Papers

New on arXiv

Mon 1 Jul 2024

342 papers

A Comprehensive Survey on Diffusion Models and Their ApplicationsDiffusion models → Diffusion foundations and sampling
The Need for Guardrails with Large Language Models in Medical Safety-Critical Settings: An Artificial Intelligence Application in the Pharmacovigilance EcosystemLLM safety and security → Safety alignment, refusal and guardrails
AutoFlow: Automated Workflow Generation for Large Language Model AgentsLLM agents and tool use → Software engineering coding agents
PQCache: Product Quantization-based KVCache for Long Context LLM InferenceEfficient LLM inference and serving → KV cache quantization
Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the EdgeEfficient LLM inference and serving → Token pruning and merging for ViTs
Image-to-Text Logic Jailbreak: Your Imagination can Help You Do AnythingLLM safety and security → Vision-language and text-to-image safety
Meerkat: Audio-Visual Large Language Model for Grounding in Space and TimeMultimodal LLMs / vision-language models → Video understanding with MLLMs
Purple-teaming LLMs with Adversarial Defender TrainingLLM safety and security → Prompt injection and agent security
To Switch or Not to Switch? Balanced Policy Switching in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
Equivariant Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics
Normalization and effective learning rates in reinforcement learningDeep reinforcement learning methods → Deep RL algorithms and representations
Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Label-free Neural Semantic Image SynthesisDiffusion models → Image generation, text-to-image and editing
DiscoveryBench: Towards Data-Driven Discovery with Large Language ModelsLLM agents and tool use → Web, search, and research agents
Weight Clipping for Deep Continual and Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
A Deep Reinforcement Learning Approach to Battery Management in Dairy Farming via Proximal Policy OptimizationDeep reinforcement learning methods → RL for energy, networks and operations
Aligning Target-Aware Molecule Diffusion Models with Exact Energy OptimizationDiffusion models → Flow matching, time series and science
Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot LearningDiffusion models → Diffusion and flow policies for robotics +1
xLSTM-UNet can be an Effective 2D & 3D Medical Image Segmentation Backbone with Vision-LSTM (ViL) better than its Mamba CounterpartState-space sequence models (S4, Mamba) → Mamba for medical image analysis
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable ApproachesEfficient LLM inference and serving → KV cache optimization
ScanReason: Empowering 3D Visual Grounding with Reasoning CapabilitiesLLM reasoning → Spatial and embodied reasoning
Improving Diffusion Inverse Problem Solving with Decoupled Noise AnnealingDiffusion models → Inverse problems and image restoration
DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration ModelsDiffusion models → Inverse problems and image restoration
Open-TeleVision: Teleoperation with Immersive Active Visual FeedbackOffline RL and imitation learning from data → Robot manipulation imitation learning
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Agentless: Demystifying LLM-based Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient LearningDiffusion models → Diffusion and flow policies for robotics +1
Tree Search for Language Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
DogeRM: Equipping Reward Models with Domain Knowledge through Model MergingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Retrieval-augmented generation in multilingual settingsRetrieval-augmented generation → RAG pipeline design and evaluation
Enhancing the Capability and Robustness of Large Language Models through Reinforcement Learning-Driven Query RefinementLLM safety and security → Jailbreaking
Contractual Reinforcement Learning: Pulling Arms with Invisible HandsDeep reinforcement learning methods → RL theory and sample complexity
Reinforcement Learning-driven Data-intensive Workflow Scheduling for Volunteer Edge-CloudDeep reinforcement learning methods → RL for energy, networks and operations
FORA: Fast-Forward Caching in Diffusion Transformer AccelerationDiffusion models → Diffusion foundations and sampling
Optimization of Retrieval-Augmented Generation Context with Outlier DetectionRetrieval-augmented generation → RAG robustness and adaptive retrieval
GalLoP: Learning Global and Local Prompts for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Diffusion Forcing: Next-token Prediction Meets Full-Sequence DiffusionDiffusion models → Diffusion foundations and sampling
Badllama 3: removing safety finetuning from Llama 3 in minutesLLM safety and security → Jailbreaking
Summary of a Haystack: A Challenge to Long-Context LLMs and RAG SystemsRetrieval-augmented generation → RAG pipeline design and evaluation
Coordination Failure in Cooperative Offline MARLOffline RL and imitation learning from data → Offline multi-agent RL
Deep Reinforcement Learning for Adverse Garage Scenario GenerationDeep reinforcement learning methods → RL for autonomous driving and traffic
AdaDistill: Adaptive Knowledge Distillation for Deep Face RecognitionKnowledge distillation → General knowledge distillation methods
Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Action SpacesOffline RL and imitation learning from data → Decision transformers and sequence modeling
Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of ExplainabilityLLM safety and security → Membership inference attacks
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?LLM reasoning → Multimodal reasoning +1
uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data RegimesKnowledge distillation → General knowledge distillation methods
QUEEN: Query Unlearning against Model ExtractionLLM safety and security → Machine unlearning
MIRAI: Evaluating LLM Agents for Event ForecastingLLM agents and tool use → Financial trading and forecasting agents
Searching for Best Practices in Retrieval-Augmented GenerationRetrieval-augmented generation → Multimodal RAG
Let Hybrid A* Path Planner Obey Traffic Rules: A Deep Reinforcement Learning-Based Planning FrameworkDeep reinforcement learning methods → RL for autonomous driving and traffic
EconNLI: Evaluating Large Language Models on Economics ReasoningLLM reasoning → Reasoning for agents, planning and code
Memory3: Language Modeling with Explicit MemoryRetrieval-augmented generation → Generation and context integration
Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression ComprehensionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translationMixture-of-experts → MoE large language models
Semantic-guided Adversarial Diffusion Model for Self-supervised Shadow RemovalDiffusion models → 3D, point cloud and scene generation
BERGEN: A Benchmarking Library for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script GenerationLLM agents and tool use → Multimodal and embodied agents
CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding EvaluationMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Face4RAG: Factual Consistency Evaluation for Retrieval Augmented Generation in ChineseRetrieval-augmented generation → RAG robustness and adaptive retrieval
On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)Diffusion models → Diffusion foundations and sampling
Human-like object concept representations emerge naturally in multimodal large language modelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Evolutionary Morphology Towards Overconstrained Locomotion via Large-Scale, Multi-Terrain Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
FRoG: Evaluating Fuzzy Reasoning of Generalized Quantifiers in Large Language ModelsLLM reasoning → Mathematical reasoning
Blind Inversion using Latent Diffusion PriorsDiffusion models → Inverse problems and image restoration
An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted ObservationsDiffusion models → Inverse problems and image restoration
DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
Data on the Move: Traffic-Oriented Data Trading Platform Powered by AI Agent with Common SenseLLM agents and tool use → Financial trading and forecasting agents
Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile AgentsLLM agents and tool use → GUI and mobile agents
Deep learning for automated detection of breast cancer in deep ultraviolet fluorescence images with diffusion probabilistic modelDiffusion models → Medical imaging and segmentation
Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous DrivingWorld models → World models for autonomous driving +1
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference CostsMixture-of-experts → MoE large language models
Diffusion Transformer Model With Compact Prior for Low-dose PET ReconstructionDiffusion models → Medical imaging and segmentation
ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification QuestionsLLM agents and tool use → Web, search, and research agents
MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in EducationLLM reasoning → Reasoning benchmarks and evaluation
Learning Robust 3D Representation from CLIP via Dual DenoisingMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
From Next-Token to Mathematics: The Learning Dynamics of Mathematical Reasoning in Language ModelsLLM reasoning → Mathematical reasoning
Residual-MPPI: Online Policy Customization for Continuous ControlOffline RL and imitation learning from data → Imitation and offline RL for driving +1
Non-Prehensile Aerial Manipulation using Model-Based Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
Efficient Automated Circuit Discovery in Transformers using Contextual DecompositionMechanistic interpretability → Circuits and mechanistic analysis
Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak AttacksLLM safety and security → Jailbreaking
Silver Linings in the Shadows: Harnessing Membership Inference for Machine UnlearningLLM safety and security → Machine unlearning
The #Somos600M Project: Generating NLP resources that represent the diversity of the languages from LATAM, the Caribbean, and Spain
LLM4PM: A case study on using Large Language Models for Process Modeling in Enterprise Organizations
Toward Automated Detection of Biased Social Signals from the Content of Clinical Conversations
Accelerate Intermittent Deep Inference
Assessing the Potential of PlanetScope Satellite Imagery to Estimate Particulate Matter Oxidative Potential
DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphones
I've Got 99 Problems But FLOPS Ain't One
Comprehensive Performance Evaluation of YOLOv12, YOLO11, YOLOv10, YOLOv9 and YOLOv8 on Detecting and Counting Fruitlet in Complex Orchard Environments
ICAGC 2024: Inspirational and Convincing Audio Generation Challenge 2024
Exploring Advanced Large Language Models with LLMsuite
Reporting Risks in AI-based Assistive Technology Research: A Systematic Review
PCAPVision: PCAP-Based High-Velocity and Large-Volume Network Failure Detection
Integrating Deep Learning in Cardiology: A Comprehensive Review of Atrial Fibrillation, Left Atrial Scar Segmentation, and the Frontiers of State-of-the-Art Techniques
The Impact of an XAI-Augmented Approach on Binary Classification with Scarce Data
Chronological Analysis of Rigvedic Mandalas using Social Networks

All 342