Test-time compute

Timeline

1. Oct 9, 2026 · Opinion / analysis · 1 source
   I expect rapid progress but not towards general superintelligence
   I’ve often been surprised when I hear from top researchers in industry that they think AI will be better than them at their job in a few years, and I didn’t really know why I doubted it.
2. Oct 8, 2026 · Research paper · 1 source
   VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling
   In this work, we introduce VINCIE-NExT, a unified framework that transfers editing capability from images to videos through in-context visual demonstrations, alleviating the need for large-scale paired video editing data.
3. Oct 8, 2026 · Research paper · 1 source
   Test-Time Compute for Tabular Foundation Models: Mechanisms, Gains, and Limits
   Which forms of test-time compute improve the predictions of strong pretrained tabular foundation models (TFMs)?
4. Oct 8, 2026 · Research paper · 1 source
   Agentic-TTT: Training test-time policy for test-time training
   To fill this gap, we introduce Agentic-TTT, which learns a test-time policy to govern those decisions.
5. Oct 8, 2026 · Research paper · 1 source
   SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning
   Large Reasoning Language Models (LRLMs) enable multi-step reasoning for robotic task planning, but continued reasoning can overwrite valid intermediate plans or leave constraint violations unresolved, reducing planning reliability and wasting inference-time computation.
6. Oct 7, 2026 · Opinion / analysis · 1 source
   One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
   Starting from Nemotron 3, our teams used supervised fine-tuning (SFT), reinforcement learning (RL), and feedback-driven inference to create systems that reached gold-medal level at both IMO 2026 and IOI 2026.
7. Oct 7, 2026 · Research paper · 1 source
   From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery
   To reduce the overhead of repeated policy discovery for new user profiles, we propose PersonTTS, an amortized agentic policy-discovery framework that reuses prior search experience through requirement-matched controller initialization and source-distilled procedural guidance, while retaining target-profile evaluation for every candidate.
8. Oct 6, 2026 · Research paper · 1 source
   Readout Stability in Prefill-Only Decision Models:Zero-Label Prediction and Inference-Time Compute Allocation
   Prefill-only decision models inspired by the Jev model score every candidate in a menu during a single forward pass and never decode, which makes one call one to two orders of magnitude cheaper than a same-scale generative language model.

Often appears with