AI Research News Feeds for October 13th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• SQ-GAN: Semantic Image Communications Using Masked Vector Quantization
• CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection
• ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition
• Differentially Private 2D Human Pose Estimation
• Deep Learning for Sports Video Event Detection: Tasks, Datasets, Methods, and Challenges
• The Role of Video Generation in Enhancing Data-Limited Action Understanding
• HoliTom: Holistic Token Merging for Fast Video Large Language Models
• SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images
• Solving Inverse Problems with FLAIR
• DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
• Contour Errors: An Ego-Centric Metric for Reliable 3D Multi-Object Tracking
• Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model
• DiffMark: Diffusion-based Robust Watermark Against Deepfakes
• Event-RGB Fusion for Spacecraft Pose Estimation Under Harsh Lighting
• SMF: Template-free and Rig-free Animation Transfer using Kinetic Codes
• Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
• LLP: LLM-based Product Pricing in E-commerce
• ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering
• Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
• NL2GenSym: Natural Language to Generative Symbolic Rules for SOAR Cognitive Architecture via Large Language Models
• Understanding the Effects of Domain Finetuning on LLMs
• Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood
• KORMo: Korean Open Reasoning Model for Everyone
• Domain-Adapted Pre-trained Language Models for Implicit Information Extraction in Crash Narratives
• Getting Your Indices in a Row: Full-Text Search for LLM Training Data for Real World
• StatEval: A Comprehensive Benchmark for Large Language Models in Statistics
• Can We Reliably Rank Model Performance across Domains without Labeled Data?
• Accent-Invariant Automatic Speech Recognition via Saliency-Driven Spectrogram Masking
• Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors
• Beyond Surface Reasoning: Unveiling the True Long Chain-of-Thought Capacity of Diffusion Large Language Models
• Hierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrieval
• A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages
• WUGNECTIVES: Novel Entity Inferences of Language Models from Discourse Connectives
• AutoPR: Let's Automate Your Academic Promotion!
• Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models
• Unleashing Perception-Time Scaling to Multimodal Reasoning Models
• Exploiting Web Search Tools of AI Agents for Data Exfiltration
• Unsupervised lexicon learning from speech is limited by representations rather than clustering
• Target speaker anonymization in multi-speaker recordings
• Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services
• On the Reliability of Large Language Models for Causal Discovery
• Augmenting Compliance-Guaranteed Customer Service Chatbots: Context-Aware Knowledge Expansion with Large Language Models
• Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers
• RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented Generation
• AnyEdit: Edit Any Knowledge Encoded in Language Models
• LightMamba: Efficient Mamba Acceleration on FPGA with Quantization and Hardware Co-design
• What Are They Filtering Out? An Experimental Benchmark of Filtering Strategies for Harm Reduction in Pretraining Datasets
• RAISE: Reinforced Adaptive Instruction Selection For Large Language Models
• Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
• Learning to Reason Across Parallel Samples for LLM Reasoning
• RedDebate: Safer Responses through Multi-Agent Red Teaming Debates
• Phonikud: Hebrew Grapheme-to-Phoneme Conversion for Real-Time Text-to-Speech
• Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study
• Chain-of-Retrieval Augmented Generation
• Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
• The Digital Mirror: Gender Bias and Occupational Stereotypes in AI-Generated Images
• Dynamic Mixture-of-Experts for Visual Autoregressive Model
• Detection of high-frequency oscillations using time-frequency analysis
• PhyDAE: Physics-Guided Degradation-Adaptive Experts for All-in-One Remote Sensing Image Restoration
• Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding
• Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
• BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities
• LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution
• Q-Router: Agentic Video Quality Assessment with Expert Model Routing and Artifact Localization
• Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering
• FOLK: Fast Open-Vocabulary 3D Instance Segmentation via Label-guided Knowledge Distillation
• Modeling Time-Lapse Trajectories to Characterize Cranberry Growth
• SegTrans: Transferable Adversarial Examples for Segmentation Models
• Defense against Unauthorized Distillation in Image Restoration via Feature Space Perturbation
• mmJoints: Expanding Joint Representations Beyond (x,y,z) in mmWave-Based 3D Pose Estimation
• Hierarchical Scheduling for Multi-Vector Image Retrieval
• HandEval: Taking the First Step Towards Hand Quality Evaluation in Generated Images
• Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
• Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
• Lesion-Aware Post-Training of Latent Diffusion Models for Synthesizing Diffusion MRI from CT Perfusion
• Visual Anomaly Detection for Reliable Robotic Implantation of Flexible Microelectrode Array
• MambaH-Fit: Rethinking Hyper-surface Fitting-based Point Cloud Normal Estimation via State Space Modelling
• GL-DT: Multi-UAV Detection and Tracking with Global-Local Integration
• Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation
• Polar Separable Transform for Efficient Orthogonal Rotation-Invariant Image Representation
• Online Topological Localization for Navigation Assistance in Bronchoscopy
• Instance-Level Generation for Representation Learning
• TARO: Toward Semantically Rich Open-World Object Detection
• Online Video Depth Anything: Temporally-Consistent Depth Prediction with Low Memory Consumption
• Cattle-CLIP: A Multimodal Framework for Cattle Behaviour Recognition
• 3D Reconstruction from Transient Measurements with Time-Resolved Transformer
• Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
• Tag-Enriched Multi-Attention with Large Language Models for Cross-Domain Sequential Recommendation
• Hallucination Filtering in Radiology Vision-Language Models Using Discrete Semantic Entropy
• MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding
• Spotlight on Token Perception for Multimodal Reinforcement Learning
• Foraging with the Eyes: Dynamics in Human Visual Gaze and Deep Predictive Modeling
• RadioFlow: Efficient Radio Map Construction Framework with Flow Matching
• Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation
• Instance-Aware Robust Consistency Regularization for Semi-Supervised Nuclei Instance Segmentation
• Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark
• Boosting Multi-modal Keyphrase Prediction with Dynamic Chain-of-Thought in Vision-Language Models
• BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception
• Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban Scenes
• Minkowski-MambaNet: A Point Cloud Framework with Selective State Space Models for Forest Biomass Quantification
• Utilizing dynamic sparsity on pretrained DETR
• Mono4DEditor: Text-Driven 4D Scene Editing from Monocular Video via Point-Level Localization of Language-Embedded Gaussians
• Dynamic Weight-based Temporal Aggregation for Low-light Video Enhancement
• PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
• Diagonal Artifacts in Samsung Images: PRNU Challenges and Solutions
• PRNet: Original Information Is All You Have
• FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
• TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control
• FSP-DETR: Few-Shot Prototypical Parasitic Ova Detection
• Vision Language Models: A Survey of 26K Papers
• SpaceVista: All-Scale Visual Spatial Reasoning from mm to km
• VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
• Look before Transcription: End-to-End SlideASR with Visually-Anchored Policy Optimization
• Interlaced dynamic XCT reconstruction with spatio-temporal implicit neural representations
• Generating Sizing Fields for Mesh Generation via GCN-based Simplification of Adaptive Background Grids
• Progressive Uncertainty-Guided Evidential U-KAN for Trustworthy Medical Image Segmentation
• FS-RWKV: Leveraging Frequency Spatial-Aware RWKV for 3T-to-7T MRI Translation
• SAM2-3dMed: Empowering SAM2 for 3D Medical Image Segmentation
• Rewiring Development in Brain Segmentation: Leveraging Adult Brain Priors for Enhancing Infant MRI Segmentation
• FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images
• Diffusion-based RGB-D Semantic Segmentation with Deformable Attention Transformer
• Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
• SkipClick: Combining Quick Responses and Low-Level Features for Interactive Segmentation in Winter Sports Contexts
• Enhancing Biomedical Named Entity Recognition using GLiNER-BioMed with Targeted Dictionary-Based Post-processing for BioASQ 2025 task 6
• Systematic Diagnosis of Brittle Reasoning in Large Language Models
• Confidence, Not Perplexity: A Better Metric for the Creative Era of LLMs
• YpathRAG:A Retrieval-Augmented Generation Framework and Benchmark for Pathology
• GraphGhost: Tracing Structures Behind Large Language Models
• Gender Bias in Large Language Models for Healthcare: Assignment Consistency and Clinical Implications
• Iterative LLM-Based Generation and Refinement of Distracting Conditions in Math Word Problems
• LLMs Show Surface-Form Brittleness Under Paraphrase Stress Tests
• JAI-1: A Thai-Centric Large Language Model
• From Simulation to Strategy: Automating Personalized Interaction Planning for Conversational Agents
• Text2Stories: Evaluating the Alignment Between Stakeholder Interviews and Generated User Stories
• Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B
• ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
• Scaling Laws for Code: A More Data-Hungry Regime
• Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning
• How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspective
• Learning What to Remember: Adaptive Probabilistic Memory Retention for Memory-Efficient Language Models
• MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding
• The Model's Language Matters: A Comparative Privacy Analysis of LLMs
• Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs
• Quality Estimation Reranking for Document-Level Translation
• FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs
• Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
• Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressions
• SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures
• Creation of the Chinese Adaptive Policy Communication Corpus
• MASA: LLM-Driven Multi-Agent Systems for Autoformalization
• DARO: Difficulty-Aware Reweighting Policy Optimization
• Decoupling Safety into Orthogonal Subspace: Cost-Efficient and Performance-Preserving Alignment for Large Language Models
• LitE-SQL: A Lightweight and Efficient Text-to-SQL Framework with Vector-based Schema Linking and Execution-Guided Self-Correction
• Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise
