematical Reasoning in Large Language Models leveraging a Monte Carlo Self-Refine TreeLLM reasoning → Mathematical reasoning
ACE: Action Concept Enhancement of Video-Language Models in Procedural VideosMultimodal LLMs / vision-language models → Video understanding with MLLMs
TKG-DM: Training-free Chroma Key Content Generation Diffusion ModelDiffusion models → Image generation, text-to-image and editing
From MTEB to MTOB: Retrieval-Augmented Classification for Descriptive GrammarsRetrieval-augmented generation → Generation and context integration
ReWind: Understanding Long Videos with Instructed Learnable MemoryMultimodal LLMs / vision-language models → Video understanding with MLLMs
NeRF Inpainting with Geometric Diffusion Prior and Balanced Score DistillationDiffusion models → 3D, point cloud and scene generation
Optical-Flow Guided Prompt Optimization for Coherent Video GenerationDiffusion models → Video generation
MUNBa: Machine Unlearning via Nash BargainingLLM safety and security → Machine unlearning
Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation BenchmarkDiffusion models → Image generation, text-to-image and editing
Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in ThaiSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
Towards Robust Evaluation of Unlearning in LLMs via Data TransformationsLLM safety and security → Machine unlearning
Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual LearningState-space sequence models (S4, Mamba) → Vision Mamba backbones
MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language TrackingState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image RedundancyMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
freePruner: A Training-free Approach for Large Multimodal Model AccelerationMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
Twin Trigger Generative Networks for Backdoor Attacks against Object DetectionLLM safety and security → Backdoor and data poisoning attacks
ConsistentAvatar: Learning to Diffuse Fully Consistent Talking Head Avatar with Temporal GuidanceDiffusion models → Audio, speech and music
Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-ExpertsMultimodal LLMs / vision-language models → Image editing and quality assessment +1
LDM-Morph: Latent diffusion model guided deformable image registrationDiffusion models → Medical imaging and segmentation
Learning a local trading strategy: deep reinforcement learning for grid-scale renewable energy integrationDeep reinforcement learning methods → RL for energy, networks and operations
OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language PretrainingMultimodal LLMs / vision-language models → Medical vision-language models +1
Communication-Efficient Sparsely-Activated Model Training via Sequence Migration and Token CondensationMixture-of-experts → Efficient MoE training and inference systems
FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any GranularityMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Partial Knowledge Distillation for Alleviating the Inherent Inter-Class Discrepancy in Federated LearningKnowledge distillation → Federated, robust and private distillation
Less is More: Optimizing Function Calling for LLM Execution on Edge DevicesLLM agents and tool use → Tool learning and function calling
Gradient-Free Classifier Guidance for Diffusion Model SamplingDiffusion models → Diffusion foundations and sampling
Inducing Human-like Biases in Moral Reasoning Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
Online High-Frequency Trading Stock Forecasting with Automated Feature Clustering and Radial Basis Function Neural Networks
Reservoir Computing Generalized
Capacitive Touch Sensor Modeling With a Physics-informed Neural Network and Maxwell's Equations
MIN: Multi-channel Interaction Network for Drug-Target Interaction with Protein Distillation
Creating Hierarchical Dispositions of Needs in an Agent
3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
LoBAM: LoRA-Based Backdoor Attack on Model Merging
Text-to-SQL Calibration: No Need to Ask -- Just Rescale Model Probabilities
Gradient-Guided Parameter Mask for Multi-Scenario Image Restoration Under Adverse Weather
Federated Learning in Chemical Engineering: A Tutorial on a Framework for Privacy-Preserving Collaboration Across Distributed Data Sources
Towards Satellite Image Road Graph Extraction: A Global-Scale Dataset and A Novel Method
Maximizing the Impact of Deep Learning on Subseasonal-to-Seasonal Climate Forecasting: The Essential Role of Optimization
An Information-Theoretic Regularizer for Lossy Neural Image Compression
Learn2Synth: Learning Optimal Data Synthesis Using Hypergradients for Brain Image Segmentation
IRSKG: Unified Intrusion Response System Knowledge Graph Ontology for Cyber Defense
Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models
Ontology-Constrained Generation of Domain-Specific Clinical Summaries
Enabling Efficient Serverless Inference Serving for LLM (Large Language Model) in the Cloud
Improving Next Tokens via Second-to-Last Predictions with Generate and Refine
Federated PCA and Estimation for Spiked Covariance Matrices: Optimal Rates and Efficient Algorithm
SMM-Conv: Scalar Matrix Multiplication with Zero Packing for Accelerated Convolution
Training an Open-Vocabulary Monocular 3D Object Detection Model without 3D Data
Machine-agnostic Automated Lumbar MRI Segmentation using a Cascaded Model Based on Generative Neurons
Machine Learning-based sEMG Signal Classification for Hand Gesture Recognition
OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs
Sample- and Parameter-Efficient Auto-Regressive Image Models
Circuit design in biology and machine learning. II. Anomaly detection
Safe PDE Boundary Control with Neural Operators
AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Dataset
Learning state and proposal dynamics in state-space models using differentiable particle filters and neural networks
"All that Glitters": Approaches to Evaluations with Unreliable Model and Human Annotations
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
Aligning Generalisation Between Humans and Machines
Trans-Glasso: A Transfer Learning Approach to Precision Matrix Estimation
Multi-label Sequential Sentence Classification via Large Language Model
On the importance of local and global feature learning for automated measurable residual disease detection in flow cytometry data
Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation
Accelerated Hydration Site Localization and Thermodynamic Profiling
A Scalable Approach to Covariate and Concept Drift Management via Adaptive Data Segmentation
If you can describe it, they can see it: Cross-Modal Learning of Visual Concepts from Textual Descriptions
GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers
FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video
Enhancing Object Detection Accuracy in Autonomous Vehicles Using Synthetic Data
How Texts Help? A Fine-grained Evaluation to Reveal the Role of Language in Vision-Language Tracking
Comparative Analysis of Resource-Efficient CNN Architectures for Brain Tumor Classification
An adversarial feature learning based semantic communication method for Human 3D Reconstruction
A Survey on LLM-as-a-Judge
Classifier Enhanced Deep Learning Model for Erythroblast Differentiation with Limited Data
From Complexity to Parsimony: Integrating Latent Class Analysis to Uncover Multimodal Learning Patterns in Collaborative Learning
Deep Learning for THz Channel Estimation and Beamforming Prediction via Sub-6GHz Channel
Transparent but Powerful: Explainability, Accuracy, and Generalizability in ADHD Detection from Social Media Data
Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing
FLD+: Data-efficient Evaluation Metric for Generative Models
EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splatting
MulModSeg: Enhancing Unpaired Multi-Modal Medical Image Segmentation with Modality-Conditioned Text Embedding and Alternating Training
Do LLMs Agree on the Creativity Evaluation of Alternative Uses?
Reassessing Layer Pruning in LLMs: New Insights and Methods

All 148