Papers

New on arXiv

Mon 25 Nov 2024

345 papers

Towards Agentic Schema RefinementLLM agents and tool use → Web, search, and research agents
Targeted Therapy in Data Removal: Object Unlearning Based on Scene GraphsLLM safety and security → Machine unlearning
DiffGuard: Text-Based Safety Checker for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
Speculative Decoding with CTC-based Draft Model for LLM Inference AccelerationEfficient LLM inference and serving → Speculative decoding
MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex ImageMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Unlocking the Potential of Text-to-Image Diffusion with PAC-Bayesian TheoryDiffusion models → Image generation, text-to-image and editing
Towards Precise Scaling Laws for Video Diffusion TransformersDiffusion models → Video generation
Dynamic Self-Distillation via Previous Mini-batches for Fine-tuning Small Language ModelsKnowledge distillation → Knowledge distillation for LLMs
ZoomLDM: Latent Diffusion Model for multi-scale image generationDiffusion models → Medical imaging and segmentation
MotionWavelet: Human Motion Prediction via Wavelet Manifold LearningDiffusion models → Video generation
RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from DemonstrationsOffline RL and imitation learning from data → Robot manipulation imitation learning
Probing the limitations of multimodal language models for chemistry and materials researchMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question AnsweringMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAEMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative EditingDiffusion models → Robustness, privacy and adversarial aspects
CLIPS: An Enhanced CLIP Framework for Learning with Synthetic CaptionsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Logit-KL Flow Matching: Non-Autoregressive Text Generation via Sampling-Hybrid InferenceDiffusion models → Discrete and text diffusion
Pathways on the Image Manifold: Image Editing via Video GenerationDiffusion models → Video generation
Discrete to Continuous: Generating Smooth Transition Poses from Sign Language ObservationDiffusion models → Sign language production
Leveraging Foundation Models To learn the shape of semi-fluid deformable objectsKnowledge distillation → Detection and dense prediction distillation
Controllable Human Image Generation with Personalized Multi-GarmentsDiffusion models → 3D, point cloud and scene generation
From Diffusion to Resolution: Leveraging 2D Diffusion Models for 3D Super-Resolution TaskDiffusion models → Inverse problems and image restoration
Staleness-Centric Optimizations for Parallel Diffusion MoE InferenceMixture-of-experts → Vision mixture-of-experts
CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image SynthesisDiffusion models → Image generation, text-to-image and editing
NovelGS: Consistent Novel-view Denoising via Large Gaussian Reconstruction ModelDiffusion models → 3D, point cloud and scene generation
SynDiff-AD: Improving Semantic Segmentation and End-to-End Autonomous Driving with Synthetic Data from Latent Diffusion ModelsDiffusion models → Medical imaging and segmentation +1
Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt RewritingLLM safety and security → Vision-language and text-to-image safety
Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?LLM reasoning → Knowledge- and tool-augmented reasoning
Self-Generated Critiques Boost Reward Modeling for Language ModelsLLM reasoning → Reinforcement learning for reasoning +2
Exploring Discrete Flow Matching for 3D De Novo Molecule GenerationDiffusion models → Flow matching, time series and science
Preventing Jailbreak Prompts as Malicious Tools for Cybercriminals: A Cyber Defense PerspectiveLLM safety and security → Jailbreaking
LegoPET: Hierarchical Feature Guided Conditional Diffusion for PET Image ReconstructionDiffusion models → Medical imaging and segmentation
Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
DiffBreak: Is Diffusion-Based Purification Robust?Diffusion models → Robustness, privacy and adversarial aspects
Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time SupervisionLLM reasoning → Test-time compute and efficient thinking
RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for RoboticsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI ReconstructionDiffusion models → Inverse problems and image restoration
Continual Deep Reinforcement Learning with Task-Agnostic Policy DistillationDeep reinforcement learning methods → Deep RL algorithms and representations
LaB-RAG: Label Boosted Retrieval Augmented Generation for Radiology Report GenerationRetrieval-augmented generation → Medical and biomedical RAG
Reinforcement Learning for Bidding Strategy Optimization in Day-Ahead Energy MarketDeep reinforcement learning methods → RL for energy, networks and operations
All Languages Matter: Evaluating LMMs on Culturally Diverse 100 LanguagesWorld models → World models for language agents +1
Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image SynthesisDiffusion models → Image generation, text-to-image and editing
Interpreting Language Reward Models via Contrastive ExplanationsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?LLM reasoning → Test-time compute and efficient thinking +1
Deformable Mamba for Wide Field of View SegmentationState-space sequence models (S4, Mamba) → Vision Mamba backbones
SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting SynthesisDiffusion models → 3D, point cloud and scene generation
Privacy Protection in Personalized Diffusion Models via Targeted Cross-Attention Adversarial AttackDiffusion models → Robustness, privacy and adversarial aspects
TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object NavigationLLM reasoning → Spatial and embodied reasoning
Comparison of Generative Learning Methods for Turbulence SurrogatesDiffusion models → Flow matching, time series and science