• Exploring Cross-Lingual Knowledge Transfer via Transliteration-Based MLM Fine-Tuning for Critically Low-resource Chakma Language
• Large Language Models Do NOT Really Know What They Don't Know
• ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability
• FrameEOL: Semantic Frame Induction using Causal Language Models
• When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
• DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation
• Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM
• Stronger Re-identification Attacks through Reasoning and Aggregation
• LLaMAX2: Your Translation-Enhanced Model also Performs Well in Reasoning
• DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
• CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation
• One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations
• MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics
• ShiZhi: A Chinese Lightweight Large Language Model for Court View Generation
• A Biophysically-Conditioned Generative Framework for 3D Brain Tumor MRI Synthesis
• A Multimodal Approach to SME Credit Scoring Integrating Transaction and Ownership Networks
• Estimating Brain Activity with High Spatial and Temporal Resolution using a Naturalistic MEG-fMRI Encoding Model
• Active Model Selection for Large Language Models
• Hybrid Models for Natural Language Reasoning: The Case of Syllogistic Logic
• D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models
• Few-shot multi-token DreamBooth with LoRa for style-consistent character generation
• Efficient Autoregressive Inference for Transformer Probabilistic Models
• Unsupervised full-field Bayesian inference of orthotropic hyperelasticity from a single biaxial test: a myocardial case study
• Interpretable Generative and Discriminative Learning for Multimodal and Incomplete Clinical Data
• Conditional Flow Matching for Bayesian Posterior Inference
• Three Birds with One Stone: Improving Performance, Convergence, and System Throughput with Nest
• From Contextual Data to Newsvendor Decisions: On the Actual Performance of Data-Driven Algorithms
• Fair Graph Machine Learning under Adversarial Missingness Processes
• FREE: The Foundational Semantic Recognition for Modeling Environmental Ecosystems
• Towards Natural Machine Unlearning
• An Imitative Reinforcement Learning Framework for Pursuit-Lock-Launch Missions
• Direct Quantized Training of Language Models with Stochastic Rounding
• A Digital Twin for Diesel Engines: Operator-infused Physics-Informed Neural Networks with Transfer Learning for Engine Health Monitoring
• Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
• Network Dynamics-Based Framework for Understanding Deep Neural Networks
• Filtering out mislabeled training instances using black-box optimization and quantum annealing
• Orthogonal Representation Learning for Estimating Causal Quantities
• Causal Additive Models with Unobserved Causal Paths and Backdoor Paths
• Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data
• Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation
• COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs
• On the Interpolation Effect of Score Smoothing in Diffusion Models
• Aggregation on Learnable Manifolds for Asynchronous Federated Optimization
• MergeBench: A Benchmark for Merging Domain-Specialized LLMs
• What's Inside Your Diffusion Model? A Score-Based Riemannian Metric to Explore the Data Manifold
• CausalDynamics: A large-scale benchmark for structural discovery of dynamical causal models
• Automated Capability Evaluation of Foundation Models
• Partition Generative Modeling: Masked Modeling Without Masks
• PrivATE: Differentially Private Confidence Intervals for Average Treatment Effects
• Epistemic Errors of Imperfect Multitask Learners When Distributions Shift
• Training-free AI for Earth Observation Change Detection using Physics Aware Neuromorphic Networks
• NIMO: a Nonlinear Interpretable MOdel
• Multi-Scale Finetuning for Encoder-based Time Series Foundation Models
• Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning
• Towards the Training of Deeper Predictive Coding Neural Networks
• Large Language Model Agent for Modular Task Execution in Drug Discovery
• Networked Information Aggregation via Machine Learning
• ROC-n-reroll: How verifier imperfection affects test-time scaling
• DQS: A Low-Budget Query Strategy for Enhancing Unsupervised Data-driven Anomaly Detection Approaches
• K-ASTRO: Structure-Aware Adaptation of LLMs for Code Vulnerability Detection
• Multiparameter regularization and aggregation in the context of polynomial functional regression
• SolNet: Open-source deep learning models for photovoltaic power forecasting across the globe
• Mini-batch Estimation for Deep Cox Models: Statistical Foundations and Practical Guidance
• Frequency-Guided Posterior Sampling for Diffusion-Based Image Restoration
• NLP-ADBench: NLP Anomaly Detection Benchmark
• Making Bias Amplification in Balanced Datasets Directional and Interpretable
• Convergence of two-timescale gradient descent ascent dynamics: finite-dimensional and mean-field perspectives
• SWE-Arena: An Interactive Platform for Evaluating Foundation Models in Software Engineering
• How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders
• Hierarchical autoregressive neural networks in three-dimensional statistical system
• Understanding and Improving Information Preservation in Prompt Compression for LLMs
• Gradient-based Sample Selection for Faster Bayesian Optimization
• What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context
• Generalized Probabilistic Approximate Optimization Algorithm
• Lizard: An Efficient Linearization Framework for Large Language Models
• Velocity and Density-Aware RRI Analysis and Optimization for AoI Minimization in IoV SPS
