AI News

Riemannian Structure and Optimization for a Class of Low-Parametric Orthogonal Matrices (arxiv.org)

Linear RNN Scaling Laws: When Longer Sequences Beat More Sequences (arxiv.org)

I-SplineFlow: Learning Monotone Spline Stochastic Interpolant Schedulers for Few-Step Generation (arxiv.org)

CS-WCP: Robust Conformal Sets for LLM-Judge Traffic Shifts with Uncertain Group Proportions (arxiv.org)

Semantic Self-Distillation for Language Model Uncertainty (arxiv.org)

When Accuracy Gaps Fail to Certify: Auditing Cross-Domain Recalibration of LLM Judges (arxiv.org)

Quality over Quantity: Semi-Supervised Detection of Illicit Bitcoin Flows via Feature Engineering (arxiv.org)

Binary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output Dimensions (arxiv.org)

Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure (arxiv.org)

Spread and Scale: What Determines Whether Test-Time Budget Allocation Pays (arxiv.org)

Global tree forecasters collapse at the hierarchical aggregate: a five-panel failure characterization (arxiv.org)

False-science induction in autonomous scientific discovery (arxiv.org)

Evaluation Choices Decide the Forecasting Leaderboard: Evidence from a Production Marketplace Panel (arxiv.org)

A Shared Encoder Is Not a Shared Task: Conditional Comparison for Deep Expert Pools (arxiv.org)

What Changed? Drift Detection with Real, Virtual, and Incomparable Diagnosis (arxiv.org)

Exact Minimax One-Bit Unbiased Compression: Heavy-Tail Necessity and Finite-Randomness Approximation (arxiv.org)

From Reasoning Strings to Partial Orders: Verifier-Certified Rule Transport through Quotient Policy Optimization (arxiv.org)

CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation (arxiv.org)

When Adaptation Hurts: Split Sensitivity and Person-Level Negative Transfer in Federated Wearable Onboarding (arxiv.org)

Learning to Detect Symbolic Failure: Machine Learning and the Limits of Black-Scholes (arxiv.org)

Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning (arxiv.org)

Limiting-Kernel Q($\lambda$): Bridging Short and Long Horizons (arxiv.org)

What Do Tabular Foundation Models Compute In Context? In-Situ Representation Refinement through Attention-Gated Updates (arxiv.org)

Robust Adversarial Reinforcement Learning with Risk Sensitivity and Critic Consistency Regularization (arxiv.org)

A Scalable Multi-Robot Framework for Decentralized and Asynchronous Perception-Action-Communication Loops (arxiv.org)

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks (arxiv.org)

Retrieval Augmented (Knowledge Graph), and Large Language Model-Driven Design Structure Matrix (DSM) Generation of Cyber-Physical Systems (arxiv.org)

Where Should I Join? Robot Group Joining via Language-Guided Goal Prediction (arxiv.org)

Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark (arxiv.org)

FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation (arxiv.org)

Learning Local Heterogeneity and Cross-Region Context for Large-Scale Traffic Forecasting (arxiv.org)

Pheno-GS: Phenoscape-scale Geodesic Sinkhorn (arxiv.org)

AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios (arxiv.org)

MicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and Inference (arxiv.org)

Hidden not Deleted: How Networks Suppress Entangled Features (arxiv.org)

The Capability Manifold and ML Scaling Laws (arxiv.org)

Does Step Law Transfer to Small-Scale Language Models? An Empirical Recalibration Below 59M Parameters (arxiv.org)

VCMM: Variance-Calibrated Momentum for Multimodal Learning (arxiv.org)

DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment (arxiv.org)

Ask Which, Not How Good: Sizing Benchmarks Scored by an LLM (arxiv.org)

MemBodied: Recurrent Associative Memory for Vision-Language-Action Models (arxiv.org)

Controlling Collectives of AI Agents in Reasoning Space with Spatial Transformers (arxiv.org)

Beyond Poetry: Can Large Language Models Generate Classical Arabic Maqamat? (arxiv.org)

Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification (arxiv.org)

TNLearn: An Open Source Python Package for Task-based Neurons (arxiv.org)

From Agent Output to Authorized Transition (arxiv.org)

PhyMo: A Physical-Field Modality for Multimodal AI4Physics (arxiv.org)

EBRL: Asynchronous Embodied RL by Multi-Grained Resource Management (arxiv.org)

ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning (arxiv.org)

Optimizing watermarks for large language models (arxiv.org)