Sampling headroom is not selection gain: a compute-value audit of test-time scaling for video world models

• URL: http://arxiv.org/abs/2609.13257v1
• Date: Sun, 06 Sep 2026 06:11:15 GMT
• Title: Sampling headroom is not selection gain: a compute-value audit of test-time scaling for video world models
• Abstract summary: Test-time scaling can improve generation only when additional compute produces better candidates and the system can reliably identify them.<n>We introduce the Compute-Value Audit (CVA), a sequential framework that asks whether extra sampling creates opportunity.<n>On 192 Physics-IQ scenes, expanding the pool from 4 to 16 candidates increases oracle quality by +9.23 IQ.<n>None of twelve adaptive-depth policies outperforms uniform compute; they recover only 42-69% of the measured entry fee.
• Score: 34.20907662027954
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Test-time scaling (TTS) can improve generation only when additional compute produces better candidates and the system can reliably identify them. This distinction is especially important for video world models, where a wider sample pool may contain stronger rollouts without improving the output that is ultimately selected. We introduce the Compute-Value Audit (CVA), a sequential framework that asks whether extra sampling creates opportunity, observable signals provide a reliable state, that state supports a beneficial action, and the resulting gain exceeds the full entry fee of generation and verification. On 192 Physics-IQ scenes, expanding the pool from 4 to 16 candidates increases oracle quality by +9.23 IQ (95% CI [+7.44, +11.14]), but Flow, Cycle, and VideoReward fail to recover this headroom reliably. Across three generators, none of twelve adaptive-depth policies outperforms uniform compute; they recover only 42-69% of the measured entry fee. A matched-60-NFE Predict-and-Perturb intervention on VideoPhy2 is likewise negative across three fresh-seed replicas. These negative results are not universal: anchor-explorer passes all four stages in a sparse PRM800K setting, MMLU-Pro exposes the gap between predictive state and useful action, and a privileged paired future establishes a positive video upper bound. Together, these results show that sampling headroom has deployment value only when it can be converted into a reliable decision whose benefit survives the complete compute charge. Code is available at https://github.com/YuhuaJiang2002/sampling-headroom-is-not-selection-gain.

Related papers

• BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing [0.898478290216692]
  BLOOM-WILT elicits natural multi-turn instances of rare behaviours without training cost or access beyond the target's next-token distribution.<n>We evaluate WILT across 4 target models and 8 behaviours, where it beats the baseline auditor in 30 of the 32 settings.
  arXiv  Detail & Related papers  (2026-08-31T17:10:59Z)
• Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck [1.4991111518581999]
  Test-time scaling (TTS) improves language model outputs by spending additional inference compute.<n>We conduct the first compute-normalised comparison of five TTS families across five generation benchmarks.
  arXiv  Detail & Related papers  (2026-08-19T13:59:53Z)
• Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training [51.18425726646089]
  We propose textscSURE, a unified latent-space framework for image and video diffusion models.<n>It learns reward distributions and directly uses their reliability to guide dense post-training.<n>textscSURE-REFL achieves the highest VBench quality, semantic, and total scores among the evaluated methods.
  arXiv  Detail & Related papers  (2026-08-06T14:55:42Z)
• Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration [8.515185888009833]
  Test-time collaboration is often credited with improving LLM reasoning, yet its gains are uneven and sometimes negative.<n>For a fixed candidate pool, we decompose a selector or verifier's net gain into measurable factors.<n>This reframes collaboration as a candidate-selection problem rather than as an intrinsic property of a multi-agent topology.
  arXiv  Detail & Related papers  (2026-07-20T04:09:19Z)
• Towards Fast and Effective Long Video Understanding of Multimodal Large Language Models via Adaptive Quasi-Gaussian Sampling [71.62893745623526]
  Video frame selection is a problem of Quasi-Gaussian Sampling.<n>We propose an adaptive and training-free approach termed AdaQ.
  arXiv  Detail & Related papers  (2026-06-23T06:13:30Z)
• Selective Test-Time Compute Scaling for Click-Through Rate Prediction via Uncertainty-Triggered Feature Path Exploration [9.542597285477683]
  Scaling test-time compute has proven highly effective for language models, yet this opportunity remains largely unexplored for industrial Click-Through Rate (CTR) prediction.<n>We propose UTTSI (Uncertainty-Triggered Test-Time Selective Inference), a training-free model-agnostic framework that scales inference depth proportionally to per-instance uncertainty.
  arXiv  Detail & Related papers  (2026-05-24T10:29:10Z)
• The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive [0.0]
  CPU-only scoring primitive runs at 2.6 microseconds per token.<n> token rank-frequency distributions converge to the same two- parameter Mandelbrot ranking distribution.<n>We derive a single-pass scoring primitive that composes with model log probabilities when available and degrades to a rank-only mode usable on closed APIs.
  arXiv  Detail & Related papers  (2026-04-28T13:35:31Z)
• ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference [60.958331943869126]
  ODAR-Expert is an adaptive routing framework that optimize the accuracy-efficiency trade-off via principled resource allocation.<n>We show strong and consistent gains, including 98.2% accuracy on MATH and 54.8% on Humanity's Last Exam.
  arXiv  Detail & Related papers  (2026-02-27T05:22:01Z)
• dVoting: Fast Voting for dLLMs [71.572316901001]
  Diffusion Large Language Models (dLLMs) represent a new paradigm beyond autoregressive modeling.<n>dLLMs can generate tokens at arbitrary positions in parallel, endowing them with significant potential for parallel test-time scaling.<n>We introduce dVoting, a fast voting technique that boosts reasoning capability without training, with only an acceptable extra computational overhead.
  arXiv  Detail & Related papers  (2026-02-12T16:35:05Z)
• Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation [51.127054971591924]
  We introduce a new generative self-evaluation scheme designed to adaptively reduce the number of generated samples. We demonstrate that 74% of the improvement from using 16 samples can be achieved with only 1.2 samples on average.
  arXiv  Detail & Related papers  (2024-10-03T17:47:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.