Papers

New on arXiv

Sat 27 Dec 2025

125 papers

SLO-Conditioned Action Routing for Retrieval-Augmented Generation: Objective Ablation and Failure ModesRetrieval-augmented generation → RAG robustness and adaptive retrieval
Memento 2: Learning by Stateful Reflective MemoryLLM agents and tool use → Agent memory systems
Beg to Differ: Understanding Reasoning-Answer Misalignment Across LanguagesLLM reasoning → Reasoning benchmarks and evaluation
SCPainter: A Unified Framework for Realistic 3D Asset Insertion and Novel View SynthesisDiffusion models → Diffusion and flow policies for robotics
Autoregressive Flow Matching for Motion PredictionDiffusion models → Video generation
CritiFusion: Semantic Critique and Spectral Alignment for Faithful Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing +1
Optimal Regulation of Nonlinear Input-Affine Systems via an Integral Reinforcement Learning-Based State-Dependent Riccati Equation ApproachDeep reinforcement learning methods → RL theory and sample complexity
Scaling Unverifiable Rewards: A Case Study on Visual InsightsLLM reasoning → Reasoning for agents, planning and code +1
FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-ResolutionLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability RepairLLM reasoning → Reasoning for agents, planning and code
Evaluating GRPO and DPO for Faithful Chain-of-Thought Reasoning in LLMsLLM reasoning → Prompting and chain-of-thought reasoning +1
On the Role of Discreteness in Diffusion LLMsDiffusion models → Discrete and text diffusion +1
DICE: Discrete Interpretable Comparative Evaluation with Probabilistic Scoring for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
Chain-of-thought Reviewing and Correction for Time Series Question AnsweringLLM reasoning → Time series reasoning
Envision: Embodied Visual Planning via Goal-Imagery Video DiffusionDiffusion models → Diffusion and flow policies for robotics
Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model BackboneMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
SANet: A Semantic-aware Agentic AI Networking Framework for Cross-layer Optimization in 6GLLM agents and tool use → Agentic AI for wireless networks
RollArt: Disaggregated Multi-Task Agentic RL Training at ScaleLLM agents and tool use → Reinforcement learning for LLM agents
Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual DomainsLLM reasoning → Multimodal reasoning +2
VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness
Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry GroundingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
Hierarchical Pedagogical Oversight: A Multi-Agent Adversarial Framework for Reliable AI TutoringLLM agents and tool use → Educational agents and math problem solving
ManchuTTS: Towards High-Quality Manchu Speech Synthesis via Flow Matching and Hierarchical Text RepresentationDiffusion models → Audio, speech and music
Scalpel-SAM: A Semi-Supervised Paradigm for Adapting SAM to Infrared Small Object DetectionMixture-of-experts → Vision mixture-of-experts +1
GraphLocator: Graph-guided Causal Reasoning for Issue LocalizationLLM reasoning → Reasoning for agents, planning and code
MEGA-PCC: A Mamba-based Efficient Approach for Joint Geometry and Attribute Point Cloud CompressionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Accounting Reasoning in Large Language Models: Concepts, Evaluation, and Empirical AnalysisLLM reasoning → Reasoning for agents, planning and code
HiFi-RAG: Hierarchical Content Filtering and Two-Pass Generation for Open-Domain RAGRetrieval-augmented generation → RAG pipeline design and evaluation
AnalogSAGE: Self-evolving Analog Design Multi-Agents with Stratified Memory and Grounded ExperienceLLM agents and tool use → Software engineering coding agents +1
Differentiable Inverse Modeling with Physics-Constrained Latent Diffusion for Heterogeneous Subsurface Parameter FieldsDiffusion models → Flow matching, time series and science
Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models ServingEfficient LLM inference and serving → Speculative decoding
Emergence of Human to Robot Transfer in Vision-Language-Action ModelsVision-language-action models → Human-video and latent-action pretraining
Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA
AdaFRUGAL: Adaptive Memory-Efficient Training with Dynamic Control
Syntactic Framing Fragility: An Audit of Robustness in LLM Ethical Decisions
SagaScale: A Realistic, Scalable, and High-Quality Long-Context Benchmark Built from Full-Length Novels
ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language
Topic Segmentation Using Generative Language Models
A Global Atlas of Digital Dermatology to Map Innovation and Disparities
Unified Review and Benchmark of Deep Segmentation Architectures for Cardiac Ultrasound on CAMUS
Leveraging Machine Learning for Early Detection of Lung Diseases
