English

Browse

AI News

30934 items — filtered, classified, deduplicated

All Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework
arXiv cs.AI Research & Papers
ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inf…
arXiv cs.AI Research & Papers
Less is More: Early Stopping Rollout for On-Policy Distillation
arXiv cs.AI Research & Papers
ReasonOps: A Unified Operational Paradigm for Trustworthy Verified LLM Reasoning
arXiv cs.AI Research & Papers
Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling
arXiv cs.AI Research & Papers
LLMs versus the Halting Problem: Characterizing Program Termination Reasoning
arXiv cs.AI Research & Papers
Modernising Reinforcement Learning-Based Navigation for Embodied Semantic Scene Graph Gen…
arXiv cs.AI Research & Papers
EEG-FM-Audit: A Systematic Evaluation and Analysis Pipeline for EEG Foundation Models
arXiv cs.AI Research & Papers
PHALAR: Phasors for Learned Musical Audio Representations
arXiv cs.AI Security & Safety
Cryptographic Registry Provenance: Structural Defense Against Dependency Confusion in AI …
arXiv cs.AI Research & Papers
ContextGuard: Structured Self-Auditing for Context Learning in Language Models
arXiv cs.AI Research & Papers
EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial N…
arXiv cs.AI Research & Papers
Adversarial Training for Robust Coverage Network under Worst-case Facility Losses
arXiv cs.AI Research & Papers
Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting i…
arXiv cs.AI Research & Papers
LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective P…
arXiv cs.AI Research & Papers
Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
arXiv cs.AI Research & Papers
PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis
arXiv cs.AI Research & Papers
Model Merging on Loss Landscape: A Geometry Perspective
arXiv cs.AI Research & Papers
Beyond Linearity in Attention Projections: The Case for Nonlinear Queries
arXiv cs.AI Research & Papers
RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
arXiv cs.AI Research & Papers
GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and…
arXiv cs.AI Research & Papers
Olaf-World: Orienting Latent Actions for Video World Modeling
arXiv cs.AI Research & Papers
MatFormBench: A Benchmarking Evaluation Framework for Target-Driven Materials Formulation
arXiv cs.AI Research & Papers
MetaSICL: Adapting Audiroty LLM via Meta Speech In-Context Learning
arXiv cs.AI Research & Papers
Beyond Transfer Accuracy: Faithful Circuits for Controlled Low-Resource Adaptation
arXiv cs.AI Research & Papers
Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Le…
arXiv cs.AI Research & Papers
Faithfulness Evaluation for Decoder-only LLM Attributions with Controlled Retained Inform…
arXiv cs.AI Research & Papers
An In-Vitro Study on Cross-Lingual Generalization in Language Models
arXiv cs.AI Research & Papers
Continual Model-Based Reinforcement Learning with Hypernetworks
arXiv cs.AI Research & Papers
Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behaviora…