• Simple and Robust Forecasting of Spatiotemporally Correlated Small Earth Data with A Tabular Foundation Model
• AB-PINNs: Adaptive-Basis Physics-Informed Neural Networks for Residual-Driven Domain Decomposition
• MATT-CTR: Unleashing a Model-Agnostic Test-Time Paradigm for CTR Prediction with Confidence-Guided Inference Paths
• Bi-level Meta-Policy Control for Dynamic Uncertainty Calibration in Evidential Deep Learning
• Variability Aware Recursive Neural Network (VARNN): A Residual-Memory Model for Capturing Temporal Deviation in Sequence Regression Modeling
• When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach
• HiBBO: HiPPO-based Space Consistency for High-dimensional Bayesian Optimisation
• Diagnosing and Mitigating System Bias in Self-Rewarding RL
• FedL2T: Personalized Federated Learning with Two-Teacher Distillation for Seizure Prediction
• Constraints-of-Thought: A Framework for Constrained Reasoning in Language-Model-Guided Search
• LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data
• Slim Scheduler: A Runtime-Aware RL and Scheduler System for Efficient CNN Inference
• MagicDock: Toward Docking-oriented De Novo Ligand Design via Gradient Inversion
• The Environmental Impacts of Machine Learning Training Keep Rising Evidencing Rebound Effect
• The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
• Convergence of optimizers implies eigenvalues filtering at equilibrium
• Spatio-Temporal Graph Convolutional Networks for EV Charging Demand Forecasting Using Real-World Multi-Modal Data Integration
• Improving Anomaly Detection in Industrial Time Series: The Role of Segmentation and Heterogeneous Ensemble
• FLToP CTC: Frame-Level Token Pruning via Relative Threshold for Efficient and Memory-Saving Decoding on Diverse Platforms
• Neural Codecs as Biosignal Tokenizers
• AdaPM: a Partial Momentum Algorithm for LLM Training
• Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback
• Score-Based Density Estimation from Pairwise Comparisons
• Logits Replay + MoClip: Stabilized, Low-Cost Post-Training with Minimal Forgetting
• Agentic-KGR: Co-evolutionary Knowledge Graph Construction through Multi-Agent Reinforcement Learning
• Efficient Resource-Constrained Training of Vision Transformers via Subspace Optimization
• Robustness and Regularization in Hierarchical Re-Basin
• Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraints
• RepDL: Bit-level Reproducible Deep Learning Training and Inference
• FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
• Prime Implicant Explanations for Reaction Feasibility Prediction
• Incentivizing Time-Aware Fairness in Data Sharing
• A PCA-based Data Prediction Method
• Mitigating Model Drift in Developing Economies Using Synthetic Data and Outliers
• Large Language Model Prompt Datasets: An In-depth Analysis and Insights
• Residual-Informed Learning of Solutions to Algebraic Loops
• Safety Game: Balancing Safe and Informative Conversations with Blackbox Agentic AI using LP Solvers
• Efficient Bayesian Inference from Noisy Pairwise Comparisons
• Deep Learning to Identify the Spatio-Temporal Cascading Effects of Train Delays in a High-Density Network
• CHUCKLE -- When Humans Teach AI To Learn Emotions The Easy Way
• HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness
• Cross-Receiver Generalization for RF Fingerprint Identification via Feature Disentanglement and Adversarial Training
• What Do Temporal Graph Learning Models Learn?
• Weight Initialization and Variance Dynamics in Deep Neural Networks and Large Language Models
• Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models
• On Uniformly Scaling Flows: A Density-Aligned Approach to Deep One-Class Classification
• Interpretable Machine Learning for Predicting Startup Funding, Patenting, and Exits
• Geodesic Calculus on Latent Spaces
• CRPS-LAM: Regional ensemble weather forecasting from matching marginals
• Locally Optimal Private Sampling: Beyond the Global Minimax
• Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning
• Geo-Aware Models for Stream Temperature Prediction across Different Spatial Regions and Scales
• Automated Evolutionary Optimization for Resource-Efficient Neural Network Training
• STaTS: Structure-Aware Temporal Sequence Summarization via Statistical Window Merging
• MODE: Learning compositional representations of complex systems with Mixtures Of Dynamical Experts
• Evolutionary Computation as Natural Generative AI
• Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
• Which Is Better For Reducing Outdated and Vulnerable Dependencies: Pinning or Floating?
• Reproducible Evaluation of Data Augmentation and Loss Functions for Brain Tumor Segmentation
• PARSE: LLM Driven Schema Optimization for Reliable Entity Extraction
• Out-of-Distribution Detection in LiDAR Semantic Segmentation Using Epistemic Uncertainty from Hierarchical GMMs
• Next Semantic Scale Prediction via Hierarchical Diffusion Language Models
• QuIRK: Quantum-Inspired Re-uploading KAN
• Decoding Positive Selection in Mycobacterium tuberculosis with Phylogeny-Guided Graph Attention Models
• Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs
• Structured Output Regularization: a framework for few-shot transfer learning
• How Reliable is Language Model Micro-Benchmarking?
• A Design-based Solution for Causal Inference with Text: Can a Language Model Be Too Large?
• Understanding Exoplanet Habitability: A Bayesian ML Framework for Predicting Atmospheric Absorption Spectra
• Prioritizing Latency with Profit: A DRL-Based Admission Control for 5G Network Slices
• Detecting spills using thermal imaging, pretrained deep learning models, and a robotic platform
• Man-Made Heuristics Are Dead. Long Live Code Generators!
• Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation
• Gradient-Guided Furthest Point Sampling for Robust Training Set Selection
• A Representer Theorem for Hawkes Processes via Penalized Least Squares Minimization
• PHyCLIP: $\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning
• Mirror Flow Matching with Heavy-Tailed Priors for Generative Modeling on Convex Domains
• Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection
• Denoised Diffusion for Object-Focused Image Augmentation
• Uncolorable Examples: Preventing Unauthorized AI Colorization via Perception-Aware Chroma-Restrictive Perturbation
• Exploring Single Domain Generalization of LiDAR-based Semantic Segmentation under Imperfect Labels
• MAKO: Meta-Adaptive Koopman Operators for Learning-based Model Predictive Control of Parametrically Uncertain Nonlinear Systems
• MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation
• MCMC: Bridging Rendering, Optimization and Generative AI
• A Novel Multi-branch ConvNeXt Architecture for Identifying Subtle Pathological Features in CT Scans
• Training Feature Attribution for Vision Models
• Distributionally robust approximation property of neural networks
• Augmented data and neural networks for robust epidemic forecasting: application to COVID-19 in Italy
• Flow-Opt: Scalable Centralized Multi-Robot Trajectory Optimization with Flow Matching and Differentiable Optimization
• Provable Watermarking for Data Poisoning Attacks
• IRIS: An Iterative and Integrated Framework for Verifiable Causal Discovery in the Absence of Tabular Data
• Characterizing 5G User Throughput via Uncertainty Modeling and Crowdsourced Measurements
• Investigating the Impact of Rational Dilated Wavelet Transform on Motor Imagery EEG Decoding with Deep Learning Models
• Application of Deep Reinforcement Learning to At-the-Money S&P 500 Options Hedging
• Smart navigation of a gravity-driven glider with adjustable centre-of-mass
• Zero-shot image privacy classification with Vision-Language Models
• GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis
• Placeit! A Framework for Learning Robot Object Placement Skills
• Goal-oriented Backdoor Attack against Vision-Language-Action Models via Physical Objects
• A unified Bayesian framework for adversarial robustness
• Reliability Sensitivity with Response Gradient
• A methodology for clinically driven interactive segmentation evaluation
• Mitigating Overthinking through Reasoning Shaping
• SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
• Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
• BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards
• Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation
• StreamingVLM: Real-Time Understanding for Infinite Video Streams
• A Method to Improve the Performance of Reinforcement Learning Based on the Y Operator for a Class of Stochastic Differential Equation-Based Child-Mother Systems
• Training-Free Safe Denoisers for Safe Use of Diffusion Models
• HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions
• A Knowledge-Informed Deep Learning Paradigm for Generalizable and Stability-Optimized Car-Following Models
• GUI-Shift: Enhancing VLM-Based GUI Agents through Self-supervised Reinforcement Learning
• AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models
• ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection
• Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning
• E-ICL: Enhancing Fine-Grained Emotion Recognition through the Lens of Prototype Theory
• Confidence-weighted integration of human and machine judgments for superior decision-making
• UltraSeP: Sequence-aware Pre-training for Echocardiography Probe Movement Guidance
• Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions
• Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence
• Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training
• SwarmGPT: Combining Large Language Models with Safe Motion Planning for Drone Swarm Choreography
• Preference Discerning with LLM-Enhanced Generative Retrieval
• AD-LLM: Benchmarking Large Language Models for Anomaly Detection
• Enabling Population-Level Parallelism in Tree-Based Genetic Programming for GPU Acceleration
• OrcaLoca: An LLM Agent Framework for Software Issue Localization
• IG-MCTS: Human-in-the-Loop Cooperative Navigation under Incomplete Information
• RadVLM: A Multitask Conversational Vision-Language Model for Radiology
• Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlo
• WyckoffDiff -- A Generative Diffusion Model for Crystal Symmetry
• Contrastive Learning Augmented Social Recommendations
• Measuring directional bias amplification in image captions using predictability
• CCDP: Composition of Conditional Diffusion Policies with Guided Sampling
• Issue Localization via LLM-Driven Iterative Code Graph Searching
• Brain2Text Decoding Model Reveals the Neural Mechanisms of Visual Semantic Processing
• DeepOHeat-v1: Efficient Operator Learning for Fast and Trustworthy Thermal Simulation and Optimization in 3D-IC Design
• TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis
• Diffusion Generative Recommendation with Continuous Tokens
• Exploring human-SAV interaction using LLMs: The impact of psychological factors on user experience
• Multimodal Language Models See Better When They Look Shallower
• Cognitio Emergens: Agency, Dimensions, and Dynamics in Human-AI Knowledge Co-Creation
• System Prompt Optimization with Meta-Learning
• Collaborative Unlabeled Data Optimization
• Game of Trust: How Trustworthy Does Your Blockchain Think You Are?
