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
LUCoS: Latent Unsupervised Context Selection for Tabular Foundation Models
arXiv cs.AI Research & Papers
Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs
arXiv cs.AI Research & Papers
Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conf…
arXiv cs.AI Research & Papers
It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertain…
arXiv cs.AI Research & Papers
Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
arXiv cs.AI Research & Papers
Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision…
arXiv cs.AI Research & Papers
EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial Requirements E…
arXiv cs.AI Research & Papers
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
arXiv cs.AI Research & Papers
Multi-Agent Causal Discovery Using Large Language Models
arXiv cs.AI Research & Papers
Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization
arXiv cs.AI Research & Papers
Cross-scale Aligned Supervision for Training GANs
arXiv cs.AI Research & Papers
Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction
arXiv cs.AI Research & Papers
Doc-CoB: Enhancing Document Understanding with Visual Chain-of-Boxes Reasoning
arXiv cs.AI Research & Papers
EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price…
arXiv cs.AI Research & Papers
Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelin…
arXiv cs.AI Research & Papers
TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents
arXiv cs.AI Research & Papers
AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learn…
arXiv cs.AI Research & Papers
Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Dif…
arXiv cs.AI Research & Papers
Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
arXiv cs.AI Research & Papers
Qrita: High-performance Top-k and Top-p using Pivot-based Truncation and Selection
arXiv cs.AI Research & Papers
Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Ad…
arXiv cs.AI Research & Papers
Degradation-Consistent Paired Training for Robust AI-Generated Image Detection
arXiv cs.AI Research & Papers
The Rescue Effect: Spatio-Semantic Early Exit Bypasses Quantization Collapse in CLIP
arXiv cs.AI Research & Papers
Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking
arXiv cs.AI Research & Papers
To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs
arXiv cs.AI Research & Papers
DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning
arXiv cs.AI Research & Papers
Semigroup Consistency as a Diagnostic for Learned Physics Simulators
arXiv cs.AI Research & Papers
Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusi…
arXiv cs.AI Research & Papers
Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Contex…
arXiv cs.AI Research & Papers
Ethical Fairness without Demographics in Human-Centered AI