Papers

New on arXiv

Mon 2 Dec 2024

383 papers

Mastering Board Games by External and Internal Planning with Language ModelsLLM reasoning → Reasoning for agents, planning and code
Multi-View 3D Reconstruction using Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
PKRD-CoT: A Unified Chain-of-thought Prompting for Multi-Modal Large Language Models in Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
Explore Reinforced: Equilibrium Approximation with Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
Free Process Rewards without Process LabelsLLM reasoning → Reinforcement learning for reasoning +1
Self-Improvement in Language Models: The Sharpening MechanismSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
MALT: Improving Reasoning with Multi-Agent LLM TrainingLLM reasoning → Reasoning for agents, planning and code +1
Diffusion models learn distributions generated by complex Langevin dynamicsDiffusion models → Diffusion foundations and sampling
RandAR: Decoder-only Autoregressive Visual Generation in Random OrdersEfficient LLM inference and serving → Fast autoregressive visual generation
X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
World-consistent Video Diffusion with Explicit 3D ModelingDiffusion models → 3D, point cloud and scene generation
Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-trainingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative ModelsDiffusion models → Diffusion foundations and sampling
Gradient-Free Generation for Hard-Constrained SystemsDiffusion models → Flow matching, time series and science
HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration TestingLLM agents and tool use → Agent threats, guardrails and governance
LamRA: Large Multimodal Model as Your Advanced Retrieval AssistantMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous DrivingWorld models → World models for autonomous driving +1
Driving View Synthesis on Free-form Trajectories with Generative PriorDiffusion models → Diffusion and flow policies for robotics +1
Enhancing Video-LLM Reasoning via Agent-of-Thoughts DistillationLLM reasoning → Multimodal reasoning +1
Can We Afford The Perfect Prompt? Balancing Cost and Accuracy with the Economical Prompting IndexLLM reasoning → Prompting and chain-of-thought reasoning
Diffusion Models with Anisotropic Gaussian Splatting for Image InpaintingDiffusion models → 3D, point cloud and scene generation
Gen-SIS: Generative Self-augmentation Improves Self-supervised LearningDiffusion models → Image generation, text-to-image and editing
DaDu-E: Rethinking the Role of Large Language Model in Robotic Computing PipelineLLM reasoning → Spatial and embodied reasoning
Vision-based Tactile Image Generation via Contact Condition-guided Diffusion ModelDiffusion models → Diffusion and flow policies for robotics
NYT-Connections: A Deceptively Simple Text Classification Task that Stumps System-1 ThinkersLLM reasoning → Reasoning benchmarks and evaluation
Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive SequenceLLM agents and tool use → Medical and scientific domain agents
Agentic-HLS: An agentic reasoning based high-level synthesis system using large language models (AI for EDA workshop 2024)LLM reasoning → Reasoning for agents, planning and code +1
MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question ComplexityRetrieval-augmented generation → Agentic RAG, agents and memory
VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment RetrievalMultimodal LLMs / vision-language models → Video understanding with MLLMs
SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language ModelLLM reasoning → Spatial and embodied reasoning +1
Improved Large Language Model Jailbreak Detection via Pretrained EmbeddingsLLM agents and tool use → Agent threats, guardrails and governance +1
Towards Type Agnostic Cyber Defense AgentsDeep reinforcement learning methods → Adversarial robustness and RL in finance
Effectiveness of L2 Regularization in Privacy-Preserving Machine LearningLLM safety and security → Membership inference attacks
Generative AI-based data augmentation for improved bioacoustic classification in noisy environmentsDiffusion models → Audio, speech and music
CopyrightShield: Enhancing Diffusion Model Security against Copyright Infringement AttacksDiffusion models → Robustness, privacy and adversarial aspects +1
InfinityDrive: Breaking Time Limits in Driving World ModelsWorld models → World models for autonomous driving +1
Intelligent Spark Agents: A Modular LangGraph Framework for Scalable, Visualized, and Enhanced Big Data Machine Learning WorkflowsLLM agents and tool use → Web, search, and research agents
FastRM: An efficient and automatic explainability framework for multimodal generative modelsLLM reasoning → Multimodal reasoning +1
Early Exit Is a Natural Capability in Transformer-based Models: An Empirical Study on Early Exit without Joint OptimizationEfficient LLM inference and serving → Early exit and edge inference
PLD+: Accelerating LLM inference by leveraging Language Model ArtifactsEfficient LLM inference and serving → Speculative decoding
LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal DemonstrationsOffline RL and imitation learning from data → Robot manipulation imitation learning
BadPatch: Diffusion-Based Generation of Physical Adversarial PatchesDiffusion models → Robustness, privacy and adversarial aspects
CPA: Camera-pose-awareness Diffusion Transformer for Video GenerationDiffusion models → Video generation
MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint DetectionState-space sequence models (S4, Mamba) → Vision Mamba backbones
Task Adaptation of Reinforcement Learning-based NAS Agents through Transfer LearningDeep reinforcement learning methods → Deep RL algorithms and representations
HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous DrivingEnd-to-end autonomous driving → Generative simulation for driving
MambaU-Lite: A Lightweight Model based on Mamba and Integrated Channel-Spatial Attention for Skin Lesion SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Harnessing Preference Optimisation in Protein LMs for Hit Maturation in Cell TherapyLLM alignment / RLHF / preference optimisation → Preference optimization for molecular design
Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware MaskingEfficient LLM inference and serving → Serving systems and request scheduling
An overview of diffusion models for generative artificial intelligenceDiffusion models → Diffusion foundations and sampling
Understanding Museum Exhibits using Vision-Language ReasoningLLM reasoning → Multimodal reasoning +1
MoTrans: Customized Motion Transfer with Text-driven Video Diffusion ModelsDiffusion models → Video generation
Negative Token Merging: Image-based Adversarial Feature GuidanceDiffusion models → Robustness, privacy and adversarial aspects
Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data CurationDiffusion models → Video generation
LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual PreferencesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Enhancing Perception Capabilities of Multimodal LLMs with Training-Free FusionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
MFTF: Mask-free Training-free Object Level Layout Control Diffusion ModelMultimodal LLMs / vision-language models → Image editing and quality assessment +1
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model EnhancementLLM reasoning → Multimodal reasoning +1
MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible CostDiffusion models → Image generation, text-to-image and editing
Ponder & Press: Advancing Visual GUI Agent towards General Computer ControlLLM agents and tool use → GUI and mobile agents
NLPrompt: Noise-Label Prompt Learning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Yi-Lightning Technical ReportLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent DialoguesLLM agents and tool use → Multimodal and embodied agents
Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic PerspectiveDiffusion models → Diffusion and flow policies for robotics +1
Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision LocalizationDiffusion models → Robustness, privacy and adversarial aspects
Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image GenerationDiffusion models → Diffusion foundations and sampling
Integrating Decision-Making Into Differentiable Optimization Guided Learning for End-to-End Planning of Autonomous VehiclesEnd-to-end autonomous driving → Imitation-learning end-to-end planners
GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning
PainterNet: Adaptive Image Inpainting with Actual-Token Attention and Diverse Mask ControlDiffusion models → 3D, point cloud and scene generation
Siamese Machine Unlearning with Knowledge Vaporization and ConcentrationLLM safety and security → Machine unlearning
TinyFusion: Diffusion Transformers Learned ShallowDiffusion models → Diffusion foundations and sampling
OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Rectified Flow For Structure Based Drug DesignDiffusion models → Flow matching, time series and science
OmniFlow: Any-to-Any Generation with Multi-Modal Rectified FlowsDiffusion models → Audio, speech and music
Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual TranslationLLM agents and tool use → Tool learning and function calling
LoyalDiffusion: A Diffusion Model Guarding Against Data ReplicationDiffusion models → Diffusion foundations and sampling
DIR: Retrieval-Augmented Image Captioning with Comprehensive UnderstandingRetrieval-augmented generation → Multimodal RAG
Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with DemonstrationsDeep reinforcement learning methods → Deep RL algorithms and representations
LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step ArithmeticsLLM reasoning → Prompting and chain-of-thought reasoning
VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
A Memory-Based Reinforcement Learning Approach to Integrated Sensing and CommunicationDeep reinforcement learning methods → RL for energy, networks and operations
FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking PortraitDiffusion models → Audio, speech and music
Quantization-Aware Imitation-Learning for Resource-Efficient Robotic ControlVision-language-action models → Efficient VLA inference and adaptation
SAUP: Situation Awareness Uncertainty Propagation on LLM AgentLLM agents and tool use → General LLM agent frameworks and benchmarks
On the Feature Learning in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Social Media Data Mining With Natural Language Processing on Public Dream Contents
Forward and Inverse Simulation of Pseudo-Two-Dimensional Model of Lithium-Ion Batteries Using Neural Networks
NLLG Quarterly arXiv Report 09/24: What are the most influential current AI Papers?
High-Throughput Detection of Risk Factors to Sudden Cardiac Arrest in Youth Athletes: A Smartwatch-Based Screening Platform
AI in Education: Rationale, Principles, and Instructional Implications
Rashomon effect in Educational Research: Why More is Better Than One for Measuring the Importance of the Variables?
Federated Block-Term Tensor Regression for decentralised data analysis in healthcare
Physics-informed Gaussian Processes as Linear Model Predictive Controller
The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?
emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation
DYffCast: Regional Precipitation Nowcasting Using IMERG Satellite Data. A case study over South America
Enhanced N-BEATS for Mid-Term Electricity Demand Forecasting
Predicting the Impact of Scope Changes on Project Cost and Schedule Using Machine Learning Techniques

All 383