AI Research News Feeds for January 9th, 2026

AI RESEARCH PAPERS & ACADEMIC SOURCES

• ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos
• Plenoptic Video Generation
• RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation
• GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation
• Pixel-Perfect Visual Geometry Estimation
• RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes
• QNeRF: Neural Radiance Fields on a Simulated Gate-Based Quantum Computer
• Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video
• UNIC: Learning Unified Multimodal Extrinsic Contact Estimation
• End-to-end differentiable design of geometric waveguide displays
• In-SRAM Radiant Foam Rendering on a Graph Processor
• Decentralized Privacy-Preserving Federal Learning of Computer Vision Models on Edge Devices
• Scalable neural pushbroom architectures for real-time denoising of hyperspectral images onboard satellites
• GenAI-DrawIO-Creator: A Framework for Automated Diagram Generation
• Learning Latent Action World Models In The Wild
• Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstration
• Controllable Generation with Text-to-Image Diffusion Models: A Survey
• Explainable Binary Classification of Separable Shape Ensembles
• SynDroneVision: A Synthetic Dataset for Image-Based Drone Detection
• Name That Part: 3D Part Segmentation and Naming
• Extended OpenTT Games Dataset: A table tennis dataset for fine-grained shot type and point outcome
• Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes
• Embedding Textual Information in Images Using Quinary Pixel Combinations
• Unified Text-Image Generation with Weakness-Targeted Post-Training
• ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers
• SCAR-GS: Spatial Context Attention for Residuals in Progressive Gaussian Splatting
• PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache
• Combining facial videos and biosignals for stress estimation during driving
• Few-Shot LoRA Adaptation of a Flow-Matching Foundation Model for Cross-Spectral Object Detection
• Performance Analysis of Image Classification on Bangladeshi Datasets
• 3D-Agent:Tri-Modal Multi-Agent Collaboration for Scalable 3D Object Annotation
• From Preoperative CT to Postmastoidectomy Mesh Construction:1Mastoidectomy Shape Prediction for Cochlear Implant Surgery
• CRUNet-MR-Univ: A Foundation Model for Diverse Cardiac MRI Reconstruction
• UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving
• TokenSeg: Efficient 3D Medical Image Segmentation via Hierarchical Visual Token Compression
• FaceRefiner: High-Fidelity Facial Texture Refinement with Differentiable Rendering-based Style Transfer
• All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
• 3D Conditional Image Synthesis of Left Atrial LGE MRI from Composite Semantic Masks
• MiLDEdit: Reasoning-Based Multi-Layer Design Document Editing
• Detection of Deployment Operational Deviations for Safety and Security of AI-Enabled Human-Centric Cyber Physical Systems
• HUR-MACL: High-Uncertainty Region-Guided Multi-Architecture Collaborative Learning for Head and Neck Multi-Organ Segmentation
• HyperAlign: Hyperbolic Entailment Cones for Adaptive Text-to-Image Alignment Assessment
• DB-MSMUNet:Dual Branch Multi-scale Mamba UNet for Pancreatic CT Scans Segmentation
• HATIR: Heat-Aware Diffusion for Turbulent Infrared Video Super-Resolution
• WebCryptoAgent: Agentic Crypto Trading with Web Informatics
• Forge-and-Quench: Enhancing Image Generation for Higher Fidelity in Unified Multimodal Models
• On the Holistic Approach for Detecting Human Image Forgery
• Training a Custom CNN on Five Heterogeneous Image Datasets
• AIVD: Adaptive Edge-Cloud Collaboration for Accurate and Efficient Industrial Visual Detection
• Skeletonization-Based Adversarial Perturbations on Large Vision Language Model's Mathematical Text Recognition
• ProFuse: Efficient Cross-View Context Fusion for Open-Vocabulary 3D Gaussian Splatting
• Segmentation-Driven Monocular Shape from Polarization based on Physical Model
• GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models
• Defocus Aberration Theory Confirms Gaussian Model in Most Imaging Devices
• SRU-Pix2Pix: A Fusion-Driven Generator Network for Medical Image Translation with Few-Shot Learning
• PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference
• Detector-Augmented SAMURAI for Long-Duration Drone Tracking
• Integrated Framework for Selecting and Enhancing Ancient Marathi Inscription Images from Stone, Metal Plate, and Paper Documents
• SOVABench: A Vehicle Surveillance Action Retrieval Benchmark for Multimodal Large Language Models
