Papers

New on arXiv

Mon 8 Apr 2024

251 papers

Computing Transition Pathways for the Study of Rare Events Using Deep Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
WILBUR: Adaptive In-Context Learning for Robust and Accurate Web AgentsLLM agents and tool use → Web, search, and research agents
Learning Heuristics for Transit Network Design and Improvement with Deep Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful KnowledgeLLM safety and security → Jailbreaking
CodecLM: Aligning Language Models with Tailored Synthetic DataLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
Negative Preference Optimization: From Catastrophic Collapse to Effective UnlearningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
IA2: Leveraging Instance-Aware Index Advisor with Reinforcement Learning for Diverse WorkloadsDeep reinforcement learning methods → RL training of language and agent models
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Evaluating Mathematical Reasoning Beyond AccuracyLLM reasoning → Mathematical reasoning
Retrieval-Augmented Open-Vocabulary Object DetectionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
MoMA: Multimodal LLM Adapter for Fast Personalized Image GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
CoReS: Orchestrating the Dance of Reasoning and SegmentationLLM reasoning → Multimodal reasoning
NAF-DPM: A Nonlinear Activation-Free Diffusion Probabilistic Model for Document EnhancementDiffusion models → Image generation, text-to-image and editing
YaART: Yet Another ART Rendering TechnologyDiffusion models → Diffusion and flow policies for robotics
BinaryDM: Accurate Weight Binarization for Efficient Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion ModelDiffusion models → Diffusion foundations and sampling
Learning a Category-level Object Pose Estimator without Pose AnnotationsDiffusion models → 3D, point cloud and scene generation
MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language PruningMultimodal LLMs / vision-language models → Visual token pruning and efficiency
MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without RetrainingDiffusion models → Robustness, privacy and adversarial aspects +1
SpeechAlign: Aligning Speech Generation to Human PreferencesLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
UniFL: Improve Latent Diffusion Model via Unified Feedback LearningDiffusion models → Diffusion foundations and sampling
MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question AnsweringRetrieval-augmented generation → Medical and biomedical RAG
360^circREA: Towards A Reusable Experience Accumulation with 360deg Assessment for Multi-Agent SystemLLM agents and tool use → General LLM agent frameworks and benchmarks
Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language ModelsLLM reasoning → Test-time compute and efficient thinking +1
Evaluating Interventional Reasoning Capabilities of Large Language ModelsLLM reasoning → Causal reasoning in LLMs
Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference DataLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
Investigating the Effectiveness of Cross-Attention to Unlock Zero-Shot Editing of Text-to-Video Diffusion ModelsDiffusion models → Video generation
Taming Transformers for Realistic Lidar Point Cloud GenerationWorld models → World modeling from LiDAR generation +1
HAMMR: HierArchical MultiModal React agents for generic VQALLM agents and tool use → Multimodal and embodied agents
Residual Chain Prediction for Autonomous Driving Path PlanningEnd-to-end autonomous driving → End-to-end system architecture
SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model SafetyLLM safety and security → Safety alignment, refusal and guardrails
Rethinking the Spatial Inconsistency in Classifier-Free Diffusion GuidanceDiffusion models → Diffusion foundations and sampling
CNN-based Game State Detection for a Foosball TableDeep reinforcement learning methods → RL for games and combinatorial optimization
Towards Objectively Benchmarking Social Intelligence for Language Agents at Action LevelLLM agents and tool use → General LLM agent frameworks and benchmarks
Mask-ControlNet: Higher-Quality Image Generation with An Additional Mask PromptDiffusion models → Image generation, text-to-image and editing
Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model SecurityMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
StyleForge: Enhancing Text-to-Image Synthesis for Any Artistic Styles with Dual BindingDiffusion models → Image generation, text-to-image and editing
SAFE-GIL: SAFEty Guided Imitation Learning for Robotic SystemsOffline RL and imitation learning from data → Safe offline RL
LayoutLLM: Layout Instruction Tuning with Large Language Models for Document UnderstandingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language ModelsWorld models → World models for language agents +1
