Papers

New on arXiv

Fri 2 Jan 2026

138 papers

SearchGym: A Modular Infrastructure for Cross-Platform Benchmarking and Hybrid Search OrchestrationRetrieval-augmented generation → RAG pipeline design and evaluation
Entropy-Tree: Tree-Based Decoding with Entropy-Guided ExplorationLLM reasoning → Test-time compute and efficient thinking
Opening the Black Box: A Survey on the Mechanisms of Multi-Step Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
Automatic Question Generation for Intuitive Learning Utilizing Causal Graph Guided Chain of Thought ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
Semantic Event Graphs for Long-Form Video Question AnsweringMultimodal LLMs / vision-language models → Video understanding with MLLMs
Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential EquationsDiffusion models → Diffusion and flow policies for robotics
DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
ElecTwit: A Framework for Studying Persuasion in Multi-Agent Social SystemsLLM agents and tool use → Social simulation and multi-agent debate
V-VLAPS: Value-Guided Planning for Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training
Reliability Under Randomness: An Empirical Analysis of Sparse and Dense Language Models Across Decoding TemperaturesMixture-of-experts → MoE large language models
Emoji-Based Jailbreaking of Large Language ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
AlignUSER: Human-Aligned LLM Agents via World Models for Recommender System EvaluationWorld models → World models for language agents +1
Geometry of Reason: Spectral Signatures of Valid Mathematical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
Categorical Reparameterization with Denoising Diffusion modelsDiffusion models → Diffusion foundations and sampling
Investigating the Viability of Employing Multi-modal Large Language Models in the Context of Audio Deepfake DetectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Early-Stage Prediction of Review Effort in AI-Generated Pull RequestsLLM agents and tool use → Software engineering coding agents
The Reasoning-Creativity Trade-off: Toward Creativity-Driven Problem SolvingLLM reasoning → Reasoning benchmarks and evaluation
An Agentic Framework for Neuro-Symbolic ProgrammingLLM agents and tool use → General LLM agent frameworks and benchmarks
Stochastic Actor-Critic: Mitigating Overestimation via Temporal Aleatoric UncertaintyDeep reinforcement learning methods → RL theory and sample complexity
Precision autotuning for linear solvers via contextual bandit-based RLDeep reinforcement learning methods → RL theory and sample complexity
Detecting Performance Degradation under Data Shift in Pathology Vision-Language ModelMultimodal LLMs / vision-language models → Medical vision-language models
KDPhys: An Attention Guided 3D to 2D Knowledge Distillation for Real-time Video-Based Physiological MeasurementKnowledge distillation → Distillation for medical imaging
IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
CRoPS: A Training-Free Hallucination Mitigation Framework for Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Physio-DPO: Aligning Large Language Models with the Protein Energy Landscape to Eliminate Structural HallucinationsLLM alignment / RLHF / preference optimisation → Preference optimization for molecular design
FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative DecodingEfficient LLM inference and serving → Early exit and edge inference
DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM HallucinationsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
Vision-based Goal-Reaching Control for Mobile Robots Using a Hierarchical Learning FrameworkDeep reinforcement learning methods → RL for robot navigation and UAV control
Traffic-Aware Optimal Taxi Placement Using Graph Neural Network-Based Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
Beyond IVR: Benchmarking Customer Support LLM Agents for Business-AdherenceLLM agents and tool use → General LLM agent frameworks and benchmarks
SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion GenerationLLM safety and security → Vision-language and text-to-image safety
CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial PatternsLLM safety and security → Safety alignment, refusal and guardrails
HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-ExpertsMixture-of-experts → Federated mixture-of-experts
A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASRMixture-of-experts → Multimodal MoE models
LLM-Based Agentic Exploration for Robot Navigation & Manipulation with Skill OrchestrationLLM agents and tool use → Multimodal and embodied agents
A Comprehensive Dataset for Human vs. AI Generated Image DetectionDiffusion models → Image generation, text-to-image and editing
Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical TrendsLLM reasoning → Knowledge- and tool-augmented reasoning
FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph InjectionDiffusion models → Image generation, text-to-image and editing
