AI News

Memory-Augmented Online Test-Time Adaptation for EEG Motor Imagery via Perturbation Consistency and Confidence Calibration (arxiv.org)

Action Learning for Scientific Simulations (arxiv.org)

Visualizing and Interpreting Temporal Care Team Dynamics for Cancer Survival Risk Analysis (arxiv.org)

S-EDL: Eliciting Self-Evidence from Sequence Likelihoods for Semantic Calibration of LLMs (arxiv.org)

Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research (arxiv.org)

MemoryTax: The Bitter Lesson of Agent Memory (arxiv.org)

Rethinking Sequence Compression with Test-time Regression (arxiv.org)

Same Probabilities, Different Advice: Gain-Loss Framing Effects in High-Stakes LLM Decision Support (arxiv.org)

Learning What to Remember: Resource-Efficient Self-Improvement for Lifelong Agents (arxiv.org)

Random Initialization as a Baseline for Time Series Foundation Models (arxiv.org)

ACTIVA: Amortized Causal Effect Estimation via Variational Autoencoders (arxiv.org)

Robot Learning with Visual Predicted Force (arxiv.org)

Wavenumber-Aware Deep Learning for Robust Analysis of Raman Spectra (arxiv.org)

Optimal Multitask Representations Under a Rate Constraint: An Information Bottleneck Analysis (arxiv.org)

Retrieval Augmented Generation Compositionality (arxiv.org)

Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use (arxiv.org)

The End of Consensus Research? (arxiv.org)

Towards Faithful Data Selection: Statistical Limits and Scalable Algorithms (arxiv.org)

AnnoCaseLaw: Legal Annotation Benchmark of Civil Negligence (arxiv.org)

Every Part Has Its Role: Part-of-Speech Effects in LLM Post-Training (arxiv.org)

UNIVERS: Learning UNIversal Voxel-wise Embedding via Randomized Synthesis for generalizable one-shot landmark localization (arxiv.org)

Model Capacity Frontier: A Development Framework for LLM-Supported Social Simulation (arxiv.org)

PhysiCalWorld: In-Context Physics Calibration for World Models (arxiv.org)

Adaptive Deadline- and Energy-Aware Caching Algorithms in Dynamic Multi-UAV Edge Networks (arxiv.org)

HiddenLens: A Multi-Layer LLM Framework for Detecting and Resolving Hidden Assumptions in Software Requirements (arxiv.org)

Sparse Equation Matching: A Derivative-Free Learning for General-Order Dynamical Systems (arxiv.org)

An Eco-Friendly Tourism Trip Planner Driven by Z-Number Uncertainty: Evidence from Baku, Dubai, Abu Dhabi, Tashkent, and Istanbul (arxiv.org)

DiffLTM: Continuous Diffusions Large Tabular Models for Conditional Generation (arxiv.org)

Graph Topology Meets Energy-Driven Pathfinding: Preserving Contextual Consistency in Retrieval-Augmented Generation (arxiv.org)

A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse (arxiv.org)

LLM2Cert: LLM Synthesis of Certificates with SMT/Lean Verification (arxiv.org)

Quantum-Inspired Optimization Process for Data Imputation (arxiv.org)

MarkTune: Improving the Quality-Detectability Trade-off in Model-Embedded LLM Watermarking (arxiv.org)

Primal-Dual Representation Learning for Low-Rank Constrained MDPs (arxiv.org)

Algorithmic Reflectivity in Large Language Models: Methodological Study of Linguistic Structure in Mentalization (arxiv.org)

DiaLong: Benchmarking Reminiscence in Long-Context Dialogues (arxiv.org)

Metamodel-Guided LLM Decoding for Consistent DSL Generation (arxiv.org)

EgoHand: Monocular 3D Hand Reconstruction from Egocentric Video (arxiv.org)

DashVMC: Real-Time Discrete World Model Control in Geometry Dash (arxiv.org)

OpenAttention: One Percent Is Enough with Tail Proxies (arxiv.org)

TerraTransfer++: Demonstration-Free End-to-End Planner (arxiv.org)

Controlling Output Rankings in LLM-Based Search via Generative Engine Optimization (arxiv.org)

Every Alarm Has a Cause: An Open Generator of Telecom Alarm Storms with Exact Root Causes, Bound to NORIA-O, RFC 8632 and TMF642 (arxiv.org)

Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models (arxiv.org)

Benchmarking Model Compression Techniques Across Heterogeneous Edge Platforms: A Predictive Maintenance Use Case for Rotating Machinery (arxiv.org)

AgriVLN: Vision-and-Language Navigation for Agricultural Robots (arxiv.org)

Is the Judge Its Twin? Post-training makes a model's writing more predictable but barely moves its taste, as a judge, toward predictable writing (arxiv.org)

Conflicted Records: Typed Adversarial Contracts for Auditable LLM Output Quality Enforcement (arxiv.org)

Robot Generalization Beyond Volume: The Diversity Path via Zero-Shot Capabilities (arxiv.org)

PHD-Hand: A Printable Humanoid Dexterous Hand with Linkage-Driven 3-DOA Digits (arxiv.org)