Unified Inference Scaling
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
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...
ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning
Announce Type: new Abstract: Test-time compute (TTC) scaling has emerged as a powerful paradigm for improving large language model (LLM) reasoning by allocating additional compute during inference, e.g., via multi-sample generation and verifier-based reranking. Existing TTC scaling strategies and reasoning scorers remain fragmented, evaluated under inconsistent protocols, and are rarely analyzed through the lens of quality-cost trade-offs. We introduce ThinkBooster, a unified framework for...
ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning
arXiv:2606.06915v2 Announce Type: replace Abstract: Test-time compute (TTC) scaling has emerged as a powerful paradigm for improving large language model (LLM) reasoning by allocating additional compute during inference, e.g., via multi-sample generation and verifier-based reranking. Existing TTC scaling strategies and reasoning scorers remain fragmented, evaluated under inconsistent protocols, and are rarely analyzed through the lens of quality-cost trade-offs. We introduce ThinkBooster, a...
ProbeScale: Probing Analysis to Optimize Neural Scaling Laws for Efficient Small Language Model Inference
arXiv:2606.01806v1 Announce Type: new Abstract: Small Language Models (SLMs) offer a balance between capability and computational feasibility. Neural scaling laws inform their optimal training, suggesting that they possess rich internal representations that scale with their size. However, deploying even these SLMs can be challenging under strict resource constraints.
Measuring Maximum Activations in Open Large Language Models
arXiv:2605.15572v2 Announce Type: replace Abstract: The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characterized outlier features and massive activations on pre-2024 LLaMA-style models, and the downstream activation-quantization stack inherits that picture without revisiting it for the post-LLaMA open-model boom. We ask the deployment-oriented question: how large can activations get in modern...
An Asymptotic Theory of Chain-of-Thought in In-Context Learning
arXiv:2606.03217v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning has become a widely used mechanism for eliciting multi-step reasoning in large language models by generating intermediate reasoning steps at inference time. Yet the scaling behavior of generalization with CoT depth remains poorly understood. To address this question, we study a theoretically solvable model of CoT for in-context weight prediction in linear regression, where test-time reasoning is represented as...
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
arXiv:2506.05233v2 Announce Type: replace Abstract: Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compute linearly during inference. A recent stream of work linearized the softmax operation, resulting in powerful recurrent neural network (RNN) models with constant memory and compute costs such as DeltaNet, Mamba or xLSTM.
X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challenge
arXiv:2605.13258v2 Announce Type: replace Abstract: In this work, we present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions. Our method is built upon the X-Restormer baseline, which captures both channel-wise global dependencies and spatially-local structural information through its dual-attention design (Multi-DConv Head Transposed Attention and Overlapping Cross-Attention), augmented with the spatially-adaptive input...
When AI Meets Wall Street: A Survey on Trustworthy AI in Fintech
Announce Type: new Abstract: Artificial intelligence is now embedded as a primary decision engine in continuously operated financial AI pipelines spanning training and updating, deployment and inference, and operation with monitoring and feedback. The automation and scale that make these pipelines effective also create novel attack surfaces, where small algorithmic perturbations can amplify into persistent, system-level financial harm. Existing surveys, however, either treat AI as a...
Deep networks learn to parse uniform-depth context-free languages from local statistics
Announce Type: replace-cross Abstract: Understanding how the structure of language can be learned from sentences alone is a central question in both cognitive science and machine learning. Studies of the internal representations of Large Language Models (LLMs) support their ability to parse text when predicting the next word, while representing semantic notions independently of surface form. Yet, which data statistics make these feats possible, and how much data is required, remain largely...