Anthropic launches Claude Science

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-30

Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-30

Amplifying Membership Signal Through Chained Regeneration

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-30

MVP-Nav: Multi-layer Value Map Planner Navigator

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-30

Accelerating Conformal Prediction via Approximate Leave-One-Out

arXiv cs.LG (Machine Learning) ・ 2026-06-30

Better Understanding, Understanding Better

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-30

Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-30

Relational and Sequential Conformal Inference for Energy Time Series over Graphs via Foundation Models

arXiv cs.LG (Machine Learning) ・ 2026-06-30

CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-30

SpikeLogBERT: Energy-Efficient Log Parsing Using Spiking Transformer Networks

arXiv cs.CL (Computation and Language) ・ 2026-06-30

Addressing Over-Refusal in LLMs with Competing Rewards

arXiv cs.LG (Machine Learning) ・ 2026-06-30

FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-30

STEB: Style Text Embedding Benchmark

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-30

RCT: A Robot-Collected Touch-Vision-Language Dataset for Tactile Generalization

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-30

Tone-Conditioned Curriculum Learning for Low-Resource Bantu Speech Recognition

arXiv cs.CL (Computation and Language) ・ 2026-06-30

Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings

arXiv cs.CL (Computation and Language) ・ 2026-06-30

On Optimal Data Splitting for Split Conformal Prediction

arXiv cs.LG (Machine Learning) ・ 2026-06-30

Localized Conformal Prediction for Image Classification with Vision-Language Models

arXiv cs.LG (Machine Learning) ・ 2026-06-30

AutoTrainess: Teaching Language Models to Improve Language Models Autonomously

arXiv cs.CL (Computation and Language) ・ 2026-06-30

Team MKC at CLPsych 2026: Capturing and Characterizing Mental Health Changes through Social Media Timeline Dynamics

arXiv cs.CL (Computation and Language) ・ 2026-06-30

Revising RVL-CDIP: Quantifying Errors and Test-Train Overlap

arXiv cs.CL (Computation and Language) ・ 2026-06-30

CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes

arXiv cs.CL (Computation and Language) ・ 2026-06-30

Clinically Structured Rank-Gated LoRA for Cross-Benchmark Medical Question Answering

arXiv cs.CL (Computation and Language) ・ 2026-06-30

Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents

arXiv cs.CL (Computation and Language) ・ 2026-06-30

Gated Multi-Graph Fusion via Graph Attention Networks for Alzheimer's Disease Detection

arXiv cs.CL (Computation and Language) ・ 2026-06-30

VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

GROW$^2$: Grounding Which and Where for Robot Tool Use

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

arXiv cs.CL (Computation and Language) ・ 2026-06-29

C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

A Hybrid Framework For Crypto-Ransomware Detection In Enterprise Shared Storage

arXiv cs.LG (Machine Learning) ・ 2026-06-29

Morphing into Hybrid Attention Models

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Convergence of Continual Learning in Homogeneous Deep Networks

arXiv cs.LG (Machine Learning) ・ 2026-06-29

Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Bridging the NISQ and Fault-Tolerant Regimes: Generative-ML-Assisted Quantum Selected CI for Molecular Simulations

arXiv cs.LG (Machine Learning) ・ 2026-06-29

$μ$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors

arXiv cs.LG (Machine Learning) ・ 2026-06-29

Staged Hybridisation for Visual Quantum Reinforcement Learning via Knowledge Distillation

arXiv cs.LG (Machine Learning) ・ 2026-06-29

Regime-Aware Peer Specialization for Robust RAG under Heterogeneous Knowledge Conflicts

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Experience Augmented Policy Optimization for LLM Reasoning

arXiv cs.LG (Machine Learning) ・ 2026-06-29

Beyond IID: How General Are Tabular Foundation Models, Really?

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

A Stochastic--Geometric Theory of Scaling Laws in Grokking

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

On the Vulnerability of Parameter-Level Defenses to Model Merging

arXiv cs.LG (Machine Learning) ・ 2026-06-29

Residual-Guided Expert Specialization for Incomplete Multimodal Learning

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Research Entity Extraction and Topic Detection from UKRI Grant Proposals

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

ManimAgent: Self-Evolving Multimodal Agents for Visual Education

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Rehearsed Multi-Agent Live Product Demonstrations with Real-Time Voice Question Answering

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Grounding LLM Reasoning under Incomplete Graph Evidence

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Comparing Human and Automatic Recognition of Dutch Dysarthric Continuous Speech: A Case Study

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Forewarned is Forearmed: When Non-Sequential Embedding Turns Into an Anomaly Detector

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Relevance Is Not Permission: Warranted Attention for Value Contributions

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Open Problems in Constitutional Preference Reconstruction

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Information Dynamics of Language Communication

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Little Brains, Big Feats: Exploring Compact Language Models

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Parametric Skills

arXiv cs.CL (Computation and Language) ・ 2026-06-29

T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation

arXiv cs.AI (Artificial Intelligence) ・ 2026-06-29

Node-to-Neighborhood Semantic Consistency: Text-Topology Alignment for TAGs Anomaly Detection

arXiv cs.CL (Computation and Language) ・ 2026-06-29

IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Know Before You Fetch: Calibrated Retrieval-Budget Allocation for Retrieval-Augmented Generation

arXiv cs.CL (Computation and Language) ・ 2026-06-29

MemDelta: Controlled Baselines and Hidden Confounds in Agent Memory Evaluation

arXiv cs.CL (Computation and Language) ・ 2026-06-29

KbSD: Knowledge Boundary aware Self-Distillation for Behavioral Calibration in Agentic Search

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Revealing the Technology Development of Natural Language Processing: A Scientific Entity-Centric Perspective

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering

arXiv cs.CL (Computation and Language) ・ 2026-06-29

SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Are Humans Evolved Instruction Followers? An Underlying Inductive Bias Enables Rapid Instructed Task Learning

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Mandol: An Agglomerative Agent Memory System for Long-Term Conversations

arXiv cs.CL (Computation and Language) ・ 2026-06-29

Managing Map Cardinality in Automatic Disease Classification Mapping: Balancing Precision, Recall and Coverage

arXiv cs.CL (Computation and Language) ・ 2026-06-29

A Diagnostic Framework and Multi-Evaluator Audit of Evaluator-Driven Preference Dynamics in Self-Adapting LLM Agents

arXiv cs.CL (Computation and Language) ・ 2026-06-29