Papers

New on arXiv

Sun 14 Dec 2025

178 papers

Comparative Analysis of Neural Retriever-Reranker Pipelines for Retrieval-Augmented Generation over Knowledge Graphs in E-commerce ApplicationsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Auto-Tuning Safety Guardrails for Black-Box Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
COBRA: Catastrophic Bit-flip Reliability Analysis of State-Space ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
CODE ACROSTIC: Robust Watermarking for Code GenerationLLM safety and security → Watermarking generated content and models
One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMsLLM safety and security → Jailbreaking
DL3M: A Vision-to-Language Framework for Expert-Level Medical Reasoning through Deep Learning and Large Language ModelsLLM reasoning → Clinical and biomedical applications
The Laminar Flow Hypothesis: Detecting Jailbreaks via Semantic Turbulence in Large Language ModelsLLM safety and security → Jailbreaking
ERA-IT: Aligning Semantic Models with Revealed Economic Preference for Real-Time and Explainable Patent ValuationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Information-Consistent Language Model Recommendations through Group Relative Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
Forgetful but Faithful: A Cognitive Memory Architecture and Benchmark for Privacy-Aware Generative AgentsLLM agents and tool use → Agent memory systems
MPC-Guided Safe Reinforcement Learning and Lipschitz-Based Filtering for Structured Nonlinear SystemsDeep reinforcement learning methods → Safe and constrained RL
Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
On the continuity of flowsDiffusion models → Flow matching, time series and science
Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and ReflectsLLM agents and tool use → Agent memory systems
Fault-Tolerant Sandboxing for AI Coding Agents: A Transactional Approach to Safe Autonomous ExecutionLLM agents and tool use → Agent threats, guardrails and governance
Distributed Reinforcement Learning using Local Smart Meter Data for Voltage Regulation in Distribution NetworksDeep reinforcement learning methods → RL for energy, networks and operations
DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and PlanningMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
Diffusion Model-Based Posterior Sampling in Full Waveform InversionDiffusion models → Flow matching, time series and science
Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
State over Tokens: Characterizing the Role of Reasoning TokensLLM reasoning → Test-time compute and efficient thinking
JointAVBench: A Benchmark for Joint Audio-Visual Reasoning EvaluationLLM reasoning → Audio-language model reasoning
CoRe3D: Collaborative Reasoning as a Foundation for 3D IntelligenceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and ReasoningLLM reasoning → Audio-language model reasoning +1
GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video GenerationWorld models → World models for autonomous driving +1
Residual-augmented flow matching operators for probabilistic partial differential equationsDiffusion models → Flow matching, time series and science
NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding AgentsLLM agents and tool use → Software engineering coding agents
CoDA: A Context-Decoupled Hierarchical Agent with Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
Efficient Vision-Language Reasoning via Adaptive Token PruningLLM reasoning → Multimodal reasoning +2
Hybrid Retrieval-Augmented Generation for Robust Multilingual Document Question AnsweringRetrieval-augmented generation → Generation and context integration
WebOperator: Action-Aware Tree Search for Autonomous Agents in Web EnvironmentLLM agents and tool use → Web, search, and research agents
Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM ReasoningLLM reasoning → Multimodal reasoning +1
Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AILLM agents and tool use → Agent memory systems
Argumentative Reasoning with Language Models on Non-factorized Case BasesLLM reasoning → Reasoning benchmarks and evaluation
MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI AgentsLLM agents and tool use → GUI and mobile agents
DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language ModelLLM reasoning → Multimodal reasoning +1
Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent SpaceLLM reasoning → Multimodal reasoning +1
Understanding Syllogistic Reasoning in LLMs from Formal and Natural Language PerspectivesLLM reasoning → Reasoning benchmarks and evaluation
No Cache Left Idle: Accelerating diffusion model via Extreme-slimming CachingDiffusion models → Diffusion foundations and sampling
AgentSHAP: Interpreting LLM Agent Tool Importance with Monte Carlo Shapley Value EstimationLLM agents and tool use → Tool learning and function calling
Content-Aware Ad Banner Layout Generation with Two-Stage Chain-of-Thought in Vision Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
ceLLMate: Sandboxing Browser AI AgentsLLM safety and security → Prompt injection and agent security
Detecting Prompt Injection Attacks Against Application Using ClassifiersLLM safety and security → Prompt injection and agent security
Coupled Variational Reinforcement Learning for Language Model General ReasoningLLM reasoning → Reinforcement learning for reasoning
