AI News

CC-AOS: Cost- and Horizon-Conditioned Amortized Backward Induction for Finite-Horizon Optimal Stopping (arxiv.org)

Online Fair Division with Budget Constraints (arxiv.org)

Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models (arxiv.org)

KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability (arxiv.org)

Event Driven Clustering Algorithm (arxiv.org)

Unequal Trips, Unequal Places: Diagnosing and Mitigating Delay Inequity in Autonomous Vehicle Fleet Coordination (arxiv.org)

Simulating Tenant Responses to Energy Policy Interventions with Transaction-Cost-Aware LLM Age (arxiv.org)

PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation (arxiv.org)

To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion (arxiv.org)

MMOE: Modernizing Diffusion Transformers with Efficient Expert Design (arxiv.org)

Extending Desbordante with Probabilistic Functional Dependency Discovery Support (arxiv.org)

An empirical investigation into the properties of standard word embeddings (arxiv.org)

A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever (arxiv.org)

Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification (arxiv.org)

On a linear fused Gromov-Wasserstein distance for graph structured data (arxiv.org)

Beyond Scale and Generation: Understanding Language Model-based Entity Matching (arxiv.org)

AIR-BENCH Live: An Evolving Safety Benchmark for Foundation Models (arxiv.org)

Music-Source-Separation-Training (MSST): A Unified Framework for Training and Evaluating Music Demixing Models (arxiv.org)

Constraint-Bound Agnostic Bayesian Optimization: One Model for All Thresholds (arxiv.org)

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift (arxiv.org)

LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports (arxiv.org)

Epistemic Norms for AI Safety and Alignment Research (arxiv.org)

BERT-based Models vs. Large Language Models for Low-Resource Named Entity Recognition: A Comparative Study on Marathi (arxiv.org)

Procedural Content Generation via Generative Artificial Intelligence (arxiv.org)

Optimizing Transformer Neural Network for Real-Time Outlier Detection on FPGAs (arxiv.org)

RareLens: Towards End-to-End Rare Disease Care via Aligning Divergent Large Language Model Reasoning (arxiv.org)

Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement (arxiv.org)

CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation (arxiv.org)

SymStep: Symbolic Step Verification for Logical Reasoning (arxiv.org)

AgentOmnia: Scaling Agentic Models for Full-Scenario Applications (arxiv.org)

MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models (arxiv.org)

Compiler-Grounded Hierarchical Diagnosis for LLM-Based Triton Kernel Optimization (arxiv.org)

Learning from the Descent Direction: Adaptive Gradient Descent under One-Sided H\"older Regularity (arxiv.org)

DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data (arxiv.org)

Compressing LLMs with MoP: Mixture of Pruners (arxiv.org)

Exact Evaluation of the Accuracy of Diffusion Models for Inverse Problems with Gaussian Data Distributions (arxiv.org)

From Execution to Capability: Scientific Experience Consolidation via Procedural Knowledge Synthesis (arxiv.org)

From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search (arxiv.org)

Spatial Prediction of Soil Microplastics and Organic Matter Using Graph Attention Networks (arxiv.org)

TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation (arxiv.org)

Multimodal Surface EMG Hand Gesture Recognition Using Query-Based Transformers for Prosthetic Control (arxiv.org)

Asymmetric Hierarchical Anchoring for Robust Audio-Visual Cross-Modal Generalization (arxiv.org)

MIME: Multimodal Interactive Motion Encoder (arxiv.org)

DSCH-Loss: A Dynamic Semantic Channel Objective for Deep Semantic Hashing (arxiv.org)

Visible-Light Imaging Diagnosis of Neutral Particle Emission Tomography in the Tokamak Divertor: An Efficient Transformer-based Surrogate Model (arxiv.org)

TRUAV: Distributed Multi-Agent Reinforcement Learning for Trajectory Planning and Routing Enhancement in UAV-Aided IoT-Enabled VANETs (arxiv.org)

Falsifiable Commitment Planning for Self-Correcting Web Agents (arxiv.org)

Hallucination Rates in Language Generation (arxiv.org)

Frustratingly Simple Black-Box Adaptation of Language Models via Logit Bias (arxiv.org)

Numerical Investigation of Sequence Modeling Theory using Controllable Memory Functions (arxiv.org)