Papers

New on arXiv

Thu 5 Dec 2024

349 papers

SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and RolloutDiffusion models → Diffusion and flow policies for robotics +1
TANGO: Training-free Embodied AI Agents for Open-world TasksLLM agents and tool use → Multimodal and embodied agents
Reinforcement Learning Enhanced LLMs: A SurveyLLM reasoning → Reinforcement learning for reasoning +1
Guidance is All You Need: Temperature-Guided Reasoning in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation LearningRetrieval-augmented generation → Generation and context integration
Cross-Self KV Cache Pruning for Efficient Vision-Language InferenceEfficient LLM inference and serving → Visual token pruning in multimodal models
REL: Working out is all you needLLM reasoning → Reasoning benchmarks and evaluation
Multi-Preference Optimization: Generalizing DPO via Set-Level ContrastsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Using Diffusion Priors for Video Amodal SegmentationDiffusion models → Medical imaging and segmentation
ARC Prize 2024: Technical ReportLLM reasoning → Multimodal reasoning
Give me Some Hard Questions: Synthetic Data Generation for Clinical QASynthetic data and self-improvement for LLMs → Medical synthetic data and agents
Understanding Hidden Computations in Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
Mask-Adapter: The Devil is in the Masks for Open-Vocabulary SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
MageBench: Bridging Large Multimodal Models to AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
PaintScene4D: Consistent 4D Scene Generation from Text PromptsDiffusion models → 3D, point cloud and scene generation
NVILA: Efficient Frontier Visual Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
VisionZip: Longer is Better but Not Necessary in Vision Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
4Real-Video: Learning Generalizable Photo-Realistic 4D Video DiffusionDiffusion models → 3D, point cloud and scene generation
LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative PriorsDiffusion models → Image generation, text-to-image and editing
Aguvis: Unified Pure Vision Agents for Autonomous GUI InteractionLLM reasoning → Multimodal reasoning
NaVILA: Legged Robot Vision-Language-Action Model for NavigationVision-language-action models → Generalist VLA models and benchmarks
p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio DecayMultimodal LLMs / vision-language models → Visual token pruning and efficiency
MEMO: Memory-Guided Diffusion for Expressive Talking Video GenerationDiffusion models → Audio, speech and music
EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World ScenariosLLM reasoning → Spatial and embodied reasoning +1
GenMAC: Compositional Text-to-Video Generation with Multi-Agent CollaborationLLM agents and tool use → Multimodal and embodied agents
Divot: Diffusion Powers Video Tokenizer for Comprehension and GenerationDiffusion models → Video generation
Grounding Descriptions in Images informs Zero-Shot Visual RecognitionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Towards Fast Safe Online Reinforcement Learning via Policy FinetuningDeep reinforcement learning methods → Deep RL algorithms and representations
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth FusionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM ManipulationLLM agents and tool use → Agent threats, guardrails and governance
VladVA: Discriminative Fine-tuning of LVLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Finer Behavioral Foundation Models via Auto-Regressive Features and Advantage WeightingOffline RL and imitation learning from data → Offline RL algorithms +1
ActFusion: a Unified Diffusion Model for Action Segmentation and AnticipationDiffusion models → Video generation
Retrieval-Augmented Machine Translation with Unstructured KnowledgeRetrieval-augmented generation → Generation and context integration
Reinforcement Learning for Freeway Lane-Change Regulation via Connected VehiclesDeep reinforcement learning methods → RL for autonomous driving and traffic
Likelihood-Scheduled Score-Based Generative Modeling for Fully 3D PET Image ReconstructionDiffusion models → Medical imaging and segmentation
Action Mapping for Reinforcement Learning in Continuous Environments with ConstraintsDeep reinforcement learning methods → Deep RL algorithms and representations
Multi-Subject Image Synthesis as a Generative Prior for Single-Subject PET Image ReconstructionDiffusion models → Medical imaging and segmentation
GRAM: Generalization in Deep RL with a Robust Adaptation ModuleDeep reinforcement learning methods → Deep RL algorithms and representations
Generative-Model-Based Fully 3D PET Image Reconstruction by Conditional Diffusion SamplingDiffusion models → Medical imaging and segmentation
FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual CompressionMultimodal LLMs / vision-language models → Visual token pruning and efficiency
ALMA: Alignment with Minimal AnnotationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step DiffusionDiffusion models → Image generation, text-to-image and editing
Structure-Aware Stylized Image Synthesis for Robust Medical Image SegmentationDiffusion models → Medical imaging and segmentation
SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal ModelMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Evolutionary Pre-Prompt Optimization for Mathematical ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
Reinforcement Learning from Wild Animal VideosDeep reinforcement learning methods → RL for robot locomotion and manipulation
PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on TablesLLM reasoning → Knowledge- and tool-augmented reasoning
LMDM:Latent Molecular Diffusion Model For 3D Molecule GenerationDiffusion models → Flow matching, time series and science
Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA ExpertsMixture-of-experts → Vision mixture-of-experts
