AI × Crypto News Feed

The Last Word Often Wins: A Format Confound in Chain-of-Thought Corruption Studies

HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds

Relations Are Channels: Knowledge Graph Embedding via Kraus Decompositions

Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space

Researchers have identified why diffusion transformers (DiTs) degrade in quality during multi-turn image editing and proposed VAE-LFA, a training-free alignment method that operates in VAE latent space to suppress accumulated semantic drift. The solution works with both white-box and black-box models by aligning low-frequency components across editing rounds while preserving high-frequency details.

Resource-Aware Evolutionary Neural Architecture Search for Cardiac MRI Segmentation

CardiacNAS presents an evolutionary neural architecture search framework that optimizes cardiac MRI segmentation models for both accuracy and computational efficiency. The approach achieves 93.22% dice similarity with only 3.58M parameters, demonstrating how resource-aware AI design can enable deployment of medical imaging models on resource-constrained environments.

Interpretable Machine Learning for Football Performance Analysis: Evidence of Limited Transferability from Elite Leagues to University Competition

Researchers found that machine learning models trained on elite European football leagues lose interpretability and reliability when applied to university-level competition, suggesting that performance insights don't transfer across competition tiers. The study reveals that explanation stability and feature importance hierarchies are domain-dependent, challenging the assumption that ML-derived performance determinants are universally applicable.

Hierarchical Causal Abduction: A Foundation Framework for Explainable Model Predictive Control

Researchers present Hierarchical Causal Abduction (HCA), a framework that makes Model Predictive Control decisions interpretable by combining physics-informed reasoning, optimization evidence, and causal discovery. The method achieves 53% higher explanation accuracy than existing approaches across industrial control applications, addressing a critical barrier to deploying AI in safety-critical infrastructure.

New AI-Driven Tools for Enhancing Campus Well-being: A Prevention and Intervention Approach

Researchers have developed an integrated AI framework for campus mental health monitoring, combining TigerGPT (an LLM-powered survey chatbot) for prevention and PsychoGPT (a DSM-5-aligned screening tool) for intervention. The system uses reinforcement learning and multi-model reasoning to improve feedback quality and reduce hallucinations in mental health assessment.

Bangla-WhisperDiar: Fine-Tuning Whisper and PyAnnote for Bangla Long-Form Speech Recognition and Speaker Diarization

Researchers have developed Bangla-WhisperDiar, a fine-tuned speech recognition and speaker diarization system that achieves a 24.41% word error rate for ASR and 23.92% diarization error rate. The work addresses critical gaps in Bangla language processing by combining OpenAI's Whisper model with PyAnnote's diarization framework, trained on custom datasets with extensive data augmentation techniques.

PathISE: Learning Informative Path Supervision for Knowledge Graph Question Answering

PathISE is a novel framework that enables knowledge graph question-answering systems to learn effective supervision signals from answer-level labels alone, eliminating the need for expensive intermediate annotations. By using a transformer-based estimator to identify informative relation paths and distilling them into LLM path generators, the approach achieves competitive state-of-the-art performance while reducing resource requirements for training.

PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents

Researchers introduce PaperFit, a vision-in-the-loop AI agent that automates the typesetting optimization of LaTeX scientific documents by iteratively rendering pages, diagnosing visual defects, and applying constrained repairs. The work formalizes Visual Typesetting Optimization (VTO) as a critical missing stage in document automation, addressing the gap between compilable but visually flawed PDFs and publication-ready outputs through a new benchmark of 200 papers.

Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning

NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning

NoisyCoconut is an inference-time method that improves LLM reliability by injecting controlled noise into internal representations to generate diverse reasoning paths, enabling models to abstain when uncertain without requiring retraining. The technique reduces error rates from 40-70% to below 15% on mathematical reasoning tasks through unanimous agreement among noise-perturbed paths, offering practical reliability improvements compatible with existing models.

Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning

DOSER introduces a diffusion-model-based framework for offline reinforcement learning that improves out-of-distribution (OOD) action detection beyond traditional penalization methods. The approach uses single-step denoising reconstruction error to identify risky actions while selectively encouraging beneficial exploration, with theoretical guarantees of convergence and empirical superiority on suboptimal datasets.

CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings

Researchers introduce CORTEG, a framework that adapts pretrained scalp-EEG foundation models to intracranial ECoG recordings, enabling brain-computer interfaces to learn across patients with minimal calibration time. The approach demonstrates competitive or superior performance on finger trajectory and audio envelope decoding tasks while reducing per-patient training requirements to 10-30 minutes.

PoDAR: Power-Disentangled Audio Representation for Generative Modeling

HapticLDM: A Diffusion Model for Text-to-Vibrotactile Generation

Researchers introduce HapticLDM, a diffusion model that generates haptic feedback from text descriptions, outperforming previous autoregressive approaches in realism and semantic accuracy. The breakthrough enables more efficient vibration design for metaverse, gaming, and film applications by improving how AI converts natural language into precise vibrotactile experiences.

ReplaySCM: A Benchmark for Executable Causal Mechanism Induction from Interventions

ReplaySCM introduces a 1,300-item benchmark for evaluating how well language models can infer causal mechanisms from limited intervention data. The benchmark tests whether AI systems can output executable Boolean causal models that generalize to unseen intervention scenarios, revealing that frontier LLMs struggle significantly when structural information is hidden.

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising

Researchers present a parameter-free wrapper method (WNE) that enforces Normalization Equivariance—robustness to brightness and contrast shifts—around any neural network backbone without architectural constraints. The approach characterizes NE as a normalize-process-denormalize factorization, enabling compatibility with modern components like transformers and attention mechanisms while avoiding the 1.6x computational overhead of existing methods.

Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models

Researchers present a unified mathematical framework for Test-Time Adaptation (TTA) in autoregressive generative models, decomposing entropy minimization into token-level policy gradient and entropy losses. Validated on Whisper ASR across 20+ domains, the approach demonstrates consistent performance improvements and reconciles previously disparate adaptation methods under a single theoretical foundation.

Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers

Researchers analyzed how Qwen3-VL-8B, a multimodal transformer, encodes visual interestingness—a measure derived from human engagement data—without explicit supervision. Using neuroscience-inspired methods, they found that the model's internal representations align with human-derived interestingness scores, suggesting transformers may capture principles of human attention and perception.

From Ontology Conformance to Admissible Reconfiguration: A RoSO/SMGI Adequacy Argument for Robotic Service Governance

Researchers propose embedding the Robotic Service Ontology (RoSO) into the Structural Model of General Intelligence (SMGI) to enable dynamic governance of robotic services during runtime reconfigurations. The framework addresses how service semantics can remain valid and admissible when systems are rebound, recomposed, or redeployed, moving beyond static ontology conformance to formally governed runtime change.

Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning

Researchers introduce MarsTSC, a novel framework combining Vision Language Models with agentic reasoning for few-shot multimodal time series classification. The system uses collaborative AI roles—Generator, Reflector, and Modifier—to iteratively refine knowledge and improve classification accuracy across 12 benchmarks while providing interpretable explanations.

Improving TMS EEG Signal Quality for Closed-Loop Neuro Stimulation via Source-Domain Denoising

Researchers have developed and validated a TMS EEG cleaning pipeline with a benchmark dataset to improve signal quality for closed-loop neuro-stimulation applications. The study evaluates artifact removal strategies and demonstrates their effectiveness in preserving TMS-evoked potentials while reducing noise, with implications for advancing brain-computer interface research and clinical applications.

Quantile Geometry Regularization for Distributional Reinforcement Learning

Researchers propose RQIQN, a new reinforcement learning method that improves quantile-based distributional RL by addressing distorted distribution estimates through Wasserstein distributionally robust optimization. The approach adds a lightweight correction to quantile targets that prevents distributional collapse while maintaining computational efficiency, demonstrating superior performance on navigation and Atari benchmarks.