Papers

New on arXiv

Wed 4 Dec 2024

311 papers

Modular addition without black-boxes: Compressing explanations of MLPs that compute numerical integrationMechanistic interpretability → Circuits and mechanistic analysis
A Benchmark of Generative Methods for Zero-Shot Environmental Sound ClassificationDiffusion models → Audio, speech and music
Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
ARCON: Advancing Auto-Regressive Continuation for Driving VideosEnd-to-end autonomous driving → Generative simulation for driving
Multi-view Image Diffusion via Coordinate Noise and Fourier AttentionDiffusion models → Image generation, text-to-image and editing
VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video UnderstandingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
PathletRL++: Optimizing Trajectory Pathlet Extraction and Dictionary Formation via Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
Scaling Inference-Time Search with Vision Value Model for Improved Visual ComprehensionLLM reasoning → Multimodal reasoning +1
Sprite Sheet Diffusion: Generate Game Character for AnimationDiffusion models → Video generation
Evaluating Language Models as Synthetic Data GeneratorsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Personalizing Multimodal Large Language Models for Image Captioning: An Experimental AnalysisMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
DiffuPT: Class Imbalance Mitigation for Glaucoma Detection via Diffusion Based Generation and Model PretrainingDiffusion models → Medical imaging and segmentation
How to Correctly do Semantic Backpropagation on Language-based Agentic SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
CBEval: A framework for evaluating and interpreting cognitive biases in LLMsLLM reasoning → Reasoning benchmarks and evaluation
Navigation World ModelsWorld models → World models for navigation
FreeSim: Toward Free-viewpoint Camera Simulation in Driving ScenesWorld models → World models for autonomous driving
INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction TuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based AgentsLLM agents and tool use → Social simulation and multi-agent debate
FLAIR: VLM with Fine-grained Language-informed Image RepresentationsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
MIDI: Multi-Instance Diffusion for Single Image to 3D Scene GenerationDiffusion models → 3D, point cloud and scene generation
Best-of-N JailbreakingLLM safety and security → Jailbreaking
PaliGemma 2: A Family of Versatile VLMs for TransferMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Perception Tokens Enhance Visual Reasoning in Multimodal Language ModelsLLM reasoning → Multimodal reasoning +1
Distilling Diffusion Models to Efficient 3D LiDAR Scene CompletionDiffusion models → 3D, point cloud and scene generation
Enhancing CLIP Conceptual Embedding through Knowledge DistillationKnowledge distillation → Multimodal distillation
Flow Matching with General Discrete Paths: A Kinetic-Optimal PerspectiveDiffusion models → Flow matching, time series and science
Convolutional Neural Networks and Mixture of Experts for Intrusion Detection in 5G Networks and beyondMixture-of-experts → Vision mixture-of-experts
Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction TuningLLM reasoning → Multimodal reasoning
CleanDIFT: Diffusion Features without NoiseDiffusion models → Diffusion foundations and sampling
SINGER: Vivid Audio-driven Singing Video Generation with Multi-scale Spectral Diffusion ModelDiffusion models → Audio, speech and music
PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient GenerationLLM reasoning → Multimodal reasoning +2
Skel3D: Skeleton Guided Novel View SynthesisDiffusion models → 3D, point cloud and scene generation
Implicit Priors Editing in Stable Diffusion via Targeted Token AdjustmentDiffusion models → Image generation, text-to-image and editing
WiS Platform: Enhancing Evaluation of LLM-Based Multi-Agent Systems Through Game-Based AnalysisLLM agents and tool use → General LLM agent frameworks and benchmarks
TASR: Timestep-Aware Diffusion Model for Image Super-ResolutionDiffusion models → Inverse problems and image restoration
DIVE: Taming DINO for Subject-Driven Video EditingDiffusion models → Video generation
A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated ReasoningDiffusion models → Diffusion and flow policies for robotics
Black-Box Forgery Attacks on Semantic Watermarks for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
RFSR: Improving ISR Diffusion Models via Reward Feedback LearningDiffusion models → Inverse problems and image restoration
Learning on One Mode: Addressing Multi-modality in Offline Reinforcement LearningOffline RL and imitation learning from data → Imitation learning methods
DynamicControl: Adaptive Condition Selection for Improved Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
Alignment at Pre-training! Towards Native Alignment for Arabic LLMsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Variable-Speed Teaching-Playback as Real-World Data Augmentation for Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and PruningMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?LLM safety and security → Safety alignment, refusal and guardrails
ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable CompressionLLM reasoning → Test-time compute and efficient thinking +1