Measurement Plasticity: Sensor-Level Adaptation for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video UnderstandingEfficient LLM inference and serving → Visual token pruning in multimodal models
World Models Unlock Optimal Foraging Strategies in Reinforcement Learning AgentsWorld models → World models for language agents +1
NagaNLP: Bootstrapping NLP for Low-Resource Nagamese Creole with Human-in-the-Loop Synthetic DataSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Animus3D: Text-driven 3D Animation via Motion Score DistillationDiffusion models → Video generation
KidsArtBench: Multi-Dimensional Children's Art Evaluation with Attribute-Aware MLLMsMultimodal LLMs / vision-language models → Image editing and quality assessment
SafeGen: Embedding Ethical Safeguards in Text-to-Image GenerationDiffusion models → Robustness, privacy and adversarial aspects
Social Determinants of Health Prediction for ICD-9 Code with Reasoning Models
DeliberationBench: When Do More Voices Hurt? A Controlled Study of Multi-LLM Deliberation Protocols
AnimatedLLM: Explaining LLMs with Interactive Visualizations
EEG-to-Voice Decoding of Spoken and Imagined speech Using Non-Invasive EEG
Pre-review to Peer review: Pitfalls of Automating Reviews using Large Language Models
The Complete Anatomy of the Madden-Julian Oscillation Revealed by Artificial Intelligence
FuseFi: Combining Irregularly Sampled CSI from Diverse Communication Packets and Frequency Bands for Wi-Fi Sensing
EcoNet: Multiagent Planning and Control Of Household Energy Resources Using Active Inference
What's the Price of Monotonicity? A Multi-Dataset Benchmark of Monotone-Constrained Gradient Boosting for Credit PD
Adversarial Robustness in Financial Machine Learning: Defenses, Economic Impact, and Governance Evidence
Hyperparameter Tuning-Based Optimized Performance Analysis of Machine Learning Algorithms for Network Intrusion Detection
Cyberswarm: a novel swarm intelligence algorithm inspired by cyber community dynamics
Human-AI Collaboration Mechanism Study on AIGC Assisted Image Production for Special Coverage
Instilling Organisational Values in Firefighters through Simulation-Based Training
TF-MCL: Time-frequency Fusion and Multi-domain Cross-Loss for Self-supervised Depression Detection
DARTs: A Dual-Path Robust Framework for Anomaly Detection in High-Dimensional Multivariate Time Series
Plug-and-Play Parameter-Efficient Tuning of Embeddings for Federated Recommendation
Low-Rank Compression of Language Models via Differentiable Rank Selection
PIS: A Generalized Physical Inversion Solver for Arbitrary Sparse Observations via Set Conditioned Flow Matching
Complex Mathematical Expression Recognition: Benchmark, Large-Scale Dataset and Strong Baseline
Exploring the Modular Integration of "AI + Architecture" Pedagogy in Undergraduate Design Education: A Case Study of Architectural Design III/IV Courses at Zhejiang University
SignRAG: A Retrieval-Augmented System for Scalable Zero-Shot Road Sign Recognition
Cross-Level Sensor Fusion with Object Lists via Transformer for 3D Object Detection
Unsupervised learning of multiscale switching dynamical system models from multimodal neural data
Improving Recursive Transformers with Mixture of LoRAs
Schrodinger Audio-Visual Editor: Object-Level Audiovisual Removal
Active Learning with Imperfect Labels: Optimal Labeler Assignment and Sample Selection
Counting Clues: A Lightweight Probabilistic Baseline Can Match an LLM
KANEL'E: Kolmogorov-Arnold Networks for Efficient LUT-based Evaluation
HaShiFlex: A High-Throughput Hardened Shifter DNN Accelerator with Fine-Tuning Flexibility
Selective Conformal Risk Control
SAGA: Open-World Mobile Manipulation via Structured Affordance Grounding
PRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attacks
What Matters in Evaluating Book-Length Stories? A Systematic Study of Long Story Evaluation
Algorithmic Criminal Liability in Greenwashing: Comparing India, United States, and European Union
Network Level Evaluation of Hangup Susceptibility of HRGCs using Deep Learning and Sensing Techniques: A Goal Towards Safer Future
GradID: Adversarial Detection via Intrinsic Dimensionality of Gradients
Adapting Multimodal Foundation Models for Few-Shot Learning: A Comprehensive Study on Contrastive Captioners
Decoding Human and AI Persuasion in National College Debate: Analyzing Prepared Arguments Through Aristotle's Rhetorical Principles
Optimal Resource Allocation for ML Model Training and Deployment under Concept Drift
Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA
OPAL: Operator-Programmed Algorithms for Landscape-Aware Black-Box Optimization
From Small to Large: Generalization Bounds for Transformers on Variable-Size Inputs
Causal Counterfactuals Reconsidered
A Disproof of Large Language Model Consciousness: The Necessity of Continual Learning for Consciousness
Learning Common and Salient Generative Factors Between Two Image Datasets
TRACER: Transfer Learning based Real-time Adaptation for Clinical Evolving Risk
Liquid Reasoning Transformers: A Sudoku-Based Prototype for Chess-Scale Algorithmic Tasks
L-STEC: Learned Video Compression with Long-term Spatio-Temporal Enhanced Context
Unveiling Statistical Significance of Online Regression over Multiple Datasets

All 178