Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction
Research
Research News
New papers, breakthroughs and academic AI research
Counting on Thinking: Tracing Evidence Integration in Language Models
Research
StegGNN: Learning Graphical Representation for Image Steganography
Research
A Comparative Analysis of Attention versus State-Space Models for In-Context Learning
Research
Attribution Without a Second Pass: Inline Per-Sample Gradient Provenance at ~1% Overhead
Research
When Does a Skill Add Value? Task-Conditional Gain Prediction for Selective Skill Use
Research
Reward Hacking and Agent Containment Failure: A Monte Carlo Study Based on the 2026 Hugging Face Incident
Research
Constrained Flow Policy Updates: A Generalized Schr\"odinger Bridge View
Research
SWT: Self-Supervised Video Object Segmentation via Sliding, Wavelet and Transportation
Research
Understanding the Synergy between SFT, RLVR, and OPD in LLM Post-Training
Research
High-Capacity Robust Medical Image Exfiltration via Neural Network Weight Replacement
Research
ROTE: Benchmarking Neural Memorization on Complexity-Controlled Symbolic Sequences
Research