A Study on Unsupervised Domain Adaptation for Semantic Segmentation in the Era of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Human-Calibrated Automated Testing and Validation of Generative Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache SharingDiffusion models → Video generation
Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong BaselinesRetrieval-augmented generation → Multimodal RAG
Lessons from Studying Two-Hop Latent ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +1
Preference Optimization for Reasoning with Pseudo FeedbackLLM reasoning → Mathematical reasoning +1
One Diffusion to Generate Them AllDiffusion models → Diffusion foundations and sampling
An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion ModelsDiffusion models → Medical imaging and segmentation
DiffDesign: Controllable Diffusion with Meta Prior for Efficient Interior Design GenerationDiffusion models → 3D, point cloud and scene generation
Unraveling Arithmetic in Large Language Models: The Role of Algebraic StructuresLLM reasoning → Mathematical reasoning
SMGDiff: Soccer Motion Generation using diffusion probabilistic modelsDiffusion models → Video generation
MH-MoE: Multi-Head Mixture-of-ExpertsMixture-of-experts → MoE large language models
Video-Text Dataset Construction from Multi-AI Feedback: Promoting Weak-to-Strong Preference Learning for Video Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Enhancing Multi-Agent Consensus through Third-Party LLM Integration: Analyzing Uncertainty and Mitigating Hallucinations in Large Language ModelsLLM agents and tool use → Medical and scientific domain agents
SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video AnalysisMultimodal LLMs / vision-language models → Video understanding with MLLMs
Image Generation Diversity Issues and How to Tame ThemDiffusion models → Image generation, text-to-image and editing
MixPE: Quantization and Hardware Co-design for Efficient LLM InferenceEfficient LLM inference and serving → KV cache quantization
MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion ModelDiffusion models → 3D, point cloud and scene generation
DeDe: Detecting Backdoor Samples for SSL Encoders via DecodersLLM safety and security → Backdoor and data poisoning attacks
Multi-Robot Reliable Navigation in Uncertain Topological Environments with Graph Attention NetworksDeep reinforcement learning methods → RL for robot navigation and UAV control
Context Awareness Gate For Retrieval Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
End-to-End Steering for Autonomous Vehicles via Conditional Imitation Co-LearningEnd-to-end autonomous driving → Imitation-learning end-to-end planners
CIA: Controllable Image Augmentation Framework Based on Stable DiffusionDiffusion models → Image generation, text-to-image and editing
Why the Agent Made that Decision: Contrastive Explanation Learning for Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
LLM Augmentations to support Analytical Reasoning over Multiple DocumentsLLM reasoning → Reasoning benchmarks and evaluation
Adaptive Circuit Behavior and Generalization in Mechanistic InterpretabilityMechanistic interpretability → Circuits and mechanistic analysis
Boosting 3D Object Generation through PBR MaterialsDiffusion models → 3D, point cloud and scene generation
Debiasing Classifiers by Amplifying Bias with Latent Diffusion and Large Language ModelsDiffusion models → Image generation, text-to-image and editing
SAGEval: The frontiers of Satisfactory Agent based NLG Evaluation for reference-free open-ended textLLM agents and tool use → General LLM agent frameworks and benchmarks
The brain versus AI: World-model-based versatile circuit computation underlying diverse functions in the neocortex and cerebellumWorld models → World models for navigation
ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image ExplorationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Agent-Based Modelling Meets Generative AI in Social Network SimulationsLLM agents and tool use → Social simulation and multi-agent debate
From Dashcam Videos to Driving Simulations: Stress Testing Automated Vehicles against Rare EventsEnd-to-end autonomous driving → Generative simulation for driving
M3: Mamba-assisted Multi-Circuit Optimization via MBRL with Effective SchedulingState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models +1
Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Anomaly Detection in California Electricity Price Forecasting: Enhancing Accuracy and Reliability Using Principal Component Analysis
Swin fMRI Transformer Predicts Early Neurodevelopmental Outcomes from Neonatal fMRI
Trustworthy artificial intelligence in the energy sector: Landscape analysis and evaluation framework
Can LLMs faithfully generate their layperson-understandable 'self'?: A Case Study in High-Stakes Domains
A Physics-Inspired Deep Learning Framework with Polar Coordinate Attention for Ptychographic Imaging
HiCat: A Semi-Supervised Approach for Cell Type Annotation
DocEDA: Automated Extraction and Design of Analog Circuits from Documents with Large Language Model
Specifications: The missing link to making the development of LLM systems an engineering discipline
Enhanced Lung Cancer Survival Prediction using Semi-Supervised Pseudo-Labeling and Learning from Diverse PET/CT Datasets
Deep Learning-Based Electricity Price Forecast for Virtual Bidding in Wholesale Electricity Market
A Learn-to-Optimize Approach for Coordinate-Wise Step Sizes for Quasi-Newton Methods
Real-time volumetric free-hand ultrasound imaging for large-sized organs: A study of imaging the whole spine
A Cross-Corpus Speech Emotion Recognition Method Based on Supervised Contrastive Learning
A quantum inspired predictor of Parkinsons disease built on a diverse, multimodal dataset
Deciphering Acoustic Emission with Machine Learning

All 345