Papers

New on arXiv

Sat 29 Mar 2025

146 papers

A Framework for Lightweight Responsible Prompting RecommendationLLM safety and security → Safety alignment, refusal and guardrails
Delving into: the quantification of Ai-generated content on the internet (synthetic data)Synthetic data and self-improvement for LLMs → LLM synthetic data generation
Encrypted Prompt: Securing LLM Applications Against Unauthorized ActionsLLM safety and security → Prompt injection and agent security
Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of RelevanceSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Synthetic Art Generation and DeepFake Detection A Study on Jamini Roy Inspired DatasetDiffusion models → Image generation, text-to-image and editing
Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMsLLM reasoning → Audio-language model reasoning +1
AstroAgents: A Multi-Agent AI for Hypothesis Generation from Mass Spectrometry DataLLM agents and tool use → Web, search, and research agents
Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLLLM reasoning → Knowledge- and tool-augmented reasoning
CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program SynthesisLLM reasoning → Reasoning for agents, planning and code +1
EncGPT: A Multi-Agent Workflow for Dynamic Encryption AlgorithmsLLM agents and tool use → Agent threats, guardrails and governance
When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?LLM reasoning → Multimodal reasoning +1
RefChartQA: Grounding Visual Answer on Chart Images through Instruction TuningMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Can DeepSeek Reason Like a Surgeon? An Empirical Evaluation for Vision-Language Understanding in Robotic-Assisted SurgeryLLM reasoning → Clinical and biomedical applications
Evaluating Compositional Scene Understanding in Multimodal Generative ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Efficient Explicit Joint-level Interaction Modeling with Mamba for Text-guided HOI GenerationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
RL2Grid: Benchmarking Reinforcement Learning in Power Grid OperationsDeep reinforcement learning methods → RL for energy, networks and operations
MoLAE: Mixture of Latent Experts for Parameter-Efficient Language ModelsMixture-of-experts → MoE large language models
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single DirectionLLM reasoning → Reasoning benchmarks and evaluation
Efficient Inference for Large Reasoning Models: A SurveyLLM reasoning → Test-time compute and efficient thinking
VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
Shape and Texture Recognition in Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
VLM-C4L: Continual Core Dataset Learning with Corner Case Optimization via Vision-Language Models for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
Agentic Large Language Models, a surveyLLM agents and tool use → General LLM agent frameworks and benchmarks
FreeInv: Free Lunch for Improving DDIM InversionDiffusion models → Image generation, text-to-image and editing
Reproducibility Companion Paper: Making Users Indistinguishable: Attribute-wise Unlearning in Recommender SystemsLLM safety and security → Membership inference attacks
A Retrieval-Augmented Knowledge Mining Method with Deep Thinking LLMs for Biomedical Research and Clinical SupportLLM reasoning → Clinical and biomedical applications +1
MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTsDiffusion models → 3D, point cloud and scene generation
DAT: Dynamic Alpha Tuning for Hybrid Retrieval in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
S2MoE: Robust Sparse Mixture of Experts via Stochastic LearningMixture-of-experts → MoE large language models
Rethinking Sparse Mixture of Experts from a Unified PerspectiveMixture-of-experts → MoE theory and gating functions
FReM: A Flexible Reasoning Mechanism for Balancing Quick and Slow Thinking in Long-Context Question AnsweringLLM reasoning → Reasoning benchmarks and evaluation
From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3DMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video ContextsMultimodal LLMs / vision-language models → Video understanding with MLLMs
SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective UnlearningLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
Identifying Multi-modal Knowledge Neurons in Pretrained Transformers via Two-stage FilteringMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Factored Agents: Decoupling In-Context Learning and Memorization for Robust Tool UseLLM agents and tool use → General LLM agent frameworks and benchmarks
Predictive Traffic Rule Compliance using Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
