PhysEvo: Astra Can Act, Let It
Research
Research News
New papers, breakthroughs and academic AI research
Pretraining Shapes Spectral Structure: Architecture- and Strategy-Conditional Prediction of OOD Robustness in Foundation Models
Research
Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models
Research
Goldsmith: Gold-Loss-Guided Definition Optimization with an Agentic Annotation Harness
Research
Latent Performance Profiling of Large Language Models
Research
Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
Research
Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents
Research
The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs
Research
Neighborhood Smoothing for Calibration
Research
ARCS: Towards Precise Text-to-SQL via Structured Disambiguation
Research
Knowledge boundary probing and demand-guided intervention for LLM-based power system code generation
Research
Relational Abstractions for Spatial Reasoning with Diffusion Models
Research