HINTS: Extraction of Human Insights from Time-Series Without External Sources
Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation
Geometric Scaling of Bayesian Inference in LLMs
Mitigating Social Desirability Bias in Random Silicon Sampling
GHaLIB: A Multilingual Framework for Hope Speech Detection in Low-Resource Languages
Position: Current Benchmarking Hinders Real Progress in Deep Learning for Time Series Forecasting
Predictive Modeling of Power Outages during Extreme Events: Integrating Weather and Socio-Economic Factors
Canonical correlation regression with noisy data
Learning with the p-adics
Mesquite MoCap: Democratizing Real-Time Motion Capture with Affordable, Bodyworn IoT Sensors and WebXR SLAM
Multimodal Diffeomorphic Registration with Neural ODEs and Structural Descriptors
Conformal Prediction Sets for Next-Token Prediction in Large Language Models: Balancing Coverage Guarantees with Set Efficiency
Beyond Centralization: Provable Communication Efficient Decentralized Multi-Task Learning
Semantic contrastive learning for orthogonal X-ray computed tomography reconstruction
Beyond Itinerary Planning-A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks
Quantum Generative Models for Computational Fluid Dynamics: A First Exploration of Latent Space Learning in Lattice Boltzmann Simulations
Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
INTERACT-CMIL: Multi-Task Shared Learning and Inter-Task Consistency for Conjunctival Melanocytic Intraepithelial Lesion Grading
Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains
Machine learning models for predicting catastrophe bond coupons using climate data
Investigating Deep Learning Models for Ejection Fraction Estimation from Echocardiography Videos
Clinically Calibrated Machine Learning Benchmarks for Large-Scale Multi-Disorder EEG Classification
Visual Autoregressive Modelling for Monocular Depth Estimation
Tree Meets Transformer: A Hybrid Architecture for Scalable Power Allocation in Cell-Free Networks
Likelihood-Preserving Embeddings for Statistical Inference
M2G-Eval: Enhancing and Evaluating Multi-granularity Multilingual Code Generation
The Wisdom of Deliberating AI Crowds: Does Deliberation Improve LLM-Based Forecasting?
Rethinking Memory Design in SAM-Based Visual Object Tracking
Communication Compression for Distributed Learning with Aggregate and Server-Guided Feedback
Chord Recognition with Deep Learning
Enhancing Noise Resilience in Face Clustering via Sparse Differential Transformer
Beyond Isolated Investor: Predicting Startup Success via Roleplay-Based Collective Agents
Gold Price Prediction Using Long Short-Term Memory and Multi-Layer Perceptron with Gray Wolf Optimizer
Learning Multi-Modal Mobility Dynamics for Generalized Next Location Recommendation
Structured Prompting and LLM Ensembling for Multimodal Conversational Aspect-based Sentiment Analysis
PTalker: Personalized Speech-Driven 3D Talking Head Animation via Style Disentanglement and Modality Alignment
Tyee: A Unified, Modular, and Fully-Integrated Configurable Toolkit for Intelligent Physiological Health Care
Cryptocurrency Price Prediction Using Parallel Gated Recurrent Units
Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
Data-Driven Analysis of Crash Patterns in SAE Level 2 and Level 4 Automated Vehicles Using K-means Clustering and Association Rule Mining
Structural Incompatibility of Differentiable Sorting and Within-Vector Rank Normalization
KV-Tracker: Real-Time Pose Tracking with Transformers
ReFRM3D: A Radiomics-enhanced Fused Residual Multiparametric 3D Network with Multi-Scale Feature Fusion for Glioma Characterization
Lessons from Neuroscience for AI: How integrating Actions, Compositional Structure and Episodic Memory could enable Safe, Interpretable and Human-Like AI
Geometry-Aware Optimization for Respiratory Sound Classification: Enhancing Sensitivity with SAM-Optimized Audio Spectrogram Transformers
Learning When Not to Attend Globally
Computing Pure-Strategy Nash Equilibria in a Two-Party Policy Competition: Existence and Algorithmic Approaches
TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting
CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation
Multi-AI Agent Framework Reveals the "Oxide Gatekeeper" in Aluminum Nanoparticle Oxidation
DreamOmni3: Scribble-based Editing and Generation
Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks
Decomposing Task Vectors for Refined Model Editing
Predicting LLM Correctness in Prosthodontics Using Metadata and Hallucination Signals
SCAFusion: A Multimodal 3D Detection Framework for Small Object Detection in Lunar Surface Exploration
The Quest for Winning Tickets in Low-Rank Adapters
Role-Based Fault Tolerance System for LLM RL Post-Training
Tracking by Predicting 3-D Gaussians Over Time
Toward Real-World IoT Security: Concept Drift-Resilient IoT Botnet Detection via Latent Space Representation Learning and Alignment

All 125