Weighted-Reward Preference Optimization for Implicit Model FusionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
AffordDP: Generalizable Diffusion Policy with Transferable AffordanceDiffusion models → Diffusion and flow policies for robotics
A Probabilistic Formulation of Offset Noise in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
DiffKV: Differentiated Memory Management for Large Language Models with Parallel KV CompactionEfficient LLM inference and serving → KV cache optimization
Robust Multi-bit Text Watermark with LLM-based ParaphrasersLLM safety and security → Watermarking generated content and models
Experience-driven discovery of planning strategiesDeep reinforcement learning methods → Deep RL algorithms and representations
CredID: Credible Multi-Bit Watermark for Large Language Models IdentificationLLM safety and security → Watermarking generated content and models
ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and ReasoningLLM reasoning → Time series reasoning +1
TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLMLLM agents and tool use → Social simulation and multi-agent debate
Mimir: Improving Video Diffusion Models for Precise Text UnderstandingDiffusion models → Video generation
Domain Fusion Controllable Generalization for Cross-Domain Time Series Forecasting from Multi-Domain Integrated DistributionDiffusion models → Flow matching, time series and science
Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving PoliciesEnd-to-end autonomous driving → Adversarial scenarios and safety testing +1
Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly DetectionDiffusion models → Flow matching, time series and science
Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA ApproachDiffusion models → Inverse problems and image restoration
Learning Whole-Body Loco-Manipulation for Omni-Directional Task Space Pose Tracking with a Wheeled-Quadrupedal-ManipulatorDeep reinforcement learning methods → RL for robot locomotion and manipulation
Human Multi-View Synthesis from a Single-View Model:Transferred Body and Face RepresentationsDiffusion models → 3D, point cloud and scene generation
Data Acquisition for Improving Model Fairness using Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language ModelsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Partially Conditioned Patch Parallelism for Accelerated Diffusion Model InferenceDiffusion models → Diffusion foundations and sampling
Semantic Segmentation Prior for Diffusion-Based Real-World Super-ResolutionDiffusion models → Inverse problems and image restoration
Incorporating System-level Safety Requirements in Perception Models via Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
Who Brings the Frisbee: Probing Hidden Hallucination Factors in Large Vision-Language Model via Causality AnalysisMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Inverse Delayed Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
TemporalVLM: Video LLMs for Temporal Reasoning in Long VideosLLM reasoning → Multimodal reasoning
Panoptic Diffusion Models: co-generation of images and segmentation mapsDiffusion models → Image generation, text-to-image and editing
Unveiling the Role of Artificial Intelligence and Stock Market Growth in Achieving Carbon Neutrality in the United States: An ARDL Model Analysis
Multi-Branch Mutual-Distillation Transformer for EEG-Based Seizure Subtype Classification
Leveraging Generative Adversarial Networks for Addressing Data Imbalance in Financial Market Supervision
Benchmarking Harmonized Tariff Schedule Classification Models
Seamless Optical Cloud Computing across Edge-Metro Network for Generative AI
Artificial Intelligence without Restriction Surpassing Human Intelligence with Probability One: Theoretical Insight into Secrets of the Brain with AI Twins of the Brain
Patient-specific prediction of glioblastoma growth via reduced order modeling and neural networks
Mapping The Layers of The Ocean Floor With a Convolutional Neural Network
IMPACT:InMemory ComPuting Architecture Based on Y-FlAsh Technology for Coalesced Tsetlin Machine Inference
The Role of Text-to-Image Models in Advanced Style Transfer Applications: A Case Study with DALL-E 3
Prompting Large Language Models for Clinical Temporal Relation Extraction
Pragmatic Metacognitive Prompting Improves LLM Performance on Sarcasm Detection
Video Quality Assessment: A Comprehensive Survey
MRGen: Segmentation Data Engine for Underrepresented MRI Modalities
Community Detection with Heterogeneous Block Covariance Model
WithdrarXiv: A Large-Scale Dataset for Retraction Study
A Contemporary Overview: Trends and Applications of Large Language Models on Mobile Devices
Learning Networks from Wide-Sense Stationary Stochastic Processes
End to End Collaborative Synthetic Data Generation
Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks
Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning
HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution
Deep Variational Bayesian Modeling of Haze Degradation Process
A Hybrid Deep-Learning Model for El Ni~no Southern Oscillation in the Low-Data Regime
Exploring the Role of AI-Powered Chatbots for Teens and Young Adults with ASD or Social Anxiety
Utilizing Machine Learning Models to Predict Acute Kidney Injury in Septic Patients from MIMIC-III Database
Domain-specific Question Answering with Hybrid Search

All 311