VERITYGATE: A Four-Gate Schema-Level Faithfulness Framework and Paired Benchmark for Grounded LLM Narrations over Structured Evidence
Research
Research News
New papers, breakthroughs and academic AI research
The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning
Research
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
Research
Soundwich: Video Generation with Layered and Controllable Audio
Research
Sapien: A Stateful Policy Engine for Autonomous AI Agents
Research
Kepler: Auditable World Models for ARC-AGI-3
Research
Evaluating LLM-Generated Preference Distributions
Research
Sequential Functional Structured Tucker Compression for Large Language Model Attentions
Research
Reason in Style: Discovering and Controlling Style in Language Models
Research
Can large language models unlock discrete data in ophthalmic diagnostic reports?
Research
Verbalized and Internal Probabilities Are Coupled in Large Language Models
Research
Benchmarking System One decision models against trained classifiers and language models for automated decision gates
Research