Papers

New on arXiv

Thu 4 Jul 2024

254 papers

Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait ModelingSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
metabench -- A Sparse Benchmark of Reasoning and Knowledge in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
Purification Of Contaminated Convolutional Neural Networks Via Robust Recovery: An Approach with Theoretical Guarantee in One-Hidden-Layer CaseLLM safety and security → Backdoor and data poisoning attacks
CaseGPT: a case reasoning framework based on language models and retrieval-augmented generationLLM reasoning → Clinical and biomedical applications +1
HAF-RM: A Hybrid Alignment Framework for Reward Model TrainingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
QueryMamba: A Mamba-Based Encoder-Decoder Architecture with a Statistical Verb-Noun Interaction Module for Video Action Forecasting @ Ego4D Long-Term Action Anticipation Challenge 2024State-space sequence models (S4, Mamba) → Core SSM architectures for language
Orchestrating LLMs with Different PersonalizationsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Defense Against Syntactic Textual Backdoor Attacks with Token SubstitutionLLM safety and security → Backdoor and data poisoning attacks
Mixture of A Million ExpertsMixture-of-experts → Expert routing strategies
Securing Multi-turn Conversational Language Models From Distributed Backdoor TriggersLLM safety and security → Backdoor and data poisoning attacks
Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMsLLM safety and security → Backdoor and data poisoning attacks
Advances in Diffusion Models for Image Data Augmentation: A Review of Methods, Models, Evaluation Metrics and Future Research DirectionsDiffusion models → Image generation, text-to-image and editing
DotaMath: Decomposition of Thought with Code Assistance and Self-correction for Mathematical ReasoningLLM reasoning → Mathematical reasoning
Collision Avoidance for Multiple UAVs in Unknown Scenarios with Causal Representation DisentanglementDeep reinforcement learning methods → RL for robot navigation and UAV control
Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous SystemsEfficient LLM inference and serving → Serving systems and request scheduling
Fully Fine-tuned CLIP Models are Efficient Few-Shot LearnersMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
ROER: Regularized Optimal Experience ReplayDeep reinforcement learning methods → Deep RL algorithms and representations
Leveraging Latent Diffusion Models for Training-Free In-Distribution Data Augmentation for Surface Defect DetectionDiffusion models → Flow matching, time series and science
Solving Zebra Puzzles Using Constraint-Guided Multi-Agent SystemsLLM reasoning → Reasoning benchmarks and evaluation +1
Meta-prompting Optimized Retrieval-augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Uncertainty-Guided Likelihood Tree SearchLLM reasoning → Test-time compute and efficient thinking
Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic DataSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
Timestep-Aware Correction for Quantized Diffusion ModelsDiffusion models → Diffusion foundations and sampling
MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile DevicesLLM agents and tool use → GUI and mobile agents
Continuous-time q-Learning for Jump-Diffusion Models under Tsallis EntropyDeep reinforcement learning methods → RL theory and sample complexity
ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Automated Progressive Red TeamingLLM safety and security → Prompt injection and agent security
Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting MitigationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
M5 -- A Diverse Benchmark to Assess the Performance of Large Multimodal Models Across Multilingual and Multicultural Vision-Language TasksMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
From Data to Commonsense Reasoning: The Use of Large Language Models for Explainable AILLM reasoning → Reasoning benchmarks and evaluation
Relative Difficulty Distillation for Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
STOC-TOT: Stochastic Tree-of-Thought with Constrained Decoding for Complex Reasoning in Multi-Hop Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning
Improving Self Consistency in LLMs through Probabilistic TokenizationLLM reasoning → Test-time compute and efficient thinking
A Survey of Data Synthesis ApproachesSynthetic data and self-improvement for LLMs → LLM synthetic data generation
High Fidelity Text-Guided Music Editing via Single-Stage Flow MatchingDiffusion models → Audio, speech and music
QET: Enhancing Quantized LLM Parameters and KV cache Compression through Element Substitution and Residual ClusteringEfficient LLM inference and serving → KV cache quantization
Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image RestorationDiffusion models → Inverse problems and image restoration
