Papers

New on arXiv

Mon 22 Apr 2024

252 papers

ControlMol: Adding Substructure Control To Molecule Diffusion ModelsDiffusion models → Flow matching, time series and science
Class-Level Code Generation from Natural Language Using Iterative, Tool-Enhanced Reasoning over RepositoryLLM reasoning → Reasoning for agents, planning and code
Learning Control Barrier Functions and their application in Reinforcement Learning: A SurveyDeep reinforcement learning methods → Safe and constrained RL
Interactive Visual Learning for Stable DiffusionDiffusion models → Image generation, text-to-image and editing
SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common SenseLLM reasoning → Prompting and chain-of-thought reasoning
MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsMixture-of-experts → Mixture of LoRA experts
Towards Multi-Morphology Controllers with Diversity and Knowledge DistillationKnowledge distillation → Multimodal distillation
Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension TrainingLLM reasoning → Multimodal reasoning +1
Brain-Inspired Continual Learning-Robust Feature Distillation and Re-Consolidation for Class Incremental LearningKnowledge distillation → Distillation for continual learning
UVMap-ID: A Controllable and Personalized UV Map Generative ModelDiffusion models → Image generation, text-to-image and editing
Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPsDeep reinforcement learning methods → Deep RL algorithms and representations
Align Your Steps: Optimizing Sampling Schedules in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
SnapKV: LLM Knows What You are Looking for Before GenerationEfficient LLM inference and serving → KV cache optimization
Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning
Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMsLLM safety and security → Jailbreaking
GeoDiffuser: Geometry-Based Image Editing with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
PARAMANU-GANITA: Can Small Math Language Models Rival with Large Language Models on Mathematical Reasoning?LLM reasoning → Mathematical reasoning
A Multimodal Automated Interpretability AgentLLM agents and tool use → Multimodal and embodied agents
Better Synthetic Data by Retrieving and Transforming Existing DatasetsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
X-Ray: A Sequential 3D Representation For GenerationDiffusion models → 3D, point cloud and scene generation
PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference LabelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic PerspectiveDiffusion models → Robustness, privacy and adversarial aspects
Does Your Neural Code Completion Model Use My Code? A Membership Inference ApproachLLM safety and security → Membership inference attacks
A Survey on Efficient Inference for Large Language ModelsEfficient LLM inference and serving → Serving systems and request scheduling
LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping RobotsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +2
Collaborative Filtering Based on Diffusion Models: Unveiling the Potential of High-Order ConnectivityDiffusion models → Diffusion recommenders
Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research TrajectoriesDeep reinforcement learning methods → RL for energy, networks and operations
Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI FeedbackMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
FLDM-VTON: Faithful Latent Diffusion Model for Virtual Try-onDiffusion models → 3D, point cloud and scene generation
Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and DiffusionDiffusion models → Diffusion foundations and sampling
Generative Artificial Intelligence Assisted Wireless Sensing: Human Flow Detection in Practical Communication EnvironmentsDiffusion models → Diffusion for compression and wireless
CKD: Contrastive Knowledge Distillation from A Sample-wise PerspectiveKnowledge distillation → General knowledge distillation methods
Mechanistic Interpretability for AI Safety -- A ReviewMechanistic interpretability → Circuits and mechanistic analysis
Research on Robot Path Planning Based on Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
Multi-view Disentanglement for Reinforcement Learning with Multiple CamerasDeep reinforcement learning methods → RL for robot locomotion and manipulation
FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated LearningKnowledge distillation → Graph neural network distillation
An empirical study of LLaMA3 quantization: from LLMs to MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation NetworksKnowledge distillation → Detection and dense prediction distillation
A Multimodal Feature Distillation with Mamba-Transformer Network for Brain Tumor Segmentation with Incomplete ModalitiesState-space sequence models (S4, Mamba) → Mamba for medical image analysis +1
Infusion: Preventing Customized Text-to-Image Diffusion from OverfittingDiffusion models → Image generation, text-to-image and editing