• Character Detection using YOLO for Writer Identification in multiple Medieval books
• DivAS: Interactive 3D Segmentation of NeRFs via Depth-Weighted Voxel Aggregation
• Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics
• TEA: Temporal Adaptive Satellite Image Semantic Segmentation
• SparseLaneSTP: Leveraging Spatio-Temporal Priors with Sparse Transformers for 3D Lane Detection
• OceanSplat: Object-aware Gaussian Splatting with Trinocular View Consistency for Underwater Scene Reconstruction
• Higher-Order Adversarial Patches for Real-Time Object Detectors
• Patch-based Representation and Learning for Efficient Deformation Modeling
• Driving on Registers
• UniLiPs: Unified LiDAR Pseudo-Labeling with Geometry-Grounded Dynamic Scene Decomposition
• From Rays to Projections: Better Inputs for Feed-Forward View Synthesis
• Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing
• VERSE: Visual Embedding Reduction and Space Exploration. Clustering-Guided Insights for Training Data Enhancement in Visually-Rich Document Understanding
• VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control
• Multi-Scale Local Speculative Decoding for Image Generation
• Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering
• CoV: Chain-of-View Prompting for Spatial Reasoning
• VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
• MoE3D: A Mixture-of-Experts Module for 3D Reconstruction
• FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matching
• Can AI-Generated Persuasion Be Detected? Persuaficial Benchmark and AI vs. Human Linguistic Differences
• GenProve: Learning to Generate Text with Fine-Grained Provenance
• A Unified Spoken Language Model with Injected Emotional-Attribution Thinking for Human-like Interaction
• Text as a Universal Interface for Transferable Personalization
• Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization
• Can Large Language Models Resolve Semantic Discrepancy in Self-Destructive Subcultures? Evidence from Jirai Kei
• H\'an D\=an Xu\'e B\`u (Mimicry) or Q\=ing Ch\=u Y\'u L\'an (Mastery)? A Cognitive Perspective on Reasoning Distillation in Large Language Models
• ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG
• SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment
• How Human is AI? Examining the Impact of Emotional Prompts on Artificial and Human and Responsiveness
• Agent-as-a-Judge
• DocDancer: Towards Agentic Document-Grounded Information Seeking
• Reverse-engineering NLI: A study of the meta-inferential properties of Natural Language Inference
• Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems
• LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation
• Generative Teaching via Code
• Sphinx: Benchmarking and Modeling for LLM-Driven Pull Request Review
• Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs
• Generalization to Political Beliefs from Fine-Tuning on Sports Team Preferences
• The Language of Bargaining: Linguistic Effects in LLM Negotiations
• Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
• Vision-Language Agents for Interactive Forest Change Analysis
• CircuitLM: A Multi-Agent LLM-Aided Design Framework for Generating Circuit Schematics from Natural Language Prompts
• Advancing Language Models for Code-related Tasks
• BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents
• Agri-R1: Empowering Generalizable Agricultural Reasoning in Vision-Language Models with Reinforcement Learning
• A Method for Constructing a Digital Transformation Driving Mechanism Based on Semantic Understanding of Large Models
• Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning
• Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models
• AT$^2$PO: Agentic Turn-based Policy Optimization via Tree Search
• CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
• Defense Against Indirect Prompt Injection via Tool Result Parsing
• DR-LoRA: Dynamic Rank LoRA for Mixture-of-Experts Adaptation
• ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning
• Publishing FAIR and Machine-actionable Reviews in Materials Science: The Case for Symbolic Knowledge in Neuro-symbolic Artificial Intelligence
• Reinforced Efficient Reasoning via Semantically Diverse Exploration
• Multi-Disciplinary Dataset Discovery from Citation-Verified Literature Contexts
• Semantically Orthogonal Framework for Citation Classification: Disentangling Intent and Content
• A Lightweight and Explainable Vision-Language Framework for Crop Disease Visual Question Answering
• Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop
• Mechanisms of Prompt-Induced Hallucination in Vision-Language Models
• Pelican Soup Framework: A Theoretical Framework for Language Model Capabilities
• ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliteration
• MedPI: Evaluating AI Systems in Medical Patient-facing Interactions
• RAGVUE: A Diagnostic View for Explainable and Automated Evaluation of Retrieval-Augmented Generation
• Automatic Construction of Chinese Verb Collostruction Database
• Attribute-Aware Controlled Product Generation with LLMs for E-commerce
• Collective Narrative Grounding: Community-Coordinated Data Contributions to Improve Local AI Systems
• STDD:Spatio-Temporal Dynamics-Driven Token Refinement in Diffusion Language Models
• Enhancing Admission Inquiry Responses with Fine-Tuned Models and Retrieval-Augmented Generation
• Ideology as a Problem: Lightweight Logit Steering for Annotator-Specific Alignment in Social Media Analysis
• LLMs for Explainable Business Decision-Making: A Reinforcement Learning Fine-Tuning Approach
• Leveraging Language Models and RAG for Efficient Knowledge Discovery in Clinical Environments
• Complexity Agnostic Recursive Decomposition of Thoughts
• Qwerty AI: Explainable Automated Age Rating and Content Safety Assessment for Russian-Language Screenplays
• TrueBrief: Faithful Summarization through Small Language Models
• AnimatedLLM: Explaining LLMs with Interactive Visualizations
• RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation
• Dialect Matters: Cross-Lingual ASR Transfer for Low-Resource Indic Language Varieties
• MiJaBench: Revealing Minority Biases in Large Language Models via Hate Speech Jailbreaking
• ARREST: Adversarial Resilient Regulation Enhancing Safety and Truth in Large Language Models
• Interpreting Transformers Through Attention Head Intervention
• Gavel: Agent Meets Checklist for Evaluating LLMs on Long-Context Legal Summarization
• Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs
• Learning to Simulate Human Dialogue
• Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
• Users Mispredict Their Own Preferences for AI Writing Assistance
• Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
• WESR: Scaling and Evaluating Word-level Event-Speech Recognition
• LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation
• GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence
• BanglaLorica: Design and Evaluation of a Robust Watermarking Algorithm for Large Language Models in Bangla Text Generation
• Identifying Good and Bad Neurons for Task-Level Controllable LLMs
• FeedEval: Pedagogically Aligned Evaluation of LLM-Generated Essay Feedback
• Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization
• THaLLE-ThaiLLM: Domain-Specialized Small LLMs for Finance and Thai -- Technical Report
• When More Words Say Less: Decoupling Length and Specificity in Image Description Evaluation
• Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR
• From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Dataset
• MAGA-Bench: Machine-Augment-Generated Text via Alignment Detection Benchmark
• SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation
• CRANE: Causal Relevance Analysis of Language-Specific Neurons in Multilingual Large Language Models
• ToolGate: Contract-Grounded and Verified Tool Execution for LLMs
• See, Explain, and Intervene: A Few-Shot Multimodal Agent Framework for Hateful Meme Moderation
• Thunder-KoNUBench: A Corpus-Aligned Benchmark for Korean Negation Understanding
• PRISM: A Unified Framework for Post-Training LLMs Without Verifiable Rewards
• DSC2025 -- ViHallu Challenge: Detecting Hallucination in Vietnamese LLMs
• Fame Fades, Nature Remains: Disentangling the Character Identity of Role-Playing Agents
• Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
• Automatic Classifiers Underdetect Emotions Expressed by Men
• AM$^3$Safety: Towards Data Efficient Alignment of Multi-modal Multi-turn Safety for MLLMs
• RiskAtlas: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
• Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrieval
• PILOT-Bench: A Benchmark for Legal Reasoning in the Patent Domain with IRAC-Aligned Classification Tasks
• Revisiting Judge Decoding from First Principles via Training-Free Distributional Divergence
• LANGSAE EDITING: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal
• NC2C: Automated Convexification of Generic Non-Convex Optimization Problems
• Belief in Authority: Impact of Authority in Multi-Agent Evaluation Framework
• When AI Settles Down: Late-Stage Stability as a Signature of AI-Generated Text Detection