SSP-IR: Semantic and Structure Priors for Diffusion-based Realistic Image RestorationDiffusion models → Inverse problems and image restoration
SOWA: Adapting Hierarchical Frozen Window Self-Attention to Visual-Language Models for Better Anomaly DetectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
Question-Analysis Prompting Improves LLM Performance in Reasoning TasksLLM reasoning → Prompting and chain-of-thought reasoning
Modality-Specialized Synergizers for Interleaved Vision-Language GeneralistsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
FDS: Feedback-guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain GeneralizationDiffusion models → Diffusion foundations and sampling
Vision Mamba for Classification of Breast Ultrasound ImagesState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Unveiling Scoring Processes: Dissecting the Differences between LLMs and Human Graders in Automatic Scoring
Classification-Based Automatic HDL Code Generation Using LLMs
AI in Remote Patient Monitoring
Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry
Robust Adaptation of Foundation Models with Black-Box Visual Prompting
The Price of Prompting: Profiling Energy Use in Large Language Models Inference
BSH for Collision Detection in Point Cloud models
Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mapping
NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptions
MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production
Black-box Model Ensembling for Textual and Visual Question Answering via Information Fusion
Historical Ink: 19th Century Latin American Spanish Newspaper Corpus with LLM OCR Correction
Bridging Data Gaps in Healthcare: A Scoping Review of Transfer Learning in Biomedical Data Analysis
Hadamard Adapter: An Extreme Parameter-Efficient Adapter Tuning Method for Pre-trained Language Models
Mechanisms for Data Sharing in Collaborative Causal Inference (Extended Version)
Psychology of Artificial Intelligence: Epistemological Markers of the Cognitive Analysis of Neural Networks
Digital twin with automatic disturbance detection for real-time optimization of a semi-autogenous grinding (SAG) mill
Bias Correction in Machine Learning-based Classification of Rare Events
A Survey of Controllable Learning: Methods and Applications in Information Retrieval
Meta-Learning and representation learner: A short theoretical note
Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms
Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing
Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs
ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild
Attention Normalization Impacts Cardinality Generalization in Slot Attention
Solutions to Deepfakes: Can Camera Hardware, Cryptography, and Deep Learning Verify Real Images?
Learning Interpretable Differentiable Logic Networks
ELCC: the Emergent Language Corpus Collection
Finite Operator Learning: Bridging Neural Operators and Numerical Methods for Efficient Parametric Solution and Optimization of PDEs
VoxAct-B: Voxel-Based Acting and Stabilizing Policy for Bimanual Manipulation
SineKAN: Kolmogorov-Arnold Networks Using Sinusoidal Activation Functions
Towards Automating Text Annotation: A Case Study on Semantic Proximity Annotation using GPT-4
Biometric Authentication Based on Enhanced Remote Photoplethysmography Signal Morphology
Query-Guided Self-Supervised Summarization of Nursing Notes
Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models
An Autoencoder Architecture for L-band Passive Microwave Retrieval of Landscape Freeze-Thaw Cycle
MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization
Predictive Coding Networks and Inference Learning: Tutorial and Survey
MiniGPT-Med: Large Language Model as a General Interface for Radiology Diagnosis
Can Pre-trained Language Models Understand Chinese Humor?
Network-based Neighborhood regression
C3DG: Conditional Domain Generalization for Hyperspectral Imagery Classification with Convergence and Constrained-risk Theories
Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations
Learning to Be a Transformer to Pinpoint Anomalies
Artificial Intelligence and Algorithmic Price Collusion in Two-sided Markets
Advanced Artificial Intelligence Strategy for Optimizing Urban Rail Network Design using Nature-Inspired Algorithms
Certifiably Robust Image Watermark
FIPGNet:Pyramid grafting network with feature interaction strategies
AXOLOTL'24 Shared Task on Multilingual Explainable Semantic Change Modeling
Sparsest Models Elude Pruning: An Expos'e of Pruning's Current Capabilities
Behavioural gap assessment of human-vehicle interaction in real and virtual reality-based scenarios in autonomous driving
A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations
CLIP-DR: Textual Knowledge-Guided Diabetic Retinopathy Grading with Ranking-aware Prompting
Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLM
E2MPL:An Enduring and Efficient Meta Prompt Learning Framework for Few-shot Unsupervised Domain Adaptation

All 254