Cloud-Native Generative AI for Automated Planogram Synthesis: A Diffusion Model Approach for Multi-Store Retail OptimizationDiffusion models → 3D, point cloud and scene generation
Trajectory Guard -- A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AILLM agents and tool use → Agent threats, guardrails and governance
The Illusion of Insight in Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
FinRetrieval: A Benchmark for Financial Data Retrieval by AI Agents
ChiEngMixBench: Evaluating Large Language Models on Expert-Style Chinese-English Terminology Mixing
The Slow Drift of Support: Boundary Failures in Multi-Turn Mental Health LLM Dialogues
Filtering Beats Fine Tuning: A Bayesian Kalman View of In Context Learning in LLMs
Feedback Indices to Evaluate LLM Responses to Rebuttals for Multiple Choice Type Questions
AI-Guided Discovery of Novel Ionic Liquid Solvents for Industrial CO2 Capture
Socially-Aware Recommender Systems Mitigate Opinion Clusterization
SpikySpace: A Spiking State Space Model for Energy-Efficient Time Series Forecasting
The Vibe-Check Protocol: Quantifying Cognitive Offloading in AI Programming
Expert-Guided Explainable Few-Shot Learning with Active Sample Selection for Medical Image Analysis
Scale-aware Adaptive Supervised Network with Limited Medical Annotations
Lightweight Channel Attention for Efficient CNNs
Dynamic Accuracy Estimation in a Wi-Fi-based Positioning System
VEAT Quantifies Implicit Associations in Text-to-Video Generator Sora and Reveals Challenges in Bias Mitigation
WildIng: A Wildlife Image Invariant Representation Model for Geographical Domain Shift
UnrealPose: Leveraging Game Engine Kinematics for Large-Scale Synthetic Human Pose Data
Uncertainty-Calibrated Explainable Artificial Intelligence for Fetal Ultrasound Plane Classification: A Systematic Review
Few-Shot Video Object Segmentation in X-Ray Angiography Using Local Matching and Spatio-Temporal Consistency Loss
Tessellation Localized Transfer learning for nonparametric regression
Simulations of MRI Guided and Powered Ferric Applicators for Tetherless Delivery of Therapeutic Interventions
Zero-shot Forecasting by Simulation Alone
Explainability-Guided Defense: Attribution-Aware Model Refinement Against Adversarial Data Attacks
Adapting Feature Attenuation to NLP
A Deep Learning Approach for Automated Skin Lesion Diagnosis with Explainable AI
Deep Clustering with Associative Memories
PhyEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education
Comparative Analysis of Formula and Structure Prediction from Tandem Mass Spectra
Learning to Segment Liquids in Real-world Images
Rate-Distortion Analysis of Compressed Query Delegation with Low-Rank Riemannian Updates
Improving Code-Switching Speech Recognition with TTS Data Augmentation
LOFA: Online Influence Maximization under Full-Bandit Feedback using Lazy Forward Selection
Enhanced Data-Driven Product Development via Gradient Based Optimization and Conformalized Monte Carlo Dropout Uncertainty Estimation
Analyzing the Shopping Journey: Computing Shelf Browsing Visits in a Physical Retail Store
Measuring Social Media Polarization Using Large Language Models and Heuristic Rules
AdaGaR: Adaptive Gabor Representation for Dynamic Scene Reconstruction
Two Deep Learning Approaches for Automated Segmentation of Left Ventricle in Cine Cardiac MRI
Fusion-SSAT: Unleashing the Potential of Self-supervised Auxiliary Task by Feature Fusion for Generalized Deepfake Detection
Adapting Natural Language Processing Models Across Jurisdictions: A pilot Study in Canadian Cancer Registries
FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharing
LLM Agents for Combinatorial Efficient Frontiers: Investment Portfolio Optimization
Unified Primitive Proxies for Structured Shape Completion
Memory Bank Compression for Continual Adaptation of Large Language Models
A Machine Learning Framework for Off Ball Defensive Role and Performance Evaluation in Football
Exploring the Performance of Large Language Models on Subjective Span Identification Tasks
Grading Handwritten Engineering Exams with Multimodal Large Language Models
Multi-Level Feature Fusion for Continual Learning in Visual Quality Inspection
Efficient Deep Demosaicing with Spatially Downsampled Isotropic Networks
DefVINS: Visual-Inertial Odometry for Deformable Scenes
BSAT: B-Spline Adaptive Tokenizer for Long-Term Time Series Forecasting
Bayesian Inverse Games with High-Dimensional Multi-Modal Observations
A Vision-and-Knowledge Enhanced Large Language Model for Generalizable Pedestrian Crossing Behavior Inference
ARISE: Adaptive Reinforcement Integrated with Swarm Exploration
TeleDoCTR: Domain-Specific and Contextual Troubleshooting for Telecommunications
Cost Optimization in Production Line Using Genetic Algorithm
Sigmoid Head for Quality Estimation under Language Ambiguity
QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models
Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians
Sparse FEONet: A Low-Cost, Memory-Efficient Operator Network via Finite-Element Local Sparsity for Parametric PDEs
Fast-weight Product Key Memory

All 138