LangVAE and LangSpace: Building and Probing for Language Model VAEs
Cooperative Speech, Semantic Competence, and AI
Diverse AI Personas Can Mitigate the Homogenization Effect in Human-AI Collaborative Ideation
MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation
TransNet: Transfer Knowledge for Few-shot Knowledge Graph Completion
Towards Symmetric Low-Rank Adapters
Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edge
RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm
Evaluating Large Language Models for Fair and Reliable Organ Allocation
Who Owns the Output? Bridging Law and Technology in LLMs Attribution
Estimating Unbounded Density Ratios: Applications in Error Control under Covariate Shift
Fair Sufficient Representation Learning
Skeletonization Quality Evaluation: Geometric Metrics for Point Cloud Analysis in Robotics
Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models
FIESTA: Fisher Information-based Efficient Selective Test-time Adaptation
Context in object detection: a systematic literature review
Simulation of Non-Ordinary Consciousness
Evaluating how LLM annotations represent diverse views on contentious topics
Beyond speculation: Measuring the growing presence of LLM-generated texts in multilingual disinformation
Geometry in Style: 3D Stylization via Surface Normal Deformation
UP-dROM : Uncertainty-Aware and Parametrised dynamic Reduced-Order Model, application to unsteady flows
Z-SASLM: Zero-Shot Style-Aligned SLI Blending Latent Manipulation
CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models
Citegeist: Automated Generation of Related Work Analysis on the arXiv Corpus
Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection
Unsupervised Learning: Comparative Analysis of Clustering Techniques on High-Dimensional Data
Action Recognition in Real-World Ambient Assisted Living Environment
RECALL-MM: A Multimodal Dataset of Consumer Product Recalls for Risk Analysis using Computational Methods and Large Language Models
Convolutional Neural Networks Can (Meta-)Learn the Same-Different Relation
A QUBO Framework for Team Formation
Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context
The Challenge of Achieving Attributability in Multilingual Table-to-Text Generation with Question-Answer Blueprints
A GAN-Enhanced Deep Learning Framework for Rooftop Detection from Historical Aerial Imagery
Incorporating GNSS Information with LIDAR-Inertial Odometry for Accurate Land-Vehicle Localization
Ethereum Price Prediction Employing Large Language Models for Short-term and Few-shot Forecasting
Real-time Video Prediction With Fast Video Interpolation Model and Prediction Training
Enhancing Weakly Supervised Video Grounding via Diverse Inference Strategies for Boundary and Prediction Selection
OncoReg: Medical Image Registration for Oncological Challenges
Intelligent bear deterrence system based on computer vision: Reducing human-bear conflicts in remote areas
Large Language Models Are Unreliable for Cyber Threat Intelligence
TRA: Better Length Generalisation with Threshold Relative Attention
Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networks
The realization of tones in spontaneous spoken Taiwan Mandarin: a corpus-based survey and theory-driven computational modeling
NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations
Neural Bayes estimation and selection for complex bivariate extremal dependence models
Conversational Agents for Older Adults' Health: A Systematic Literature Review
Agent-Based Modeling and Deep Neural Networks for Establishing Digital Twins of Secure Facilities under Sensing Restrictions
LSNet: See Large, Focus Small
CrossMuSim: A Cross-Modal Framework for Music Similarity Retrieval with LLM-Powered Text Description Sourcing and Mining
How to safely discard features based on aggregate SHAP values
Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction
SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System
A large-scale image-text dataset benchmark for farmland segmentation
Open-Vocabulary Semantic Segmentation with Uncertainty Alignment for Robotic Scene Understanding in Indoor Building Environments
Fast Training of Recurrent Neural Networks with Stationary State Feedbacks
The geomagnetic storm and Kp prediction using Wasserstein transformer
Learning phases with Quantum Monte Carlo simulation cell
Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering
FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video
Parsing Through Boundaries in Chinese Word Segmentation
UNITYAI-GUARD: Pioneering Toxicity Detection Across Low-Resource Indian Languages
Efficient Adaptation For Remote Sensing Visual Grounding
InkFM: A Foundational Model for Full-Page Online Handwritten Note Understanding

All 146