Papers

New on arXiv

Sun 6 Apr 2025

130 papers

Show Me How: Benefits and Challenges of Agent-Augmented Counterfactual Explanations for Non-Expert UsersLLM agents and tool use → Medical and scientific domain agents
ArXivBench: When You Should Avoid Using ChatGPT for Academic WritingLLM reasoning → Reasoning benchmarks and evaluation
ZeroED: Hybrid Zero-shot Error Detection through Large Language Model ReasoningLLM reasoning → Mathematical reasoning
A Novel Algorithm for Personalized Federated Learning: Knowledge Distillation with Weighted Combination LossKnowledge distillation → Federated, robust and private distillation
M2IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation EngineeringMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Exact Unlearning of Finetuning Data via Model Merging at ScaleLLM safety and security → Machine unlearning
AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretabilityWorld models → World models for language agents
Diffusion-Based Approximate MPC: Fast and Consistent Imitation of Multi-Modal Action DistributionsDiffusion models → Diffusion and flow policies for robotics +1
Your Image Generator Is Your New Private DatasetDiffusion models → Robustness, privacy and adversarial aspects +1
Advancing Egocentric Video Question Answering with Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
The Point, the Vision and the Text: Does Point Cloud Boost Spatial Reasoning of Large Language Models? A Bias-Controlled StudyLLM reasoning → Spatial and embodied reasoning
BrainMRDiff: A Diffusion Model for Anatomically Consistent Brain MRI SynthesisDiffusion models → Medical imaging and segmentation
Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoningLLM reasoning → Reinforcement learning for reasoning +1
GAMBAS: Generalised-Hilbert Mamba for Super-resolution of Paediatric Ultra-Low-Field MRIState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Saliency-driven Dynamic Token Pruning for Large Language ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
Attributed Synthetic Data Generation for Zero-shot Domain-specific Image ClassificationSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
Building LLM Agents by Incorporating Insights from Computer SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
VideoAgent2: Enhancing the LLM-Based Agent System for Long-Form Video Understanding by Uncertainty-Aware CoTLLM agents and tool use → Multimodal and embodied agents
AI2STOW: End-to-End Deep Reinforcement Learning to Construct Master Stowage Plans under Demand UncertaintyDeep reinforcement learning methods → RL for robot navigation and UAV control
On the Spatial Structure of Mixture-of-Experts in TransformersMixture-of-experts → Expert routing strategies
Driving-RAG: Driving Scenarios Embedding, Search, and RAG ApplicationsRetrieval-augmented generation → Multimodal RAG +1
Human-Level Competitive Pok'emon via Scalable Offline Reinforcement Learning with TransformersOffline RL and imitation learning from data → Imitation learning methods
Retro-Search: Exploring Untaken Paths for Deeper and Efficient ReasoningLLM reasoning → Test-time compute and efficient thinking
Solving Sokoban using Hierarchical Reinforcement Learning with LandmarksDeep reinforcement learning methods → Deep RL algorithms and representations
AutoPDL: Automatic Prompt Optimization for LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
DDPT: Diffusion-Driven Prompt Tuning for Large Language Model Code GenerationDiffusion models → Discrete and text diffusion
OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual ReasoningWorld models → World models for autonomous driving +3
Pruning Laws for Large Language ModelsMixture-of-experts → MoE large language models
Data Scaling Laws for End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
Economic Battery Storage Dispatch with Deep Reinforcement Learning from Rule-Based DemonstrationsDeep reinforcement learning methods → RL for energy, networks and operations
CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
Multimodal Cinematic Video Synthesis Using Text-to-Image and Audio Generation Models
Efficient Portfolio Selection through Preference Aggregation with Quicksort and the Bradley--Terry Model
Exploring Generative AI Techniques in Government: A Case Study
AdaptRec: A Self-Adaptive Framework for Sequential Recommendations with Large Language Models
Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases
SolRPDS: A Dataset for Analyzing Rug Pulls in Solana Decentralized Finance
Embedding Reliability Verification Constraints into Generation Expansion Planning
Non-linear Phillips Curve for India: Evidence from Explainable Machine Learning
Hyperflux: Pruning Reveals Importance
Structuring Multiple Simple Cycle Reservoirs with Particle Swarm Optimization
Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression
Divergent Paths: Separating Homophilic and Heterophilic Learning for Enhanced Graph-level Representations
AROMA: Autonomous Rank-one Matrix Adaptation
MASS: MoErging through Adaptive Subspace Selection
Three-Factor Learning in Spiking Neural Networks: An Overview of Methods and Trends from a Machine Learning Perspective
Here Comes the Explanation: A Shapley Perspective on Multi-contrast Medical Image Segmentation
Splits! Flexible Sociocultural Linguistic Investigation at Scale
Ineffectiveness for Search and Undecidability of PCSP Meta-Problems
Steering off Course: Reliability Challenges in Steering Language Models
Walk Before You Dance: High-fidelity and Editable Dance Synthesis via Generative Masked Motion Prior
Systematic Literature Review on Vehicular Collaborative Perception -- A Computer Vision Perspective
DynClean: Training Dynamics-based Label Cleaning for Distantly-Supervised Named Entity Recognition
SiameseDuo++: Active Learning from Data Streams with Dual Augmented Siamese Networks
Tool-as-Interface: Learning Robot Policies from Observing Human Tool Use
Scalable Approximate Algorithms for Optimal Transport Linear Models
Capturing AI's Attention: Physics of Repetition, Hallucination, Bias and Beyond
Targetless LiDAR-Camera Calibration with Neural Gaussian Splatting
SECQUE: A Benchmark for Evaluating Real-World Financial Analysis Capabilities
"Trust me on this" Explaining Agent Behavior to a Human Terminator
Modeling of AUV Dynamics with Limited Resources: Efficient Online Learning Using Uncertainty
From Continual Learning to SGD and Back: Better Rates for Continual Linear Models
Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification
Cramer-Rao Bounds for Laplacian Matrix Estimation
Multimodal Lengthy Videos Retrieval Framework and Evaluation Metric
KnowsLM: A framework for evaluation of small language models for knowledge augmentation and humanised conversations
Estimating Coverage in Streams via a Modified CVM Method
DyCON: Dynamic Uncertainty-aware Consistency and Contrastive Learning for Semi-supervised Medical Image Segmentation
Planning Safety Trajectories with Dual-Phase, Physics-Informed, and Transportation Knowledge-Driven Large Language Models
Opening the black box of deep learning: Validating the statistical association between explainable artificial intelligence (XAI) and clinical domain knowledge in fundus image-based glaucoma diagnosis
SnapPix: Efficient-Coding--Inspired In-Sensor Compression for Edge Vision
An Empirical Comparison of Text Summarization: A Multi-Dimensional Evaluation of Large Language Models
A Consequentialist Critique of Binary Classification Evaluation: Theory, Practice, and Tools
Hessian of Perplexity for Large Language Models by PyTorch autograd (Open Source)
SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation
Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection
Active Learning with a Noisy Annotator
A Classification View on Meta Learning Bandits
AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection
Skin Color Measurement from Dermatoscopic Images: An Evaluation on a Synthetic Dataset
Learning Conditionally Independent Transformations using Normal Subgroups in Group Theory
Statistical Management of the False Discovery Rate in Medical Instance Segmentation Based on Conformal Risk Control
Fine Tuning a Simulation-Driven Estimator
Directed Graph-alignment Approach for Identification of Gaps in Short Answers
Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering
LoopGen: Training-Free Loopable Music Generation
Spatial-Geometry Enhanced 3D Dynamic Snake Convolutional Neural Network for Hyperspectral Image Classification
An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability
CALF: A Conditionally Adaptive Loss Function to Mitigate Class-Imbalanced Segmentation
VSLAM-LAB: A Comprehensive Framework for Visual SLAM Methods and Datasets
EclipseNETs: Learning Irregular Small Celestial Body Silhouettes
PRISM: Probabilistic Representation for Integrated Shape Modeling and Generation
Prot42: a Novel Family of Protein Language Models for Target-aware Protein Binder Generation
Thermoxels: a voxel-based method to generate simulation-ready 3D thermal models
Do We Need Responsible XR? Drawing on Responsible AI to Inform Ethical Research and Practice into XRAI / the Metaverse
Evaluation framework for Image Segmentation Algorithms
Foundational Requirements for Artificial General Intelligence: A Falsifiable Framework Based on Signal Prediction
Formula-Supervised Sound Event Detection: Pre-Training Without Real Data
FluentLip: A Phonemes-Based Two-stage Approach for Audio-Driven Lip Synthesis with Optical Flow Consistency
UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding

All 130