• Sequential Monte Carlo for Policy Optimization in Continuous POMDPs
• DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaboration
• Beyond Demonstrations: Dynamic Vector Construction from Latent Representations
• FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information
• An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks
• Elicit and Enhance: Advancing Multimodal Reasoning in Medical Scenarios
• Robustness in Both Domains: CLIP Needs a Robust Text Encoder
• AD-EE: Early Exiting for Fast and Reliable Vision-Language Models in Autonomous Driving
• Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
• CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Models
• Symmetry in Neural Network Parameter Spaces
• Bures-Wasserstein Flow Matching for Graph Generation
• Interpretable and Granular Video-Based Quantification of Motor Characteristics from the Finger Tapping Test in Parkinson Disease
• Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System
• Tuning without Peeking: Provable Privacy and Generalization Bounds for LLM Post-Training
• AirScape: An Aerial Generative World Model with Motion Controllability
• Site-Level Fine-Tuning with Progressive Layer Freezing: Towards Robust Prediction of Bronchopulmonary Dysplasia from Day-1 Chest Radiographs in Extremely Preterm Infants
• Preprint: Poster: Did I Just Browse A Website Written by LLMs?
• A Mega-Study of Digital Twins Reveals Strengths, Weaknesses and Opportunities for Further Improvement
• How Scale Breaks "Normalized Stress" and KL Divergence: Rethinking Quality Metrics
• Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting
• Counterfactually Fair Conformal Prediction
• Transmuting prompts into weights
• SHAP-Based Supervised Clustering for Sample Classification and the Generalized Waterfall Plot
• Faithful and Interpretable Explanations for Complex Ensemble Time Series Forecasts using Surrogate Models and Forecastability Analysis
• RFOD: Random Forest-based Outlier Detection for Tabular Data
• Conformal Risk Training: End-to-End Optimization of Conformal Risk Control
• Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning
• LOTION: Smoothing the Optimization Landscape for Quantized Training
• Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inference
• Reinforcement Learning-Based Optimization of CT Acquisition and Reconstruction Parameters Through Virtual Imaging Trials
• Zero-Shot Policy Transfer in Reinforcement Learning using Buckingham's Pi Theorem
• Weights initialization of neural networks for function approximation
• PO-CKAN:Physics Informed Deep Operator Kolmogorov Arnold Networks with Chunk Rational Structure
• TAPAS: Datasets for Learning the Learning with Errors Problem
• Edu-EmotionNet: Cross-Modality Attention Alignment with Temporal Feedback Loops
• TinyGraphEstimator: Adapting Lightweight Language Models for Graph Structure Inference
• Long-Tailed Recognition via Information-Preservable Two-Stage Learning
• The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective
• On the Alignment Between Supervised and Self-Supervised Contrastive Learning
• Sparse components distinguish visual pathways & their alignment to neural networks
• Multi-fidelity Batch Active Learning for Gaussian Process Classifiers
• An Improved Model-Free Decision-Estimation Coefficient with Applications in Adversarial MDPs
• MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces
• Deceptive Exploration in Multi-armed Bandits
• SkipSR: Faster Super Resolution with Token Skipping
• Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective
• Adaptive Science Operations in Deep Space Missions Using Offline Belief State Planning
• $\mathsf{P} \neq \mathsf{NP}$: A Non-Relativizing Proof via Quantale Weakness and Geometric Complexity
• D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition
• McMining: Automated Discovery of Misconceptions in Student Code
• CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization
• Reinforcement Learning-Driven Edge Management for Reliable Multi-view 3D Reconstruction
• Repository-Aware File Path Retrieval via Fine-Tuned LLMs
• Time-Aware Feature Selection: Adaptive Temporal Masking for Stable Sparse Autoencoder Training
• Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models
• Slicing Is All You Need: Towards A Universal One-Sided Algorithm for Distributed Matrix Multiplication
• Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval
• ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling
• Designing and Evaluating an AI-driven Immersive Multidisciplinary Simulation (AIMS) for Interprofessional Education
• Exploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVR
• HES-SQL: Hybrid Reasoning for Efficient Text-to-SQL with Structural Skeleton Guidance
• Pinpointing crucial steps: Attribution-based Credit Assignment for Verifiable Reinforcement Learning
• A Unified Biomedical Named Entity Recognition Framework with Large Language Models
• A Frequency-Domain Analysis of the Multi-Armed Bandit Problem: A New Perspective on the Exploration-Exploitation Trade-off
• Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenders
• RO-Bench: Large-scale robustness evaluation of MLLMs with text-driven counterfactual videos
• SHERLOCK: Towards Dynamic Knowledge Adaptation in LLM-enhanced E-commerce Risk Management
• A Human Behavioral Baseline for Collective Governance in Software Projects
• Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation
• Learning Regularizers: Learning Optimizers that can Regularize
• SEER: Sustainability Enhanced Engineering of Software Requirements
• PlatformX: An End-to-End Transferable Platform for Energy-Efficient Neural Architecture Search
• Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent Evaluation
• SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions
• On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
