News
AI, cybersecurity, machine learning, scraping & programming news.
214 results on this page · clear filters
The Missing Minimal Pair: Stereotype Evaluation in LLMs
Measuring bias in large language models has often relied on comparing the log-likelihoods of two contrastive stereotype sentences. This approach can produce unreliable results because simply rewriting the same stereotype with an a...
Base Models Can Reason By Taking a Cue From Training Data
The study of reasoning in base models has taken a surprising turn. Rather than relying on reinforcement learning to shape behavior, researchers have found that specific starting token cues can unlock reasoning capabilities already...
TranScope: What the Software Hides About LLM Training Data, the Hardware Reveals at Scale, and Accelerators Magnify
The fundamental assumption that neural network inference can be made truly independent of training data has been called into question. Membership inference, the problem of determining whether a particular datum was part of a model...
BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance
Evaluating Spurious Feature Reliance Beyond Worst-Group Accuracy Worst-group accuracy (WGA) has become the de facto metric for assessing whether a machine learning model fails on underserved subsets of data. WGA measures the accur...
Anatomy-aware Fine-grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report
Why T-Staging Laryngopharyngeal Cancer Needs a New Approach Laryngopharyngeal cancer affects the voice box and throat, and accurate T-staging determines whether a patient receives organ-preserving surgery or more aggressive total...
TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts
Every recurrence of a looped language model adds cost in training, decoding, prefill, and reinforcement learning RL. The closer recurrent states get to fixed points, the less the path to them matters. This enables truncated backpr...
Deep Learning for Sleep Heart Rate Estimation from Accelerometers: Toward Population-Scale Cardiac Insight Without Optical Sensors
Large longitudinal cohorts often contain wrist accelerometry without optical heart-rate sensing, motivating recovery of cardiac information from motion signals already collected during sleep. We present SeqSmoother, a transformer-...
What Should World Models Forget? Stratified Retention for Continual Adaptation
Stationary targets versus drifting environments Continual learning has long treated performance loss on previously observed data as a signal of failure. This convention originates from prediction settings where a correct label rem...
RNADyn: A Benchmark for Generating and Understanding RNA Dynamics
RNA conformational dynamics and the limitations of static structures RNA molecules adopt multiple three-dimensional shapes to perform cellular tasks. These conformational changes are not captured by static structures obtained from...
LESSER: Post-Training Data Selection with Output-Layer Gradients
Why Post-Training Data Selection Matters for LLM Adaptation The choice of post-training data substantially affects large language model downstream performance. This makes data curation a high-leverage activity for teams that fine-...