How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits
Research
Research News
New papers, breakthroughs and academic AI research
LVS: Local View Synthesis from Relative Camera Pose by Reusing Previous Views
Research
DADP: Dynamic Activity-Dependent Pruning, A Reverse Hebbian-Inspired Structural Pruning Method
Research
From Surface to Depth: Towards Cognitive Appraisal Reasoning in Multimodal Emotion Understanding
Research
Imperative Interference: Social Register Shapes Instruction Topology in Large Language Models
Research
PRAXIS: Learning Dynamics of Self-Improving Models with Symbolic Archives
Research
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
Research
RAGenome: Scaling Retrieval-Based Genomic Language Models to Long Contexts
Research
ContourVLA: A Closed-Loop Perception-Action Contour Policy for Generalized Referring Expression Segmentation
Research
Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing
Research
Stochastic Grouping Conformal Prediction for Effective Subgroup Reliability
Research
Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning
Research