• DiTSinger: Scaling Singing Voice Synthesis with Diffusion Transformer and Implicit Alignment
• Value-State Gated Attention for Mitigating Extreme-Token Phenomena in Transformers
• D\'er\'everb\'eration non-supervis\'ee de la parole par mod\`ele hybride
• Robust Driving Control for Autonomous Vehicles: An Intelligent General-sum Constrained Adversarial Reinforcement Learning Approach
• Cost-Efficient Long Code Translation using LLMs while Leveraging Identifier Replacements
• Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation
• Emotion-Disentangled Embedding Alignment for Noise-Robust and Cross-Corpus Speech Emotion Recognition
• Training Models to Detect Successive Robot Errors from Human Reactions
• AI and Human Oversight: A Risk-Based Framework for Alignment
• When a Robot is More Capable than a Human: Learning from Constrained Demonstrators
• MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples
• SOS: Synthetic Object Segments Improve Detection, Segmentation, and Grounding
• On the Fairness of Privacy Protection: Measuring and Mitigating the Disparity of Group Privacy Risks for Differentially Private Machine Learning
• MSDM: Generating Task-Specific Pathology Images with a Multimodal Conditioned Diffusion Model for Cell and Nuclei Segmentation
• Controlled Personalization in Legacy Media Online Services: A Case Study in News Recommendation
• Federated Data Analytics for Cancer Immunotherapy: A Privacy-Preserving Collaborative Platform for Patient Management
• Cross-Representation Benchmarking in Time-Series Electronic Health Records for Clinical Outcome Prediction
• On the Implicit Adversariality of Catastrophic Forgetting in Deep Continual Learning
• Modern Deep Learning Approaches for Cricket Shot Classification: A Comprehensive Baseline Study
• Towards Safer and Understandable Driver Intention Prediction
• Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
• DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction
• Clear Roads, Clear Vision: Advancements in Multi-Weather Restoration for Smart Transportation
• Diagnosing Shoulder Disorders Using Multimodal Large Language Models and Consumer-Grade Cameras
• CrisiText: A dataset of warning messages for LLM training in emergency communication
• Obstacle Avoidance using Dynamic Movement Primitives and Reinforcement Learning
• Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
• SynthID-Image: Image watermarking at internet scale
• Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation
• CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts
• CapGeo: A Caption-Assisted Approach to Geometric Reasoning
• A Model-Driven Engineering Approach to AI-Powered Healthcare Platforms
• Verifying Chain-of-Thought Reasoning via Its Computational Graph
• Rate optimal learning of equilibria from data
• Randomized HyperSteiner: A Stochastic Delaunay Triangulation Heuristic for the Hyperbolic Steiner Minimal Tree
• FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference
• deep-REMAP: Probabilistic Parameterization of Stellar Spectra Using Regularized Multi-Task Learning
• The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton
• Task-Level Insights from Eigenvalues across Sequence Models
• Design Principles for Sequence Models via Coefficient Dynamics
• Identifying & Interactively Refining Ambiguous User Goals for Data Visualization Code Generation
• ChoirRec: Semantic User Grouping via LLMs for Conversion Rate Prediction of Low-Activity Users
• Beyond Single-Granularity Prompts: A Multi-Scale Chain-of-Thought Prompt Learning for Graph
• On the Representations of Entities in Auto-regressive Large Language Models
• The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approach
• Bandits with Single-Peaked Preferences and Limited Resources
• SilvaScenes: Tree Segmentation and Species Classification from Under-Canopy Images in Natural Forests
• Failure Prediction at Runtime for Generative Robot Policies
• Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
• Scalable Multi-Agent Path Finding using Collision-Aware Dynamic Alert Mask and a Hybrid Execution Strategy
• Multimodal Policy Internalization for Conversational Agents
• Performance Analysis of Machine Learning Algorithms in Chronic Kidney Disease Prediction
• Precoder Design in Multi-User FDD Systems with VQ-VAE and GNN
• Autonomous Soft Robotic Guidewire Navigation via Imitation Learning
• FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation
• EcphoryRAG: Re-Imagining Knowledge-Graph RAG via Human Associative Memory
• DualResearch: Entropy-Gated Dual-Graph Retrieval for Answer Reconstruction
• Semantic-Condition Tuning: Fusing Graph Context with Large Language Models for Knowledge Graph Completion
• Tiny-R1V: Lightweight Multimodal Unified Reasoning Model via Model Merging
• TripScore: Benchmarking and rewarding real-world travel planning with fine-grained evaluation
• RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
• Repairing Regex Vulnerabilities via Localization-Guided Instructions
• Auto-scaling Continuous Memory for GUI Agent
• Humanoid Artificial Consciousness Designed with Large Language Model Based on Psychoanalysis and Personality Theory
• MEC$^3$O: Multi-Expert Consensus for Code Time Complexity Prediction
• OSCAR: Orthogonal Stochastic Control for Alignment-Respecting Diversity in Flow Matching
• Physics-Informed High-order Graph Dynamics Identification Learning for Predicting Complex Networks Long-term Dynamics
• Leading the Follower: Learning Persuasive Agents in Social Deduction Games
• PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning
• Dr. Bias: Social Disparities in AI-Powered Medical Guidance
• Comparing Knowledge Source Integration Methods for Optimizing Healthcare Knowledge Fusion in Rescue Operation
• RegexPSPACE: A Benchmark for Evaluating LLM Reasoning on PSPACE-complete Regex Problems
