Inference-Time Scaling
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Predicting Inference-Time Scaling Gains from Labeled Validation-Set Output Statistics
arXiv:2606.02981v1 Announce Type: new Abstract: Best-of-$N$ inference scaling (drawing $N$ candidate answers from a language model and returning the one a reward model ranks highest) improves accuracy by an amount that varies across models, but predicting that amount in advance currently requires running the procedure end-to-end. Prior work links cheap statistics of a model's sampled outputs and validation-set correctness (how often samples agree, how diverse they are, how confident the...
Inference-Time Scaling for Joint Audio-Video Generation
arXiv:2606.03183v1 Announce Type: new Abstract: Joint audio-video generation aims to synthesize realistic audio-video pairs that are both semantically aligned with text prompts and precisely synchronized. While existing joint audio-video generation models often require substantial training resources to improve fidelity, Inference-Time Scaling (ITS) has recently emerged as a promising training-free alternative in single-modality domains. However, extending ITS from a single modality to...
Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability
Announce Type: new Abstract: Inference-Time Scaling (ITS) has largely succeeded in verifiable domains like math and coding, where cheap verification enables scalable output selection. However, extending ITS to tasks prone to systematic failure - driven by faulty initial assumptions or unmet multidimensional constraints - typically relies on costly external solvers or brittle, model-based verifiers. Our key insight is that the intrinsic statistics of parallel sample sets, specifically...
Ideas in Inference-time Scaling can Benefit Generative Pre-training Algorithms
arXiv:2503.07154v3 Announce Type: replace Abstract: Generative pre-training is often framed through a false dichotomy between autoregressive models for discrete signals and diffusion models for continuous signals. We argue that the dichotomy is false because it conflates model family, data representation, training objective, and inference procedure. Autoregression is an inference procedure that expands a sequence through normalized conditional draws, while diffusion is a refinement procedure...
UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling
Announce Type: new Abstract: In real-world deployments of large language models (LLMs), balancing inference quality and computational cost has become a central challenge. Existing approaches tackle this trade-off along two largely independent dimensions: model routing, which switches among models of different scales to match request complexity, and test-time scaling (TTS), which adjusts inference-time compute within a fixed model for fine-grained control. However, this decoupled design...
Divergence Decoding: Inference-Time Unlearning via Auxiliary Models
arXiv:2605.31293v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently memorize sensitive training data thereby creating significant privacy and copyright risks. Addressing these risks, i.e., removing such knowledge from an existing model checkpoint, has proven challenging as many unlearning methods lead to catastrophic utility loss or are ineffective for complex queries. We introduce Divergence Decoding (DD), a mechanism that uses small auxiliary models to steer the logits...
The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
arXiv:2606.02646v1 Announce Type: new Abstract: Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence. We derive a two-parameter scaling law $R(N) = N_\text{eff}/N = 1/(1+c(N-1)N^{-\beta})$ where the regime exponent $\beta$ classifies any configuration into one of three asymptotic regimes -- hard-ceiling at $1/c$ ($\beta = 0$), sublinear at $N^\beta/c$ ($0 0.99$; only $(c, \beta)$ shifts. On free-form math, dense peer...
The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
arXiv:2606.02646v1 Announce Type: cross Abstract: Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence. We derive a two-parameter scaling law $R(N) = N_\text{eff}/N = 1/(1+c(N-1)N^{-\beta})$ where the regime exponent $\beta$ classifies any configuration into one of three asymptotic regimes -- hard-ceiling at $1/c$ ($\beta = 0$), sublinear at $N^\beta/c$ ($0 0.99$; only $(c, \beta)$ shifts. On free-form math, dense peer...
The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs
arXiv:2606.03092v2 Announce Type: replace Abstract: Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. In this work, we formulate inference budget allocation as a global constrained optimization problem governed by economic principles. By modeling per-query reasoning utility with a shifted-surge function, we derive an optimal allocation policy based on a global...
The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs
Announce Type: new Abstract: Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. In this work, we formulate inference budget allocation as a global constrained optimization problem governed by economic principles. By modeling per-query reasoning utility with a shifted-surge function, we derive an optimal allocation policy based on a global shadow price that...