AI News

Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs (arxiv.org)

One Loop, Two Gains: Can Active Learning win the Lottery for Free? (arxiv.org)

Show-Harness: Just a VLM Agent Can Play Robots (arxiv.org)

GANDR: Claim Auditing for Verifiable Legal Answer Generation (arxiv.org)

ORCH: Organizational Principles Enable Collective Intelligence in Embodied AI (arxiv.org)

DiSCo: A Distribution-First Steering and Cultural Prior Evaluation Framework for Measuring Cultural Preference Bias in LLMs (arxiv.org)

A-JIT: Agentic Just-In-Time Software Construction (arxiv.org)

LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation (arxiv.org)

Hierarchical and Permutation-Invariant Feature Transformation Learning via Policy-Guided Embedding Search (arxiv.org)

Learning structural balance of graphs from quantum spectral features (arxiv.org)

Optimizing AI Inference Across the Deployment Stack (arxiv.org)

Negative Self-Distillation: Learning to Reason by Avoiding Flaws (arxiv.org)

Geospatial Foundation Models Capture Health-Relevant Dimensions of Place Beyond Conventional Social Risk Indices (arxiv.org)

On the Societal Impact of Machine Learning (arxiv.org)

PEARL: A Task-Aware Framework for Evaluating Differentially Private Synthetic Educational Data (arxiv.org)

When Noise Fabricates Bias: The Fragility of LLM-as-a-Judge Bias Measurement under Noisy Text (arxiv.org)

Meta-Learning for Classifier Selection in Image Datasets: A Feature-Driven Framework for Accuracy Prediction (arxiv.org)

Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove (arxiv.org)

Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization (arxiv.org)

Safe to Stop? Risk-Constrained Stopping for Sequential Clinical Diagnosis Agents (arxiv.org)

PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations (arxiv.org)

From Plausible to Actionable: A Position on LLM Self-Explanations (arxiv.org)

RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems (arxiv.org)

No Screening is More Efficient with Multiple Objects (arxiv.org)

Quantum State Preparation with the QNN-based SRBB Algorithm (arxiv.org)

Configuration-Dependent Lower Bounds for Approximation by Shallow ReLU$^k$ Networks on the Sphere (arxiv.org)

Addressing A Posteriori Performance Degradation in Neural Network Subgrid Stress Models (arxiv.org)

Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery (arxiv.org)

RobustSGPO: Search-Space Control for Agent Harness Evolution (arxiv.org)

Seven Sources of Physical AI Capability Formation (arxiv.org)

From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning (arxiv.org)

From State Synchronization to Cognitive Self-Evolution: An Operational Architecture for Cognitive Digital Twins (arxiv.org)

A Function-Space Approach to the Statistical Mechanics of Learning Dynamics (arxiv.org)

CityPlanner: A Sandbox Agent for Executable Urban Planning (arxiv.org)

Multi-Agent Agentic Graph Learning via Structural Signatures (arxiv.org)

Narrative Consolidation: Formulating a New Task for Unifying Multi-Perspective Accounts (arxiv.org)

Introducing Consort: A Spec-First Agent Framework for Enforced, Test-Driven Development on Live Database Branches (arxiv.org)

Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints (arxiv.org)

Elsewise: Authoring Open-ended Interactive Narrative with Possibility Space Visualization (arxiv.org)

BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models (arxiv.org)

A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Model (arxiv.org)

BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RL (arxiv.org)

Adaptive Entangled Game Modules in Artificial General Intelligence (arxiv.org)

Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks (arxiv.org)

Rebalancing Token Importance in Language Models with TF-IDF Weighted Cross-Entropy Loss (arxiv.org)

Positional task conditioning for scalable defect detection across product families in large product catalogs (arxiv.org)

Partial GFlowNet: Accelerating Convergence in Large State Spaces via Strategic Partitioning (arxiv.org)

Semidefinite Programming for Quantum Channel Learning (arxiv.org)

UBCL: A Reinforcement Learning Framework for Controllable and Diverse Player Behaviors (arxiv.org)

When More Is Not Better: Component Anti-Synergy in a P300 Speller (arxiv.org)