CALMM-Drive: Confidence-Aware Autonomous Driving with Large Multimodal ModelEnd-to-end autonomous driving → Large language models for driving
A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation TasksDeep reinforcement learning methods → Safe and constrained RL
AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
Reducing Tool Hallucination via Reliability AlignmentLLM agents and tool use → Tool learning and function calling
Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability LandscapesDiffusion models → Diffusion foundations and sampling
Monet: Mixture of Monosemantic Experts for TransformersMechanistic interpretability → SAE features and their applications
GRAF: Graph Retrieval Augmented by Facts for Romanian Legal Multi-Choice Question AnsweringRetrieval-augmented generation → Legal and financial RAG
Enhancing Mathematical Reasoning in LLMs with Background OperatorsLLM reasoning → Mathematical reasoning
Practical Considerations for Agentic LLM SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
LossAgent: Towards Any Optimization Objectives for Image Processing with LLM AgentsLLM agents and tool use → Multimodal and embodied agents
Mind the Gap: Towards Generalizable Autonomous Penetration Testing via Domain Randomization and Meta-Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
Integrated Sensing and Communications for Low-Altitude Economy: A Deep Reinforcement Learning ApproachDeep reinforcement learning methods → RL for robot navigation and UAV control
ZipAR: Parallel Auto-regressive Image Generation through Spatial LocalityEfficient LLM inference and serving → Fast autoregressive visual generation
Prompt Engineering Guidance for Conceptual Agent-based Model Extraction using Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
Learning Dual-Arm Push and Grasp Synergy in Dense ClutterDeep reinforcement learning methods → RL for robot locomotion and manipulation
IF-MDM: Implicit Face Motion Diffusion Model for High-Fidelity Realtime Talking Head GenerationDiffusion models → Audio, speech and music
MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLMLLM reasoning → Prompting and chain-of-thought reasoning
Demonstration Selection for In-Context Learning via Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
Local Curvature Smoothing with Stein's Identity for Efficient Score MatchingDiffusion models → Diffusion foundations and sampling
Is FISHER All You Need in The Multi-AUV Underwater Target Tracking Task?Offline RL and imitation learning from data → Imitation learning methods +1
Learning Speed-Adaptive Walking Agent Using Imitation Learning with Physics-Informed SimulationOffline RL and imitation learning from data → Real-world robot offline RL
Chain-of-Thought in Large Language Models: Decoding, Projection, and ActivationLLM reasoning → Prompting and chain-of-thought reasoning
Enhancing and Accelerating Diffusion-Based Inverse Problem Solving through Measurements OptimizationDiffusion models → Inverse problems and image restoration
InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video ModelsWorld models → World models for autonomous driving
Exploring AI Text Generation, Retrieval-Augmented Generation, and Detection Technologies: a Comprehensive OverviewRetrieval-augmented generation → RAG pipeline design and evaluation
MegaCOIN: Enhancing Medium-Grained Color Perception for Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Traffic Co-Simulation Framework Empowered by Infrastructure Camera Sensing and Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
A Survey on Large Language Model-Based Social Agents in Game-Theoretic ScenariosLLM agents and tool use → Reinforcement learning for LLM agents
Generalizable Targeted Data Poisoning against Varying Physical ObjectsLLM safety and security → Backdoor and data poisoning attacks
MISR: Measuring Instrumental Self-Reasoning in Frontier ModelsLLM reasoning → Test-time compute and efficient thinking
A Noise is Worth Diffusion GuidanceDiffusion models → Diffusion foundations and sampling
Weak-to-Strong Generalization Through the Data-Centric LensLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
DiffSign: AI-Assisted Generation of Customizable Sign Language Videos With Enhanced RealismDiffusion models → Sign language production
Safeguarding Text-to-Image Generation via Inference-Time Prompt-Noise OptimizationDiffusion models → Robustness, privacy and adversarial aspects
CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors GuidanceMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
Educational-Psychological Dialogue Robot Based on Multi-Agent CollaborationLLM agents and tool use → Educational agents and math problem solving
LL-ICM: Image Compression for Low-level Machine Vision via Large Vision-Language ModelMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Beyond the Binary: Capturing Diverse Preferences With Reward RegularizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Pinco: Position-induced Consistent Adapter for Diffusion Transformer in Foreground-conditioned InpaintingDiffusion models → 3D, point cloud and scene generation
EditScout: Locating Forged Regions from Diffusion-based Edited Images with Multimodal LLMMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Towards an Autonomous Test Driver: High-Performance Driver Modeling via Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
ELEMENT: Episodic and Lifelong Exploration via Maximum EntropyDeep reinforcement learning methods → Deep RL algorithms and representations
INRFlow: Flow Matching for INRs in Ambient SpaceDiffusion models → Flow matching, time series and science
How Large Language Models (LLMs) Extrapolate: From Guided Missiles to Guided Prompts
Superposition through Active Learning lens
Hierarchical Multi-Agent DRL Based Dynamic Cluster Reconfiguration for UAV Mobility Management
Early Dementia Detection Using Multiple Spontaneous Speech Prompts: The PROCESS Challenge
Learning-by-teaching with ChatGPT: The effect of teachable ChatGPT agent on programming education

All 349