Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding
Research
Research News
New papers, breakthroughs and academic AI research
XS-VID: A Large-Scale Benchmark for Small Object Detection and Tracking in Videos
Research
Large Language Model-Guided Discovery of Weight-Five Bivariate Bicycle Codes
Research
BRANCH-MoE: Balance-Aware Tree Routing for Large Embedding Models
Research
Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution
Research
Validation-Gated Causal Interventions for Interpreting High-Stakes Large Language Model Behavior: A Case Study in Suicidality Detection
Research
ORCA: The Annealed Spectral Conditioning Optimizer for Faster, Better LLM Training
Research
Integrating Survival-Based Aging Models with Data-Driven RUL Prognostics
Research
Event-based Continuous Color Video Decompression from Single Frames
Research
Deep Learning for Sleep Heart Rate Estimation from Accelerometers: Toward Population-Scale Cardiac Insight Without Optical Sensors
Research
Inference-Time Amplification of Weak Reasoning Models
Research
Who Checks the Citations? Benchmarking Legal Hallucination Detection
Research