• RAAR: Retrieval Augmented Agentic Reasoning for Cross-Domain Misinformation Detection
• MisSpans: Fine-Grained False Span Identification in Cross-Domain Fake News
• A Navigational Approach for Comprehensive RAG via Traversal over Proposition Graphs
• EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesis
• Mind2Report: A Cognitive Deep Research Agent for Expert-Level Commercial Report Synthesis
• Faithful Summarisation under Disagreement via Belief-Level Aggregation
• Comparison of Maximum Likelihood Classification Before and After Applying Weierstrass Transform
• Illumination Angular Spectrum Encoding for Controlling the Functionality of Diffractive Networks
• Token Maturation: Autoregressive Language Generation via Continuous Token Dynamics
• Gradient-based Optimisation of Modulation Effects
• Higher-Order Knowledge Representations for Agentic Scientific Reasoning
• CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters
• Scaling Vision Language Models for Pharmaceutical Long Form Video Reasoning on Industrial GenAI Platform
• V-FAT: Benchmarking Visual Fidelity Against Text-bias
• Rotation-Robust Regression with Convolutional Model Trees
• Leveraging Prediction Entropy for Automatic Prompt Weighting in Zero-Shot Audio-Language Classification
• Exponential capacity scaling of classical GANs compared to hybrid latent style-based quantum GANs
• Challenges and Research Directions for Large Language Model Inference Hardware
• From Understanding to Engagement: Personalized pharmacy Video Clips via Vision Language Models (VLMs)
• Compositional Steering of Large Language Models with Steering Tokens
• Quantitative mapping from conventional MRI using self-supervised physics-guided deep learning: applications to a large-scale, clinically heterogeneous dataset
• Code-Mix Sentiment Analysis on Hinglish Tweets
• Token-Level LLM Collaboration via FusionRoute
• Neural Algorithmic Reasoning for Approximate $k$-Coloring with Recursive Warm Starts
• Atlas 2 -- Foundation models for clinical deployment
• ROOFS: RObust biOmarker Feature Selection
• Learning Mixture Models via Efficient High-dimensional Sparse Fourier Transforms
• RelayLLM: Efficient Reasoning via Collaborative Decoding
• Cutting AI Research Costs: How Task-Aware Compression Makes Large Language Model Agents Affordable
• Stock Market Price Prediction using Neural Prophet with Deep Neural Network
• CAOS: Conformal Aggregation of One-Shot Predictors
• Stochastic Deep Learning: A Probabilistic Framework for Modeling Uncertainty in Structured Temporal Data
• Measuring and Fostering Peace through Machine Learning and Artificial Intelligence
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
• Convergence of Sign-based Random Reshuffling Algorithms for Nonconvex Optimization
• GRAPHGINI: Fostering Individual and Group Fairness in Graph Neural Networks
• What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• Human-in-the-Loop Feature Selection Using Interpretable Kolmogorov-Arnold Network-based Double Deep Q-Network
• Graph-Dictionary Signal Model for Sparse Representations of Multivariate Data
• Low-rank variational dropout: Rank selection and uncertainty in adapters
• OpenEM: Large-scale multi-structural 3D datasets for electromagnetic methods
• Realised Volatility Forecasting: Machine Learning via Financial Word Embedding
• Extreme Solar Flare Prediction Using Residual Networks with HMI Magnetograms and Intensitygrams
• Fourier Neural Operators for Learning Dynamics in Quantum Spin Systems
• Surface solar radiation: AI satellite retrieval can outperform Heliosat and generalizes well to other climate zones
• A Match Made in Heaven? AI-driven Matching of Vulnerabilities and Security Unit Tests
• Variational decision diagrams for quantum-inspired machine learning applications
• Excess Description Length of Learning Generalizable Predictors
• Fast Mining and Dynamic Time-to-Event Prediction over Multi-sensor Data Streams
• Intraday spatiotemporal PV power prediction at national scale using satellite-based solar forecast models
• Smart IoT-Based Wearable Device for Detection and Monitoring of Common Cow Diseases Using a Novel Machine Learning Technique
• AgentOCR: Reimagining Agent History via Optical Self-Compression
• Neural-Symbolic Integration with Evolvable Policies
• Parallelizing Node-Level Explainability in Graph Neural Networks
• Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solution
• FibreCastML: An Open Web Platform for Predicting Electrospun Nanofibre Diameter Distributions
• Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers
