Archive
Page 4
Error-Conditioned Neural Solvers
Neural surrogate models offer fast approximate mappings from PDE parameters to solutions, but they typically treat solving as a purely statistical task...
Mapping Political-Elite Networks in Europe with a Multilingual Joint Entity-Relation Extraction Pipeline
Whether political elites organise into rent-seeking coalitions that capture public resources or civic networks that sustain governance is a central...
AI-Assisted Computational Reproducibility on the FABRIC Testbed
Computational reproducibility remains difficult despite being central to scientific research. In this paper, we show how the international FABRIC testbed...
Anthropic accuses Alibaba of running the largest distillation campaign yet against Claude
Anthropic alleges Alibaba ran the largest model-distillation campaign yet against Claude, a serious IP and terms-of-service breach claim.
AutoRelAnnotator: Calibrated Model Cascades for Cost-Efficient Relevance Evaluation in Sponsored Search
How can we generate high-quality relevance annotations at scale without the cost and delays of human labeling? Relevance annotations are the backbone of...
Enhancing Brain MRI Anomaly Detection and Reasoning with ROI Rethink and Synthetic Data
Medical vision-language models typically generate diagnoses through single-pass inference without indicating which image regions support their...
Learning Action Priors for Cross-embodiment Robot Manipulation
Most Vision-Language-Action (VLA) models build on a Vision-Language Model (VLM) backbone by attaching an action module and optimizing the full policy...
Micron’s revenue quadrupled as AI memory demand pushes gross margins above 81 percent
Micron's revenue quadrupled as surging AI memory demand pushed gross margins above 81 percent, underscoring the HBM boom.
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult...
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with the teacher conditioned on a correct...