AI News

MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents (arxiv.org)

Learning Sampling Parameters for Diffusion Models (arxiv.org)

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model (arxiv.org)

Speed Reading Tool Powered by Artificial Intelligence for Students with ADHD, Dyslexia, and Short Attention Span (arxiv.org)

Intent-Governed Tool Authorization for AI Agents (arxiv.org)

LU-500: A Logo Benchmark for Concept Unlearning (arxiv.org)

LEDOM: Reverse Language Model (arxiv.org)

Analyzing the Importance of Blank for CTC-Based Knowledge Distillation (arxiv.org)

GeoDecider: An Evidence-Grounded Agent for Geological Interpretation via Deliberative Reasoning (arxiv.org)

Gradient-Free Continual Learning (arxiv.org)

Sign-Symmetry Learning Rules are Robust Fine-Tuners (arxiv.org)

A Survey of Graph Transformers: Architectures, Theories and Applications (arxiv.org)

The Visual Bottleneck: Sparse-Frame Adaptation of MLLMs for Joint Spatial-Temporal Video Grounding (arxiv.org)

AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use (arxiv.org)

D-Score: A Spectral Hidden-State Signal for Hallucination Detection in Large Language Models (arxiv.org)

Self-Supervised Consistency Enhanced Disentangled Learning for Neural Decoding Generalization in Brain-Machine Interface (arxiv.org)

A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility (arxiv.org)

Choosing a Text Embedding Model: A Practical Benchmarking and Decision Framework (arxiv.org)

In-Context Learning as Implicit Policy Gradient (arxiv.org)

XGRVFL-MV: Residual-Coupled Graph-Embedded Multi-View Random Vector Functional Link Network with FleXi Guardian Loss (arxiv.org)

Fairness Interventions in Classification: A Study on AI Explainability (arxiv.org)

Diffusion-Guided Search via Exponential Tilting (DiffTilt): An Application to Falsification of Safety-Critical Systems (arxiv.org)

Token-Region Guided Cross-Attention Fusion for Multimodal Affect Interpretation (arxiv.org)

The Tokenizer Tax: Quantifying and Explaining the Cross-Lingual Cost of Subword Tokenization for Indian Languages (arxiv.org)

Tag Questions and the Generational Reversal of Sycophancy Across 45 Language Models (arxiv.org)

Charging Phase Health Indicators for Battery State-of-Health Estimation: A Systematic Comparison of CC, CV, and Combined Approaches under Cross-Battery Validation (arxiv.org)

Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks (arxiv.org)

FedTaste: Topology-Aware Structural Transfer for Multimodal Federated Learning with Missing Modalities (arxiv.org)

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases (arxiv.org)

Physics-Informed Neural Networks for Discovering Periodic Orbits in the Gravitational Three-Body Problem (arxiv.org)

GOTS: Greedy Orthogonal Token Selection for High-Resolution Vision-Language Models (arxiv.org)

Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling (arxiv.org)

Earnings25: A Comprehensive 500-Hour Speech Benchmark for Finance (arxiv.org)

Certified Parallel-in-Time Sinkhorn for Dynamic Entropic Optimal Transport (arxiv.org)

Do Small Models Use the Law You Give Them? Context-Injected Fine-Tuning for Legal QA in Bangladesh (arxiv.org)

Multimodal Semantic-Probabilistic Objectness for Open World Object Detection (arxiv.org)

Domain-Prior-Regularized Graph Modeling for Anomaly Detection in Cyber-Physical Systems (arxiv.org)

Cost-Aware Recovery-Pathway Identification and Bayesian Optimization for Autonomous Materials Discovery (arxiv.org)

Where Is the Cost of Third-Party API Routers in Agentic Software Development? (arxiv.org)

Semantic Semi-Incremental Data-Association-Free Object SLAM (arxiv.org)

Disentangling Semantic Attention from Structural Bias in the Attention Manifold (arxiv.org)

DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes (arxiv.org)

GFLAN: Generative Functional Layouts (arxiv.org)

EgoPlay: Event-Triggered Video Editing for Egocentric Streams (arxiv.org)

Flick: Few Labels Text Classification using K-Aware Intermediate Learning in Multi-Task Low-Resource Languages (arxiv.org)

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models (arxiv.org)

TLA$^{+}$-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA+ Specification Generation (arxiv.org)

Reasoning or Memorization: Can LLMs Understand and Generate Chinese Xiehouyu Riddles? (arxiv.org)

A Characterization of the Orthocomplement of the Tangent Space of Semiparametric Markov Models (arxiv.org)

Explaining BiomedCLIP with Weighted Banzhaf Interactions Supported by Tree-Gram Parsing (arxiv.org)