• Distributed Online Convex Optimization with Efficient Communication: Improved Algorithm and Lower bounds
• Cardinality augmented loss functions
• Precision over Diversity: High-Precision Reward Generalizes to Robust Instruction Following
• On the Definition and Detection of Cherry-Picking in Counterfactual Explanations
• On the Hidden Objective Biases of Group-based Reinforcement Learning
• HMVI: Unifying Heterogeneous Attributes with Natural Neighbors for Missing Value Inference
• Approximate equivariance via projection-based regularisation
• A Data-Driven Predictive Framework for Inventory Optimization Using Context-Augmented Machine Learning Models
• DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights
• Milestones over Outcome: Unlocking Geometric Reasoning with Sub-Goal Verifiable Reward
• Exploring Student Expectations and Confidence in Learning Analytics
• Sequential Subspace Noise Injection Prevents Accuracy Collapse in Certified Unlearning
• Safe Continual Reinforcement Learning Methods for Nonstationary Environments. Towards a Survey of the State of the Art
• FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts
• An interpretable data-driven approach to optimizing clinical fall risk assessment
• EARL: Energy-Aware Optimization of Liquid State Machines for Pervasive AI
• Robust Reasoning as a Symmetry-Protected Topological Phase
• Optimal Lower Bounds for Online Multicalibration
• TeleTables: A Benchmark for Large Language Models in Telecom Table Interpretation
• FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback
• Beyond Interaction Effects: Two Logics for Studying Population Inequalities
• Automated Reproducibility Has a Problem Statement Problem
• SAGE-32B: Agentic Reasoning via Iterative Distillation
• Scaling Trends for Multi-Hop Contextual Reasoning in Mid-Scale Language Models
• Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models
• State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space
• Systems Explaining Systems: A Framework for Intelligence and Consciousness
• From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
• A Future Capabilities Agent for Tactical Air Traffic Control
• Human-in-the-Loop Testing of AI Agents for Air Traffic Control with a Regulated Assessment Framework
• Correct and Weight: A Simple Yet Effective Loss for Implicit Feedback Recommendation
• Comparative Analysis of Custom CNN Architectures versus Pre-trained Models and Transfer Learning: A Study on Five Bangladesh Datasets
• Disco-RAG: Discourse-Aware Retrieval-Augmented Generation
• Transformer-based Multi-agent Reinforcement Learning for Separation Assurance in Structured and Unstructured Airspaces
• Learning Multinomial Logits in $O(n \log n)$ time
• Large Language Models for Detecting Cyberattacks on Smart Grid Protective Relays
• SpectraFormer: an Attention-Based Raman Unmixing Tool for Accessing the Graphene Buffer-Layer Signature on SiC
• Re-Rankers as Relevance Judges
• Concept Tokens: Learning Behavioral Embeddings Through Concept Definitions
• SampoNLP: A Self-Referential Toolkit for Morphological Analysis of Subword Tokenizers
• Convergence Rates for Learning Pseudo-Differential Operators
• Prediction of Cellular Malignancy Using Electrical Impedance Signatures and Supervised Machine Learning
• The Minary Primitive of Computational Autopoiesis
• Towards Spatio-Temporal Extrapolation of Phase-Field Simulations with Convolution-Only Neural Networks
• Multiagent Reinforcement Learning with Neighbor Action Estimation
• Bridging Distance and Spectral Positional Encodings via Anchor-Based Diffusion Geometry Approximation
• Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data
• Paradoxical noise preference in RNNs
• Neurosymbolic Retrievers for Retrieval-augmented Generation
• Sci-Reasoning: A Dataset Decoding AI Innovation Patterns
• On the Limitations of Rank-One Model Editing in Answering Multi-hop Questions
• Crystal Generation using the Fully Differentiable Pipeline and Latent Space Optimization
• DP-MGTD: Privacy-Preserving Machine-Generated Text Detection via Adaptive Differentially Private Entity Sanitization
• Succeeding at Scale: Automated Multi-Retriever Fusion and Query-Side Adaptation for Multi-Tenant Search
• Mechanism Design for Federated Learning with Non-Monotonic Network Effects
• Tape: A Cellular Automata Benchmark for Evaluating Rule-Shift Generalization in Reinforcement Learning
• TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning
• Prior-Informed Zeroth-Order Optimization with Adaptive Direction Alignment for Memory-Efficient LLM Fine-Tuning
