Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models
Research
Research News
New papers, breakthroughs and academic AI research
Seeing Parts, Reasoning about Worlds: Visual Inference under Partial Observation
Research
Playing to Par: Reinforcement Learning for Provably Optimal Quadrilateral Block Decompositions
Research
Fail Loudly: An Auditable Runtime for Agentic Data Analysis
Research
Porimon: An LLM-Based Pok\'emon Battle Agent Enhanced by Long/Short-Term Knowledge Augmented Generation
Research
ARSM: Auto-Regressive State Machine for Agentic Reasoning Compression
Research
$T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training
Research
RPA: Residual Patch-Token Adapter for Image Retrieval from EEG and MEG
Research
Integrated Deep Learning Framework Designed on Hybrid Optimization Strategies for Automated Health Detection and Analysis in Silkworms
Research
CLC-YOLO: A Compact Channel-Gated Prototype Network for Real-Time Leakage-Aware Breast Ultrasound Lesion Segmentation
Research
MDL-Calibrated Significance-Gain Pair Encoding: Replication-Aware Automatic Stopping for Subword Tokenization
Research
Can't Find Waldo: Evaluating VLMs' Sensitivity to Image Resolution and Detail Level
Research