Information Re-Organization Improves Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
RHanDS: Refining Malformed Hands for Generated Images with Decoupled Structure and Style GuidanceDiffusion models → Diffusion and flow policies for robotics
Protecting Your LLMs with Information BottleneckLLM safety and security → Jailbreaking
Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level PerturbationsRetrieval-augmented generation → Privacy and security of RAG
Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question AnsweringMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D AssetsDiffusion models → 3D, point cloud and scene generation
Accelerating Image Generation with Sub-path Linear Approximation ModelDiffusion models → Diffusion foundations and sampling
Towards Better Text-to-Image Generation Alignment via Attention ModulationDiffusion models → Image generation, text-to-image and editing
Retrieval-Augmented Audio Deepfake DetectionRetrieval-augmented generation → Conversational and speech RAG
MambaUIE&SR: Unraveling the Ocean's Secrets with Only 2.8 GFLOPsState-space sequence models (S4, Mamba) → Mamba for image restoration
Lipschitz-Regularized Critics Lead to Policy Robustness Against Transition Dynamics UncertaintyDeep reinforcement learning methods → RL theory and sample complexity
VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense ReasoningLLM reasoning → Multimodal reasoning
Filtered Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
ReCAP: Recursive Cross Attention Network for Pseudo-Label Generation in Robotic Surgical Skill Assessment
In the Shadow of Smith`s Invisible Hand: Risks to Economic Stability and Social Wellbeing in the Age of Intelligence
U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI
Less Peaky and More Accurate CTC Forced Alignment by Label Priors
PhyPlan: Generalizable and Rapid Physical Task Planning with Physics Informed Skill Networks for Robot Manipulators
Unraveling the Autism spectrum heterogeneity: Insights from ABIDE I Database using data/model-driven permutation testing approaches
Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing
Distributed Learning for Wi-Fi AP Load Prediction
Combined Compromise for Ideal Solution (CoCoFISo): a multi-criteria decision-making based on the CoCoSo method algorithm
CNN-Based Equalization for Communications: Achieving Gigabit Throughput with a Flexible FPGA Hardware Architecture
A Survey on the Real Power of ChatGPT
Rapid Deployment of DNNs for Edge Computing via Structured Pruning at Initialization
AdaQAT: Adaptive Bit-Width Quantization-Aware Training
Pixels and Predictions: Potential of GPT-4V in Meteorological Imagery Analysis and Forecast Communication
FASTTRACK: Fast and Accurate Fact Tracing for LLMs
MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making
Do not think about pink elephant!
Performance Characterization of Expert Router for Scalable LLM Inference
Fairness Incentives in Response to Unfair Dynamic Pricing
OpenELM: An Efficient Language Model Family with Open Training and Inference Framework
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning
Cross-Task Multi-Branch Vision Transformer for Facial Expression and Mask Wearing Classification
Adaptive Bayesian Optimization for High-Precision Motion Systems
Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decoding
Latency-Distortion Tradeoffs in Communicating Classification Results over Noisy Channels
The Adversarial AI-Art: Understanding, Generation, Detection, and Benchmarking
Designing forecasting software for forecast users: Empowering non-experts to create and understand their own forecasts
WangLab at MEDIQA-M3G 2024: Multimodal Medical Answer Generation using Large Language Models
"Where am I?" Scene Retrieval with Language
Adaptive Local Binary Pattern: A Novel Feature Descriptor for Enhanced Analysis of Kidney Abnormalities in CT Scan Images using ensemble based Machine Learning Approach
Learning S-Matrix Phases with Neural Operators
Integrating Disambiguation and User Preferences into Large Language Models for Robot Motion Planning
WangLab at MEDIQA-CORR 2024: Optimized LLM-based Programs for Medical Error Detection and Correction
UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement
SwinFuSR: an image fusion-inspired model for RGB-guided thermal image super-resolution
M'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity
Edge-Assisted ML-Aided Uncertainty-Aware Vehicle Collision Avoidance at Urban Intersections
Mapping Wireless Networks into Digital Reality through Joint Vertical and Horizontal Learning
Narrative Action Evaluation with Prompt-Guided Multimodal Interaction
Integrating Chemistry Knowledge in Large Language Models via Prompt Engineering
Benchmarking Advanced Text Anonymisation Methods: A Comparative Study on Novel and Traditional Approaches
DAIC-WOZ: On the Validity of Using the Therapist's prompts in Automatic Depression Detection from Clinical Interviews
Towards smaller, faster decoder-only transformers: Architectural variants and their implications

All 252