• Fundamentals of Building Autonomous LLM Agents
• Localist LLMs -- A Mathematical Framework for Dynamic Locality Control
• Toward Mechanistic Explanation of Deductive Reasoning in Language Models
• Sequence Variables: A Constraint Programming Computational Domain for Routing and Sequencing
• Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges
• Titans Revisited: A Lightweight Reimplementation and Critical Analysis of a Test-Time Memory Model
• Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse
• GraphMERT: Efficient and Scalable Distillation of Reliable Knowledge Graphs from Unstructured Data
• LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
• Deep Multimodal Subspace Clustering Networks
• Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training
• Deep Sparse Representation-based Classification
• PyNoetic: A modular python framework for no-code development of EEG brain-computer interfaces
• Comparative Analysis of Large Language Models for the Machine-Assisted Resolution of User Intentions
• AgenticAD: A Specialized Multiagent System Framework for Holistic Alzheimer Disease Management
• LadderSym: A Multimodal Interleaved Transformer for Music Practice Error Detection
• Evaluating Hallucinations in Multimodal LLMs with Spoken Queries under Diverse Acoustic Conditions
• Articulation-Informed ASR: Integrating Articulatory Features into ASR via Auxiliary Speech Inversion and Cross-Attention Fusion
• Dynamic Stress Detection: A Study of Temporal Progression Modelling of Stress in Speech
• EGSTalker: Real-Time Audio-Driven Talking Head Generation with Efficient Gaussian Deformation
• Beyond CNNs: Efficient Fine-Tuning of Multi-Modal LLMs for Object Detection on Low-Data Regimes
• The Enduring Dominance of Deep Neural Networks: A Critical Analysis of the Fundamental Limitations of Quantum Machine Learning and Spiking Neural Networks
• Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
• Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech
• BaldWhisper: Faster Whisper with Head Shearing and Layer Merging
• Recover-LoRA: Data-Free Accuracy Recovery of Degraded Language Models via Low-Rank Adaptation
• Mnemosyne: An Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs
• LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback
• Toward a Safer Web: Multilingual Multi-Agent LLMs for Mitigating Adversarial Misinformation Attacks
• Centering Emotion Hotspots: Multimodal Local-Global Fusion and Cross-Modal Alignment for Emotion Recognition in Conversations
• MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation
• Relative Positioning Based Code Chunking Method For Rich Context Retrieval In Repository Level Code Completion Task With Code Language Model
• Impact of LLMs on Team Collaboration in Software Development
• From What to Why: Thought-Space Recommendation with Small Language Models
• Hi-OSCAR: Hierarchical Open-set Classifier for Human Activity Recognition
• Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
• Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools
• Energy-Driven Steering: Reducing False Refusals in Large Language Models
• Upfront Chain-of-Thought: A Cooperative Framework for Chain-of-Thought Compression
• Inverse-Free Wilson Loops for Transformers: A Practical Diagnostic for Invariance and Order Sensitivity
• Formalizing Style in Personal Narratives
• Knowledge Graph Sparsification for GNN-based Rare Disease Diagnosis
• A 3D Generation Framework from Cross Modality to Parameterized Primitive
• Inner-Instance Normalization for Time Series Forecasting
• Provably Robust Adaptation for Language-Empowered Foundation Models
• CATS-Linear: Classification Auxiliary Linear Model for Time Series Forecasting
• DPCformer: An Interpretable Deep Learning Model for Genomic Prediction in Crops
• A Novel Framework for Augmenting Rating Scale Tests with LLM-Scored Text Data
• Faver: Boosting LLM-based RTL Generation with Function Abstracted Verifiable Middleware
• RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
• dInfer: An Efficient Inference Framework for Diffusion Language Models
• RAG4Tickets: AI-Powered Ticket Resolution via Retrieval-Augmented Generation on JIRA and GitHub Data
• FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching
• BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
• ConPoSe: LLM-Guided Contact Point Selection for Scalable Cooperative Object Pushing
• In-Context Learning for Non-Stationary MIMO Equalization
• Enhancing Self-Supervised Learning with Semantic Pairs A New Dataset and Empirical Study
• When to Reason: Semantic Router for vLLM
• Coordinates from Context: Using LLMs to Ground Complex Location References
• Graph Diffusion Transformers are In-Context Molecular Designers
• SAFER-AiD: Saccade-Assisted Foveal-peripheral vision Enhanced Reconstruction for Adversarial Defense
• Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings
• Re-Identifying K\={a}k\={a} with AI-Automated Video Key Frame Extraction
• Measuring Moral LLM Responses in Multilingual Capacities
• Guiding Exploration in Reinforcement Learning Through LLM-Augmented Observations
• Hypothesis Hunting with Evolving Networks of Autonomous Scientific Agents
• Optimizing delivery for quick commerce factoring qualitative assessment of generated routes
• Unified World Models: Memory-Augmented Planning and Foresight for Visual Navigation
• Robust Heuristic Algorithm Design with LLMs
• COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context
• Everyone prefers human writers, including AI
• What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment
• ReviewerToo: Should AI Join The Program Committee? A Look At The Future of Peer Review
• GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare
• LM Fight Arena: Benchmarking Large Multimodal Models via Game Competition
• RADAR: Mechanistic Pathways for Detecting Data Contamination in LLM Evaluation