DiffCJK: Conditional Diffusion Model for High-Quality and Wide-coverage CJK Character GenerationDiffusion models → Image generation, text-to-image and editing
MeSA-DRL: Memory-Enhanced Deep Reinforcement Learning for Advanced Socially Aware Robot Navigation in Crowded EnvironmentsDeep reinforcement learning methods → RL for robot navigation and UAV control
Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model MergingLLM safety and security → Watermarking generated content and models
Enabling Privacy-Preserving Cyber Threat Detection with Federated LearningLLM safety and security → Federated unlearning and poisoning
GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts
Transductive Zero-Shot and Few-Shot CLIP
Foundation Models for Education: Promises and Prospects
A unified cross-attention model for predicting antigen binding specificity to both HLA and TCR molecules
From "AI" to Probabilistic Automation: How Does Anthropomorphization of Technical Systems Descriptions Influence Trust?
EB-GAME: A Game-Changer in ECG Heartbeat Anomaly Detection
Clinical translation of machine learning algorithms for seizure detection in scalp electroencephalography: systematic review
Variational Bayesian Optimal Experimental Design with Normalizing Flows
Neural Sequence-to-Sequence Modeling with Attention by Leveraging Deep Learning Architectures for Enhanced Contextual Understanding in Abstractive Text Summarization
Is English the New Programming Language? How About Pseudo-code Engineering?
Text clustering applied to data augmentation in legal contexts
EFSA: Towards Event-Level Financial Sentiment Analysis
Automating Research Synthesis with Domain-Specific Large Language Model Fine-Tuning
ApproxDARTS: Differentiable Neural Architecture Search with Approximate Multipliers
Xiwu: A Basis Flexible and Learnable LLM for High Energy Physics
Lightweight Deep Learning for Resource-Constrained Environments: A Survey
Interpretability in Symbolic Regression: a benchmark of Explanatory Methods using the Feynman data set
The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models
Natural Learning
Inexact Simplification of Symbolic Regression Expressions with Locality-sensitive Hashing
Use of a Structured Knowledge Base Enhances Metadata Curation by Large Language Models
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
Condition Monitoring with Incomplete Data: An Integrated Variational Autoencoder and Distance Metric Framework
Rapid and Precise Topological Comparison with Merge Tree Neural Networks
TabConv: Low-Computation CNN Inference via Table Lookups
GeniL: A Multilingual Dataset on Generalizing Language
Towards Improved Semiconductor Defect Inspection for high-NA EUVL based on SEMI-SuperYOLO-NAS
A Neuromorphic Approach to Obstacle Avoidance in Robot Manipulation
Localizing Moments of Actions in Untrimmed Videos of Infants with Autism Spectrum Disorder
Softmax Attention with Constant Cost per Token
Attention-Driven Multi-Agent Reinforcement Learning: Enhancing Decisions with Expertise-Informed Tasks
'UFAL LatinPipe at EvaLatin 2024: Morphosyntactic Analysis of Latin
Parameter-Adaptive Approximate MPC: Tuning Neural-Network Controllers without Retraining
SambaLingo: Teaching Large Language Models New Languages
Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning
LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding
Quantum Adversarial Learning for Kernel Methods
Just Wing It: Near-Optimal Estimation of Missing Mass in a Markovian Sequence
Label Propagation for Physics-Informed Neural Networks and Physics-Informed Gaussian Processes
Centrality Estimators for Probability Density Functions
Towards Explainable Automated Neuroanatomy
Self-Labeling in Multivariate Causality and Quantification for Adaptive Machine Learning
BatSort: Enhanced Battery Classification with Transfer Learning for Battery Sorting and Recycling
A Survey on Responsible Generative AI: What to Generate and What Not
Dynamical stability and chaos in artificial neural network trajectories along training
Group-specific discriminant analysis reveals statistically validated sex differences in lateralization of brain functional network
Data Readiness for AI: A 360-Degree Survey
Forecasting Electric Vehicle Battery Output Voltage: A Predictive Modeling Approach
STMGF: An Effective Spatial-Temporal Multi-Granularity Framework for Traffic Forecasting
Finding Visual Task Vectors
An Empirical Study of μP Learning Rate Transfer
Predicting Overtakes in Trucks Using CAN Data
Language-Independent Representations Improve Zero-Shot Summarization
SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing
Learning 3D-Aware GANs from Unposed Images with Template Feature Field

All 251