Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Age…
Browse
AI News
37834 items — filtered, classified, deduplicated
Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schemati…
Skill Composition for Legged Robot Reinforcement Learning
NoteVQA: Benchmarking VLMs on Real-Life Questions from Human Communities
On the role of the tokenizer in ECG transformer models
Robust and Efficient Communication for Multi-Agent Learning
Efficient On-Device Agents via Adaptive Context Management
PU classification under Non-SCAR: clustering-assisted logistic model with oversampling en…
Kaininja: Extending Native 3D Generators to the Part Level
Authorship attribution and aesthetic evaluation of AI poetry: a case study with Haiku
PACE: Progressive Angular-to-Norm Contrastive Embedding
Interpreting hierarchical organisation of speaker embeddings
Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulne…
Don't Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatica…
Beyond AI Literacy: A Structured Review and Exploratory Meta-Analysis of Measures for Com…
VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long V…
Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized …
Predictive Likelihood Ratios for Language Model Watermark Detection
A Responsive Present, a Shared Past, a Social Other: Teens' Overreliance on Companion AI …
ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMs
Attention Is All You Need (to Avoid Spurious Oscillations)
FedLTLib: A Comprehensive Benchmark for Federated Long-Tail Learning
Event-Native Symbolic-Temporal Spike Encoding Framework for Heterogeneous Cyber Streams
A Language-Guided Multimodal Foundation Model for Zero-Shot and Multi-Task Brain Signal A…
Salesforce Koa: An Enterprise Language Model for Agentic Tool Use
Per-Matrix Optimality Is Not Enough: Three-Level Optimization for Low-Rank LLM Compression
Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communicat…
When the World Lies: Backdoor Attacks on Latent World Models for Downstream Control
Privacy-enhanced federated learning via asynchronous aggregation and local differential p…
Data Security in Large Language Models: Risks, Defense, and Directions