AI News

Mitigating Diffusion Model Hallucinations with Dynamic Guidance (arxiv.org)

A large-scale nanocrystal database with aligned synthesis and properties enabling generative inverse design (arxiv.org)

One if by Land, Two if by Sea, Three if by Four Seas, and More to Come -- Values of Perception, Prediction, Communication, and Common Sense in Decision Making (arxiv.org)

How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs (arxiv.org)

DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs (arxiv.org)

A Comparative Study of Student Perspectives on Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics (arxiv.org)

Dynamics of learning to integrate in linear recurrent neural networks (arxiv.org)

CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models (arxiv.org)

DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback (arxiv.org)

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization (arxiv.org)

RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments (arxiv.org)

DHAuDS: A Dynamic and Heterogeneous Audio Benchmark for Test-Time Adaptation (arxiv.org)

Quantifying Rodda and Graham Gait Classification from 3D Markerless Kinematics derived from a Single-view Video in a Heterogeneous Pediatric Clinical Cohort (arxiv.org)

NutriMLLM: Multimodal Large Language Models for Dietary Micronutrient Analysis (arxiv.org)

CARE: A Conformal Safety Layer for Medical Summarization (arxiv.org)

SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning (arxiv.org)

Sustainability and Artificial Intelligence: Necessary, Challenging, and Promising Intersections (arxiv.org)

Solving Inverse Problems with Flow-based Models via Model Predictive Control (arxiv.org)

Optimizing Few-Step Generation with Adaptive Matching Distillation (arxiv.org)

Towards Personalized Bangla Book Recommendation: A Large-Scale Heterogeneous Book Graph Dataset (arxiv.org)

TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech (arxiv.org)

SafeRun: Enabling Determinism in LLM Planning for Running (arxiv.org)

ATM: Action-Consistency Transfer Matrix for Diagnosing and Improving Latent World Models (arxiv.org)

BareWave: Waveform-Native Flow-Matching Text-to-Speech (arxiv.org)

Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps (arxiv.org)

Context Rot in AI-Assisted Software Development: Repurposing Documentation Consistency for AI Configuration Artifacts (arxiv.org)

Autonomous Incident Resolution at Hyperscale: An Agentic AI Architecture for Network Operations (arxiv.org)

An Enhanced Geometric-Spectral Feature Learning Framework for Airborne Multispectral Point Cloud Classification (arxiv.org)

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges (arxiv.org)

Steganography Without Modification: Hidden Communication via LLM Seeds (arxiv.org)

Decoding Pedestrian Crossing Intention from Egocentric Vision via Vision Language Models (arxiv.org)

SEF-CLGC at SemEval-2026 Task 11: Logical Notation Impact on Language Model Performance (arxiv.org)

Unified Energy for Invariant and Independent Decoding in Diffusion Language Models (arxiv.org)

Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative Analysis (arxiv.org)

Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation Models (arxiv.org)

Investigating the Histogram Loss in Regression (arxiv.org)

Resource-aware Computation-Communication Overlap for multi-GPU ML Workloads (arxiv.org)

Trustworthy Smart Fabs via Professional Proxies: Scaling Safe and Sustainable by Design (SSbD) through Industrial Data Spaces (arxiv.org)

End-to-End Training for Discrete Token LLM based TTS System (arxiv.org)

Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation (arxiv.org)

EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric Video (arxiv.org)

Proposal Refinement for Few-Shot Object Detection (arxiv.org)

Physics-Guided Sequence-Based Generative Framework for Acoustic Metamaterial Inverse Design (arxiv.org)

Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents (arxiv.org)

Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design (arxiv.org)

The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes (arxiv.org)

Transforming Police-Car Swerving for Mitigating Isolated Stop-and-Go Traffic Waves: A Practice-Oriented Jam-Absorption Driving Strategy (arxiv.org)

Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models (arxiv.org)

Consensus-based adaptive sampling and approximation for high-dimensional energy landscapes (arxiv.org)

From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Design (arxiv.org)