Compute Scaling
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models
arXiv:2504.04718v2 Announce Type: replace Abstract: Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs). However, prior research has mainly examined test-time compute scaling with an additional larger model as a verifier, leaving verification by sLMs underexplored. In this work, we investigate whether sLMs can reliably verify the output candidates under test-time scaling.
Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers
arXiv:2606.04678v1 Announce Type: new Abstract: End-to-end ASR systems typically use fixed-depth acoustic encoders at inference, making it difficult to trade additional test-time computation for improved recognition without training a larger model. A natural approach is to reuse a shared Transformer block recurrently, but we find that naive looping does not fully exploit additional recurrent compute. We introduce LARM, a depth-conditioned looped Transformer that turns recurrent encoder depth...
ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction
arXiv:2605.11212v3 Announce Type: replace Abstract: Computer-use agents (CUAs) rely on visual observations of graphical user interfaces, where each screenshot is encoded into a large number of visual tokens. As interaction trajectories grow, the token cost increases rapidly, limiting the amount of history that can be incorporated under fixed context and compute budgets. This has resulted in no or very limited improvement in the performance when using history unlike other domains.
Quantum computing for accurate large-scale electronic-structure calculations: DFT-embedded, post-processed quantum-selected configuration interaction
arXiv:2606.06015v1 Announce Type: new Abstract: We present a multilevel embedding framework for quantum chemistry calculations on a quantum computer. In our framework, a quantum algorithm treats the strongly correlated active space, while a high-level wave-function method such as coupled cluster theory or multireference perturbation theory recovers the remaining correlation in the surrounding region. A sampling-based quantum algorithm, quantum-selected configuration interaction, bridges the...
FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration
Announce Type: replace Abstract: Scaling test-time computation has been shown to significantly improve large language model (LLM) performance without additional training. However, extending these techniques to multi-agent systems remains challenging: existing approaches lack principled mechanisms for allocating compute to enable effective collaboration, scaling coordination itself, or optimizing compute usage under explicit budget constraints. To address this gap, we propose FutureWeaver, a...
Metasurfaces for neutral-atom trapping
arXiv:2605.30498v1 Announce Type: new Abstract: Trapped neutral atoms are one of the leading platforms for quantum information technologies, in particular for quantum computing, but scaling them to array sizes needed for utility-scale quantum computing is a major engineering challenge. Here we review optical metasurfaces as an enabling technology that provides fine control over the phase, amplitude, and polarization of light, with pixel counts far exceeding what is available with spatial...
Nanomagnets control diamond qubits, pointing to more scalable quantum hardware
Nanomagnets control diamond qubits, pointing to more scalable quantum hardware Gaby Clark Scientific Editor Robert Egan Associate Editor Quantum computing, once only a theoretical possibility, promises to deliver faster, more energy-efficient computers—but only if scientists can build and scale the hardware needed to run the machines. New research from Virginia Commonwealth University brings scientists one small step closer to quantum computing at a practical scale, which could help...
Chip-scale 'acoustic atom' controls sound waves to imitate atomic energy levels and advance computing
Chip-scale 'acoustic atom' controls sound waves to imitate atomic energy levels and advance computing Stephanie Baum Scientific Editor Robert Egan Associate Editor For every action, there is an equal and opposite reaction. What goes up must come down. Physical laws like these govern all of the natural world—except for the tiny internal components of today's microprocessors, which operate according to the unique and complicated rules of quantum physics.
Ablation Study of Block Size, Weight Precision, and Scale Precision in NVFP4 Inference for Low-Power Edge-Efficient Neural Networks
Announce Type: new Abstract: Energy-efficient edge inference requires reducing arithmetic cost, memory traffic, and hardware overhead. This paper presents an ablation-focused study of NVFP4 LUT-based inference for edge-efficient neural networks. The proposed NVLUT framework combines 4-bit NVFP4 activations, two-level scaling, LUT-based mantissa computation, voltage-scaled storage, and selective ECC protection.
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...