• The Role of Quantum in Hybrid Quantum-Classical Neural Networks: A Realistic Assessment
• Differential syntactic and semantic encoding in LLMs
• Measurement-Consistent Langevin Corrector: A Remedy for Latent Diffusion Inverse Solvers
• MPM-LLM4DSE: Reaching the Pareto Frontier in HLS with Multimodal Learning and LLM-Driven Exploration
• The Forgotten Shield: Safety Grafting in Parameter-Space for Medical MLLMs
• Green MLOps: Closed-Loop, Energy-Aware Inference with NVIDIA Triton, FastAPI, and Bio-Inspired Thresholding
• Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
• Learning to Reason: Temporal Saliency Distillation for Interpretable Knowledge Transfer
• MemKD: Memory-Discrepancy Knowledge Distillation for Efficient Time Series Classification
• Making Tunable Parameters State-Dependent in Weather and Climate Models with Reinforcement Learning
• Predictable Gradient Manifolds in Deep Learning: Temporal Path-Length and Intrinsic Rank as a Complexity Regime
• Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMs
• Generation of synthetic delay time series for air transport applications
• LEGATO: Good Identity Unlearning Is Continuous
• Mitigating Position-Shift Failures in Text-Based Modular Arithmetic via Position Curriculum and Template Diversity
• Enhancing Robustness of Asynchronous EEG-Based Movement Prediction using Classifier Ensembles
• Online Action-Stacking Improves Reinforcement Learning Performance for Air Traffic Control
• ArtCognition: A Multimodal AI Framework for Affective State Sensing from Visual and Kinematic Drawing Cues
• Transformer-Based Multi-Modal Temporal Embeddings for Explainable Metabolic Phenotyping in Type 1 Diabetes
• Quantifying the Effect of Test Set Contamination on Generative Evaluations
• Causally-Aware Information Bottleneck for Domain Adaptation
• Phasor Agents: Oscillatory Graphs with Three-Factor Plasticity and Sleep-Staged Learning
• Survival Dynamics of Neural and Programmatic Policies in Evolutionary Reinforcement Learning
• Machine Learning Model for Sparse PCM Completion
• Aligned explanations in neural networks
• Enhanced-FQL($\lambda$), an Efficient and Interpretable RL with novel Fuzzy Eligibility Traces and Segmented Experience Replay
• Rate or Fate? RLV$^\varepsilon$R: Reinforcement Learning with Verifiable Noisy Rewards
• Distribution-Guided and Constrained Quantum Machine Unlearning
• Improving and Accelerating Offline RL in Large Discrete Action Spaces with Structured Policy Initialization
• When Predictions Shape Reality: A Socio-Technical Synthesis of Performative Predictions in Machine Learning
• Explainable Admission-Level Predictive Modeling for Prolonged Hospital Stay in Elderly Populations: Challenges in Low- and Middle-Income Countries
• Using Large Language Models to Detect Socially Shared Regulation of Collaborative Learning
• Meta-probabilistic Modeling
• When Models Manipulate Manifolds: The Geometry of a Counting Task
• Hybrid Federated Learning for Noise-Robust Training
• IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation
• Surface-based Molecular Design with Multi-modal Flow Matching
• TSSR: Two-Stage Swap-Reward-Driven Reinforcement Learning for Character-Level SMILES Generation
• Not All Steps are Informative: On the Linearity of LLMs' RLVR Training
• Timeliness-Oriented Scheduling and Resource Allocation in Multi-Region Collaborative Perception
• GEnSHIN: Graphical Enhanced Spatio-temporal Hierarchical Inference Network for Traffic Flow Prediction
• Improving Semi-Supervised Contrastive Learning via Entropy-Weighted Confidence Integration of Anchor-Positive Pairs
• A Vision for Multisensory Intelligence: Sensing, Synergy, and Science
• Spatial-Temporal Feedback Diffusion Guidance for Controlled Traffic Imputation
• FedKDX: Federated Learning with Negative Knowledge Distillation for Enhanced Healthcare AI Systems
• Density Matrix RNN (DM-RNN): A Quantum Information Theoretic Framework for Modeling Musical Context and Polyphony
• DeepHalo: A Neural Choice Model with Controllable Context Effects
• Learning Dynamics in RL Post-Training for Language Models
• Estimating Causal Effects in Gaussian Linear SCMs with Finite Data
• Nightmare Dreamer: Dreaming About Unsafe States And Planning Ahead
• Do LLMs Benefit from User and Item Embeddings in Recommendation Tasks?
• A zone-based training approach for last-mile routing using Graph Neural Networks and Pointer Networks
• MQ-GNN: A Multi-Queue Pipelined Architecture for Scalable and Efficient GNN Training
• GPU-Accelerated INT8 Quantization for KV Cache Compression in Large Language Models