The 7 papers the radar tracked in May 2026. The current radar lives on the research page. Back to the radar →
Feedback Distillation improves post-training of reasoning models by using self-distillation with token-level supervision and privileged feedback from language models, offering bet…
LLM-as-a-judge has become the standard for automated evaluation, but it suffers from high cost, significant latency, and opaque decisions -- limitations that undermine its scalability and reliability. We address these with a simple,…
The quality of training data fundamentally determines the capabilities of large language models (LLMs), yet no unified benchmark exists to measure how well LLMs, agents, and data-centric workflows actually prepare training data end to end.…
Recent advances in powerful text-to-image generation models have made it increasingly important to develop test-time methods that modify the sampling trajectory to produce images more faithful to complex compositional prompts. We present…
An axiomatic evaluation framework reveals systematic failures in latent thought representations of LLMs across multiple reasoning tasks, demonstrating that current representations fail to satisfy fundamental functional axioms consistently…
In this paper we introduce token time continuous diffusion (TTCD), a new diffusion language model which (a) operates in continuous space, deterministically mapping Gaussian noise to a final token canvas with no further sampling, and…
Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixed task and reward difficulties become ineffective signals as model performance improves,…