AI News Archive

188 items · 50 per page

51DConstrain for Constrained Decoding in Diffusion Language Models9h ago0.36 52PopDRP Framework for Multimodal Brain Disorder Diagnosis9h ago0.24 53OpenDS Benchmark for Real-World Web Deep Search Agents9h ago0.60 54Demis Hassabis Accelerates AGI Timeline Projections to 2-3 Years10h ago0.14 55

Biological Context Failure in LLM-Guided Experimental Optimization

10h ago

0.31

56Information-Theoretic Analysis of Chain-of-Thought Monitorability10h ago0.24

57AlignGemini Achieves Cross-Generator Image Detection via Orthogonal Supervision10h ago0.27

58A2A Benchmark for Vision-and-Language Navigation in Agricultural Robotics10h ago0.20

59AFFORD2ACT tests robot manipulation using sparse 2D keypoints11h ago0.24

60WindINR uses implicit neural representations for local wind queries11h ago0.18

61Characterizing entropy dynamics and reasoning correctness in LLMs11h ago0.24

62Discovering novel research directions via the Alien Space of Science11h ago0.18

63TabAgent replaces LLM agent components with lightweight classifiers11h ago0.38

64TextRIRO uses real data for style-preserving scene text editing11h ago0.41

65AI agents develop emergent behaviors in isolated virtual environments11h ago0.42

66inDrive plans 2027 robotaxi testing in Kazakhstan with Pony.ai11h ago0.33

67Warning on Low-Value AI Projects as Compute Costs Stabilize11h ago0.19

68StructLens for Analyzing Transformer Representation Organization11h ago0.18

69PRISM Training-Free Framework for Financial Information Retrieval11h ago0.31

70MedicalBench for Implicit Medical Concept Extraction11h ago0.27

71GLUScope for Analyzing GLU Neuron Activation Quadrants11h ago0.24

72TraceForge for Distilling Reasoning Traces from Teacher Models11h ago0.59

73StreamEval Benchmark for Interactive Streaming Video Generation11h ago0.47

74SpatialBrain Framework for Experience-Based Spatial Intelligence11h ago0.47

75Scaling Embodied Agents via Continued Pre-Training in Virtual Worlds11h ago0.30

76Qwen-Audio-3.1-ASR with Improved Speaker Diarization11h ago0.53

77DeepEvolve Framework for Recursive Self-Improvement in Agents11h ago0.36

78Increased Thinking Time Enhances Logical Reasoning in LLMs11h ago0.41

79DONIC Generalist Bimanual Tracker Trained on BiHOI Dataset11h ago0.47

80DeLoop Method to Reduce Agentic Loops via Self-Supervision11h ago0.59

81CulturalRiddles Benchmark for Multicultural LLM Evaluation11h ago0.31

82Spectral-Spatial Interpretation for Localized Multispectral Attribution11h ago0.36

83MiniMax-M3.1-Flash Model Release12h ago0.14

84RAG+Prompt System for Japanese-Chinese Translation12h ago0.18

85Policy-Aligned Text Simplification via LLM-as-a-Judge12h ago0.35

86Evaluating LLM Generalization vs. Memorization via Chess12h ago0.24

87Deep Reasoning via Structured Meta-Cognition in Agents12h ago0.35

88CORE Method for Optimizing LLM-Based Search Rankings12h ago0.27

89Autonomous AI Research Teams for Linear Attention Discovery12h ago0.41

90Agent4Sci Evaluates Coding Agents on Scientific Machine Learning12h ago0.53

91Post-Training Biases in Dialectal Language Accommodation12h ago0.31

92AW-0 Framework for Agentic World Action Models12h ago0.60

93Adaptive Item-Level Recursion for Efficient Sequential Recommendation12h ago0.36

94WildAWM Pipeline for Synthesizing Computer-Use Agent Environments12h ago0.58

95ClusterFusion Hybrid Framework for LLM-Driven Text Clustering12h ago0.18

96AfrIFact Dataset for Multilingual Fact-Checking in African Languages12h ago0.21

97Adaptive Auditing Framework for AI Systems with Anytime-Valid Guarantees12h ago0.18

98Masked Diffusion Models Mitigate the Reversal Curse via Parameter Coupling12h ago0.24

99PrismaCoder Uses Decomposed Rubric Synthesis for Multimodal Code Intelligence12h ago0.36

100Diagnosing Benchmark Failure via Empirical Difficulty Measures13h ago0.24

← prevpage 2 / 4next →